diff --git a/.all-contributorsrc b/.all-contributorsrc
index f0a57af..cd1d65b 100644
--- a/.all-contributorsrc
+++ b/.all-contributorsrc
@@ -1,8 +1,8 @@
{
"files": [
"README.md",
- "site/contents/contribute/contributors.md",
- "site/contents/about.md"
+ "site/contribute/contributors.md",
+ "site/index.md"
],
"imageSize": 100,
"commit": false,
@@ -19,16 +19,9 @@
"eventOrganizing",
"maintenance",
"infra",
- "doc"
- ]
- },
- {
- "login": "conorhoughton",
- "name": "Conor Houghton",
- "avatar_url": "https://avatars.githubusercontent.com/u/6955092?v=4",
- "profile": "https://github.com/conorhoughton",
- "contributions": [
- "fundingFinding"
+ "doc",
+ "research",
+ "code"
]
},
{
@@ -44,7 +37,18 @@
"a11y",
"doc",
"design",
- "bug"
+ "bug",
+ "research",
+ "code"
+ ]
+ },
+ {
+ "login": "conorhoughton",
+ "name": "Conor Houghton",
+ "avatar_url": "https://avatars.githubusercontent.com/u/6955092?v=4",
+ "profile": "https://github.com/conorhoughton",
+ "contributions": [
+ "fundingFinding"
]
},
{
@@ -64,27 +68,30 @@
"contributions": [
"eventOrganizing",
"ideas",
- "talks",
+ "talk",
"promotion",
- "a11y"
+ "a11y",
+ "research"
]
},
{
"login": "",
"name": "Kate Robson-Brown",
- "avatar_url": "http://www.bristol.ac.uk/media-library/sites/jean-golding-institute/images/people/kate-robson-brown-head-shot150x100.jpg",
- "profile": "https://research-information.bris.ac.uk/en/persons/kate-robson-brown",
+ "avatar_url": "https://www.turing.ac.uk/sites/default/files/styles/people/public/2018-07/kate-robson-brown-head-shot_0.jpg?itok=1lKG9FgK",
+ "profile": "https://www.turing.ac.uk/people/researchers/katharine-robson-brown",
"contributions": [
- "review"
+ "review",
+ "promotion"
]
},
{
"login": "",
"name": "Patricia Holley",
- "avatar_url": "http://www.bristol.ac.uk/media-library/sites/jean-golding-institute/images/people/patty-head-shot150x100.jpg",
+ "avatar_url": "https://www.bristol.ac.uk/media-library/sites/jean-golding-institute/images/people/PattyHolley_150x150.png",
"profile": "https://www.bris.ac.uk/contact/person/getDetails?personKey=9tNdYV3TvjDC0p0L3d6TSvZ4ligZa3",
"contributions": [
- "review"
+ "review",
+ "promotion"
]
},
{
@@ -111,7 +118,9 @@
"avatar_url": "https://avatars.githubusercontent.com/u/48878399?v=4",
"profile": "https://linkedin.com/in/jatonline",
"contributions": [
- "review"
+ "review",
+ "talk",
+ "promotion"
]
},
{
@@ -131,7 +140,9 @@
"contributions": [
"design",
"ideas",
- "promotion"
+ "promotion",
+ "research",
+ "talk"
]
},
{
@@ -163,6 +174,17 @@
"ideas"
]
},
+ {
+ "login": "",
+ "name": "Claire Haworth",
+ "avatar_url": "https://research-information.bris.ac.uk/ws/files/289337272/Claire_head_bristol_profile.jpg",
+ "profile": "https://www.bristol.ac.uk/people/person/Claire-Haworth-04ed5882-f1f6-4fb5-8960-5581b0cc8bc4/",
+ "contributions": [
+ "talk",
+ "fundingFinding",
+ "promotion"
+ ]
+ },
{
"login": "Susana465",
"name": "Susana Roman Garcia",
@@ -173,7 +195,8 @@
"talk",
"ideas",
"promotion",
- "eventOrganizing"
+ "eventOrganizing",
+ "research"
]
},
{
@@ -184,7 +207,7 @@
"contributions": [
"design",
"ideas",
- "support"
+ "video"
]
},
{
@@ -193,9 +216,11 @@
"avatar_url": "https://avatars.githubusercontent.com/u/85741581?v=4",
"profile": "https://github.com/HDiscoDay",
"contributions": [
+ "eventOrganizing",
"example",
"ideas",
- "promotion"
+ "promotion",
+ "research"
]
},
{
@@ -205,7 +230,198 @@
"profile": "http://melaniestefan.net/",
"contributions": [
"ideas",
- "talk"
+ "talk",
+ "research"
+ ]
+ },
+ {
+ "login": "",
+ "name": "Euan Bennet",
+ "avatar_url": "https://www.gla.ac.uk/media/Media_865350_smxx.jpg",
+ "profile": "https://www.gla.ac.uk/schools/bohvm/staff/euanbennet/",
+ "contributions": [
+ "research",
+ "talk",
+ "doc"
+ ]
+ },
+ {
+ "login": "",
+ "name": "Emma Kuwertz",
+ "avatar_url": "",
+ "profile": "https://www.bristol.ac.uk/people/person/Emma-Kuwertz-d6ca1344-b999-42ae-8603-db59266ad245/",
+ "contributions": [
+ "research",
+ "talk"
+ ]
+ },
+ {
+ "login": "",
+ "name": "Phil Clatworthy",
+ "avatar_url": "https://research-information.bris.ac.uk/ws/files/289033062/Phil_July_2020.png",
+ "profile": "https://www.bristol.ac.uk/people/person/Philip-Clatworthy-a349d87c-0b95-4779-91d2-edf71a214f2d/",
+ "contributions": [
+ "research"
+ ]
+ },
+ {
+ "login": "SamCallaghan",
+ "name": "SamCallaghan",
+ "avatar_url": "https://avatars.githubusercontent.com/u/39956651?v=4",
+ "profile": "https://github.com/SamCallaghan",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "kateliddell",
+ "name": "kateliddell",
+ "avatar_url": "https://avatars.githubusercontent.com/u/52200743?v=4",
+ "profile": "https://github.com/kateliddell",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "Dylan246456",
+ "name": "Dylan246456",
+ "avatar_url": "https://avatars.githubusercontent.com/u/108466203?v=4",
+ "profile": "https://github.com/Dylan246456",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "stefgrs",
+ "name": "stefgrs",
+ "avatar_url": "https://avatars.githubusercontent.com/u/16223692?v=4",
+ "profile": "https://github.com/stefgrs",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "harrietrs",
+ "name": "Harriet Sands",
+ "avatar_url": "https://avatars.githubusercontent.com/u/28767009?v=4",
+ "profile": "https://github.com/harrietrs",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "PeopleByNumbers",
+ "name": "Joanne Parkes",
+ "avatar_url": "https://avatars.githubusercontent.com/u/108466233?v=4",
+ "profile": "https://github.com/PeopleByNumbers",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "maelorin",
+ "name": "loki maelorin",
+ "avatar_url": "https://avatars.githubusercontent.com/u/3904823?v=4",
+ "profile": "https://github.com/maelorin",
+ "contributions": [
+ "doc"
+ ]
+ },
+ {
+ "login": "dsmukilan",
+ "name": "Mukilan Suresh",
+ "avatar_url": "https://avatars.githubusercontent.com/u/11191375?v=4",
+ "profile": "https://github.com/dsmukilan",
+ "contributions": [
+ "ideas"
+ ]
+ },
+ {
+ "login": "mcnanton",
+ "name": "mcnanton",
+ "avatar_url": "https://avatars.githubusercontent.com/u/42379883?v=4",
+ "profile": "https://github.com/mcnanton",
+ "contributions": [
+ "bug"
+ ]
+ },
+ {
+ "login": "",
+ "name": "Emma Kuwertz",
+ "avatar_url": "",
+ "profile": "https://www.bristol.ac.uk/people/person/Emma-Kuwertz-d6ca1344-b999-42ae-8603-db59266ad245/",
+ "contributions": [
+ "research",
+ "talk"
+ ]
+ },
+ {
+ "login": "CeilidhWelsh",
+ "name": "CeilidhWelsh",
+ "avatar_url": "https://avatars.githubusercontent.com/u/71887891?v=4",
+ "profile": "https://github.com/CeilidhWelsh",
+ "contributions": [
+ "talk",
+ "research",
+ "ideas"
+ ]
+ },
+ {
+ "login": "OliverDavis",
+ "name": "Oliver Davis",
+ "avatar_url": "https://avatars.githubusercontent.com/u/5032882?v=4",
+ "profile": "http://dynamicgenetics.org/",
+ "contributions": [
+ "talk",
+ "promotion"
+ ]
+ },
+ {
+ "login": "davidcsterratt",
+ "name": "David C Sterratt",
+ "avatar_url": "https://avatars.githubusercontent.com/u/4264803?v=4",
+ "profile": "http://homepages.inf.ed.ac.uk/sterratt",
+ "contributions": [
+ "research",
+ "ideas"
+ ]
+ },
+ {
+ "login": "nicolaromano",
+ "name": "Nicola RomanΓ²",
+ "avatar_url": "https://avatars.githubusercontent.com/u/208254?v=4",
+ "profile": "https://www.nicolaromano.net/",
+ "contributions": [
+ "research",
+ "ideas"
+ ]
+ },
+ {
+ "login": "l-gorman",
+ "name": "LΓ©o Gorman",
+ "avatar_url": "https://avatars.githubusercontent.com/u/55786252?v=4",
+ "profile": "https://www.turing.ac.uk/people/doctoral-students/leo-gorman",
+ "contributions": [
+ "talk"
+ ]
+ },
+ {
+ "login": "bengcooper",
+ "name": "Ben Cooper",
+ "avatar_url": "https://avatars.githubusercontent.com/u/3008392?v=4",
+ "profile": "https://github.com/bengcooper",
+ "contributions": [
+ "promotion",
+ "code"
+ ]
+ },
+ {
+ "login": "JennyBunn",
+ "name": "JennyBunn",
+ "avatar_url": "https://avatars.githubusercontent.com/u/29119194?v=4",
+ "profile": "https://github.com/JennyBunn",
+ "contributions": [
+ "doc"
]
}
],
diff --git a/.github/workflows/deploy_site.yml b/.github/workflows/deploy_site.yml
index 38aec3e..aabd852 100644
--- a/.github/workflows/deploy_site.yml
+++ b/.github/workflows/deploy_site.yml
@@ -20,10 +20,10 @@ jobs:
- uses: actions/checkout@v2
# Install dependencies
- - name: Set up Python 3.7
+ - name: Set up Python 3.9
uses: actions/setup-python@v1
with:
- python-version: 3.7
+ python-version: 3.9
- name: Install dependencies
run: |
diff --git a/.github/workflows/test-build.yml b/.github/workflows/test-build.yml
index 7a5e304..0969c55 100644
--- a/.github/workflows/test-build.yml
+++ b/.github/workflows/test-build.yml
@@ -22,7 +22,7 @@ jobs:
- name: Set up Python 3.7
uses: actions/setup-python@v1
with:
- python-version: 3.7
+ python-version: 3.9
- name: Install dependencies
run: |
diff --git a/.gitignore b/.gitignore
index be5566c..299e993 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,6 +8,8 @@ presentations/
.Rproj.user/
.Rhistory
data/
+venv/
+node_modules/
# Storage for misc docs I don't want to commit (e.g abstracts/bios)
misc_docs/
diff --git a/README.md b/README.md
index 1aff116..289d2f2 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
# Data Hazards Project
[![DOI](https://zenodo.org/badge/346286403.svg)](https://zenodo.org/badge/latestdoi/346286403)
-[![All Contributors](https://img.shields.io/badge/all_contributors-16-orange.svg?style=flat-square)](#contributors-)
+[![All Contributors](https://img.shields.io/badge/all_contributors-40-orange.svg?style=flat-square)](#contributors-)
@@ -45,27 +45,56 @@ If you'd like to join us as a contributor, check out our [contributor's guide](h
diff --git a/analysis/infographics.Rmd b/analysis/infographics.Rmd
deleted file mode 100644
index d138bd9..0000000
--- a/analysis/infographics.Rmd
+++ /dev/null
@@ -1,91 +0,0 @@
----
-title: "infographics - Workshop 1 (Sept 2021)"
-author: "Natalie Thurlby"
-date: "9/30/2021"
-output: html_document
----
-
-This document creates the info-graphics from Data Hazards Workshop 1 - Sept 2021 - academic focus.
-These info-graphics visualise things like how many people found the hazards useful.
-
-```{r setup, include=FALSE}
-knitr::opts_chunk$set(echo = TRUE)
-```
-
-```{r}
-library(tidyverse)
-library(waffle)
-```
-## Read in and clean data
-
-### Data provenance
-The data is stored in a private folder called `data`, within the analysis folder. Data can be downloaded from [this](https://uob.sharepoint.com/:f:/r/teams/grp-ethicaldatascience/Shared%20Documents/Data%20Hazards/Results?csf=1&web=1&e=6pvo8u) SharePoint folder, for researchers working on the project only (at time of writing Natalie and Nina).
-
-The data was collected through a series of surveys via wualtrics, for which the exact questions can be seen on the [Data Hazards project OSF page](https://osf.io/3fv7t/).
-
-### Read in data
-
-```{r cars}
-survey_data <- read_csv('data/data-hazards-workshop-21-sept-2021.csv')
-```
-### Rename labels
-```{r}
-survey_data <- rename(survey_data,
- Name=Q28,
- AttendeeType=Q27,
- ProjOwner=`Proj Title`,
- HazardsPre=`Hazards Pre 1`,
- HazardsComments1=`Hazards Comments`,
- HazardsPost=`Hazards Post 1`,
- HazardsComments2=Q18,
- Clarity=Q20,
- Ease=Q24,
- UsefulHazards=Q21,
- UsefulDiscussion=Q26,
- Learning=Q23,
- OverallHazards=Q27_1,
- OverallWorkshop=Q28_1,
- EncourageParticipation=Q29,
- )
-```
-
-### Data cleaning
-
-Remove first row and use as a lookup for actual wording of questions
-```{r}
-question_wording <- survey_data[1,]
-survey_data <- survey_data[-1,]
-```
-
-## Plots
-To create the pictograms, I followed [this tutorial](https://rud.is/rpubs/building-pictograms.html) as a guide.
-
-```{r}
-```
-
-```{r}
-extrafont::font_import('~/Downloads/fontawesome-free-5.15.4-web/', prompt=FALSE)
-```
-
-
-### How useful did you think the Data Hazards were for exploring potential downfalls of data science projects?
-```{r}
-qscale <- c("1"="Very Useful",
- "2"="Useful",
- "3"="Neutral",
- "4"="Not useful",
- "5"="Not useful at all")
-text <- question_wording$UsefulHazards
-data <- tibble(survey_data$UsefulHazards)
-#data$qscale = qscale[data]
-qscale[data]
-i```
-```{r pressure, echo=FALSE}
-# TODO: Change format of data so that it works in the geom_waffle
-#ggplot(survey_data, aes(fill=UsefulHazards, values=UsefulHazards)) +
-# waffle::geom_waffle()
-ggplot(xdf, aes(fill=vals)) +
- waffle::geom_waffle()
-```
-
-Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.
diff --git a/analysis/nina-analysis/hazard-ratings-graph.Rmd b/analysis/nina-analysis/hazard-ratings-graph.Rmd
deleted file mode 100644
index 7110d37..0000000
--- a/analysis/nina-analysis/hazard-ratings-graph.Rmd
+++ /dev/null
@@ -1,158 +0,0 @@
----
-title: "Hazard Ratings Graph"
-author: "Nina Di Cara"
-date: "30/09/2021"
-output: html_document
----
-
-```{r setup, include=FALSE}
-knitr::opts_chunk$set(echo = TRUE)
-
-library(here)
-library(dplyr)
-library(tidyr)
-library(ggplot2)
-
-data <- read.table(here("..", "data", "21-sept-survey.txt"), sep = "\t", header = TRUE, encoding="utf-8")
-
-# Add a person ID colum
-data$ID <- seq.int(nrow(data))
-
-# Do some initial tidying
-data <- data %>%
- mutate(project = as.factor(project))
-
-hazards <- c(
- "Data Science (general)",
- "Automates decision making",
- "Classifies or ranks people",
- "Difficult to understand",
- "Lacks community involvement",
- "Lacks informed consent",
- "Danger of misuse",
- "May cause direct harm",
- "High environmental cost",
- "Risk to privacy",
- "Reinforces existing biases"
-)
-
-```
-
-
-```{r scores}
-
-data %>%
- select(contains("eval")) %>%
- mutate(across(everything(), as.factor)) %>%
- pivot_longer(cols = everything(), names_to = "Question", values_to = "Score", names_prefix = "eval.") %>%
- drop_na() %>%
- count(Question, Score) %>%
- write.csv(., here("..", "data", "ratings.csv"))
-
-```
-
-
-```{r get-rankings}
-
-# Overwrite data with a longer version of the hazard ratings data, so the timepoint of the ratings is a column
-data <- data %>%
- select(ID, role, project, hazards.1, hazards.2) %>%
- pivot_longer(cols = c("hazards.1", "hazards.2"), names_pattern = "hazards.(.)", values_to = "hazards") %>%
- rename(timepoint = name)
-
-ratings <- data %>% pull("hazards") %>% strsplit(., ",")
-
-# Initialise objects
-i = 1
-ratings_clean <-vector("list",42)
-
-# This loop will go through each set of responses and indicate if each hazard is present or not.
-for (response in ratings) {
-
- # Set up a list for the next person's responses
- next_response <- c(i)
-
- # Make a vector of TRUE/FALSE if each hazard is in the list
- for (hazard in hazards) {
- val <- hazard %in% response
- next_response <- c(next_response, val)
- }
-
- # Add the next response to the list of clean ratings
- ratings_clean[[i]] <- next_response
-
- # Increase i for the next iteration
- i = i + 1
-}
-
-ratings_clean <- as.data.frame(do.call(rbind, ratings_clean))
-colnames(ratings_clean) <- c("ID", hazards)
-ratings_clean <- ratings_clean %>% select(!ID)
-
-# Add the ratings back to the main dataset
-data <- cbind(data, ratings_clean)
-
-# Remove data no longer needed
-rm(ratings, ratings_clean)
-
-```
-
-```{r graph}
-
-data %>%
- mutate(ID = as.factor(ID), # Change this so it doesn't get caught in 'numeric' net
- timepoint = as.factor(timepoint),
- timepoint = recode_factor(timepoint,
- "1" = "Before", "2" = "After")) %>%
- group_by(project, timepoint) %>%
- summarise(across(where(is.numeric), sum)) %>%
- ungroup() %>%
- pivot_longer(cols = hazards, names_to = "hazard", values_to = "ratings") %>%
- ggplot(aes(x=ratings, y=hazard)) +
- geom_line(aes(group = hazard)) +
- geom_point(aes(color = timepoint), size = 3) +
- facet_wrap(~project) +
- theme_bw() +
- xlab("\nNumber of times selected") +
- ylab("Hazard Label\n") +
- guides(color=guide_legend(title="Timepoint"))
-
-ggsave("rating-changes.png", width = 6, height = 4, units = "in", dpi=330)
-
-```
-
-
-```{r graph2}
-
-data %>%
- mutate(ID = as.factor(ID), # Change this so it doesn't get caught in 'numeric' net
- timepoint = as.factor(timepoint),
- timepoint = recode_factor(timepoint,
- "1" = "Before", "2" = "After")) %>%
- select(!hazards) %>%
- pivot_longer(cols = hazards, names_to = "hazard", values_to = "ratings") %>%
- pivot_wider(names_from = "timepoint", values_from = "ratings") %>%
- mutate(diff = After - Before) %>%
- count(hazard, diff) %>%
- ungroup() %>%
- mutate(value = diff * n) %>%
- #pivot_wider(names_from = diff, values_from = n, values_fill = 0) %>%
- #rename("Up" = "1", "Down" = "-1") %>%
- # Make into a pyramid plot
- ggplot(aes(y = hazard, x = value)) +
- geom_point(aes(color = as.factor(diff)), size = 3) +
- #geom_line(arrow = arrow(ends="first", type = "closed")) +
- #geom_line(arrow = arrow(ends="last", type = "closed")) +
- geom_arrow(start = 0) +
- theme_minimal() +
- theme(panel.grid.minor = element_blank()) +
- #coord_flip() +
- ylab("Hazard Label\n") +
- xlab("\nNumber of people who added or removed labels")
-
- # geom_bar(aes(y = -Down), stat = "identity", fill = "#fc8d62") +
- # geom_bar(aes(y = Up), stat = "identity", fill = "#66c2a5") +
-
-
-# ggsave("ratings-moved.png", width = 6, height = 4, units = "in", dpi=330)
-```
\ No newline at end of file
diff --git a/analysis/nina-analysis/rating-changes.png b/analysis/nina-analysis/rating-changes.png
deleted file mode 100644
index 1b2cd51..0000000
Binary files a/analysis/nina-analysis/rating-changes.png and /dev/null differ
diff --git a/analysis/nina-analysis/ratings-moved.png b/analysis/nina-analysis/ratings-moved.png
deleted file mode 100644
index c94b9d1..0000000
Binary files a/analysis/nina-analysis/ratings-moved.png and /dev/null differ
diff --git a/package.json b/package.json
new file mode 100644
index 0000000..8d26c18
--- /dev/null
+++ b/package.json
@@ -0,0 +1,5 @@
+{
+ "devDependencies": {
+ "all-contributors-cli": "^6.26.1"
+ }
+}
diff --git a/requirements.txt b/requirements.txt
index 913125d..ca3c8cc 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,6 @@
-sphinx<5,>=2
-pydata-sphinx-theme
-myst-nb
-sphinx-panels
+pydata-sphinx-theme >= 0.15.2 # https://pypi.org/project/pydata-sphinx-theme/
+sphinx >= 7.2.6 # https://pypi.org/project/Sphinx/
+sphinx-design >= 0.5 # https://pypi.org/project/sphinx_design/
+myst-parser >= 2.0.0 # https://pypi.org/project/myst-parser/
+
+# NB - These versions require Python 3.9 or greater.
\ No newline at end of file
diff --git a/site/_static/custom.css b/site/_static/custom.css
index 76ca9cd..1aadc7d 100644
--- a/site/_static/custom.css
+++ b/site/_static/custom.css
@@ -28,3 +28,21 @@ div.timeline div.entry.left::after {
div.timeline div.entry.right::after {
left: -.5em;
}
+
+.sd-card-img-top {
+ padding-right: 5%;
+ padding-left: 5%;
+ padding-top: 5%;
+}
+
+html[data-theme="light"] {
+ --sd-color-card-background: #ffc404;
+ --pst-color-primary: #385f3e;
+ --pst-color-secondary: #ff5c3b;
+}
+
+html[data-theme="dark"] {
+ --pst-color-primary: white;
+ --pst-color-primary: #385f3e;
+ --pst-color-secondary: #ff5c3b;
+}
\ No newline at end of file
diff --git a/site/_templates/contact.html b/site/_templates/contact.html
new file mode 100644
index 0000000..41d79c4
--- /dev/null
+++ b/site/_templates/contact.html
@@ -0,0 +1 @@
+Contact the Data Hazards Team
\ No newline at end of file
diff --git a/site/about.md b/site/about.md
new file mode 100644
index 0000000..c65782f
--- /dev/null
+++ b/site/about.md
@@ -0,0 +1,227 @@
+# About
+
+The image below describes the 'anatomy' of a Data Hazard label.
+
+```{image} images/hazardanatomy.png
+:width: 70%
+:alt: All Hazard labels have an descriptive icon, title, description, examples and suggesed safety precautions.
+```
+
+
+
+
+## How the project started
+
+The Data Hazards project started in 2021.
+We (Natalie Zelenka and Nina Di Cara) spoke together about wanting a way to communicate what might
+go wrong in data science projects, because we were frustrated by the repetitive themes we were seeing
+in harmful technologies that we talked about in [Data Ethics Club](https://dataethicsclub.com).
+We were also concerned that many projects that have significant societal impact do not have those impacts
+scrutinised by an ethics committee, because they do not technically have research participants.
+
+After this conversation we came up with the idea of Hazard labels for communicating these potential harms,
+and called them Data Hazards.
+We decided they should be visual, like COSHH chemical hazards are, and that they should be a way for
+people at all stages of data science technology development to communicate about the same potential
+outcomes (no matter how far away those outcomes might seem).
+
+You can see [the current Data Hazard labels here](labels).
+You can [read our original proposal here](materials/misc/proposal).
+
+These days the project is bigger than just us, and we have many contributors who suggest new content,
+changes to the labels, help us to teach others about ethical hazards or run their own events.
+If you would like to get involved (we'd love you to!) then we've listed lots of ways
+you could on our [Contributing page](contribute).
+
+Once we had thought of the original list of Hazards we wanted a way for researchers to think about them in
+a format that encouraged them to reflect, invite different opinions and make them think more broadly about
+the potential ethical concerns from their project.
+This led to the development of our workshop format and [all the materials we have since made](materials)
+for self-reflection and teaching.
+All our resources are designed (and licensed) for re-use by others.
+
+
+## Ethos
+
+The Data Hazards are currently intended to be used creatively and flexibly, in whatever way they are useful
+to the user.
+Sometimes this means they are flashcards for teaching students about ethics, sometimes they are displayed with
+new research to communicate potential harms, and sometimes they are used in workshops as prompts.
+
+We believe it is important when using the Data Hazards to help investigate risks in a project, that people
+beyond the original researcher are consulted on potential hazards.
+This is because we believe that knowledge, including in the sciences, is not objective, and that our
+perspectives are shaped by our lived socio-political experiences (this is based on [standpoint theory](https://en.wikipedia.org/wiki/Standpoint_theory)).
+This means that ethical problems are not going to have a single correct answer, and that to get a well-rounded understanding of the ethical issues of any new technology we need people from lots of different standpoints to analyse it from their perspective.
+This is the best way we can understand the harms it could possibly cause.
+We also need to make sure that we are paying attention to how technology might be more likely to adversely affect people from minoritised backgrounds.
+
+We developed our [workshop format](materials/workshop) to help researchers to gather these different views.
+
+In summary, the Data Hazards exist to prompt discussion, reflection and thought.
+They are not a checkbox exercise, and there is no requirement for a group to come to a consensus.
+In an individual context you will likely come to a conclusion, but someone else may have a different view.
+We hope that the Data Hazards discussion and reflective activities will help researchers be aware of a broader variety of potential ethical risks in tech projects, and that ethics is complex, situational and worth discussing.
+
+
+## Contact
+
+The Data Hazards Project was founded by Dr Natalie Zelenka and Dr Nina Di Cara, and is now co-led by Natalie, Nina and Dr Huw Day. Our details are provided below.
+We're always keen to hear from people interested in the project, or wanting to get involved. Feel free to send us both an email, or you can find us on Twitter!
+
+```{list-table}
+:header-rows: 1
+
+* - __Nina Di Cara__
+ - __Natalie Zelenka__
+ - __Huw Day__
+* - Senior Research Associate, School of Psychological Science, University of Bristol
+ - Senior Research Fellow in Health Data Science, Institute of Health Informatics, University College London
+ - Data Scientist, Jean Golding Institute, University of Bristol
+* - GitHub: [@ninadicara](https://github.com/ninadicara)
+ - GitHub: [@NatalieZelenka](https://github.com/NatalieZelenka)
+ - GitHub: [@HuwWDay](https://github.com/HuwWDay)
+* - Twitter/X: [@ninadicara](https://twitter.com/ninadicara)
+ - Twitter/X: [@NatZelenka](https://twitter.com/NatZelenka)
+ - Twitter/X: [@disco_huw](https://twitter.com/disco_huw)
+* - Email: [nina.dicara@bristol.ac.uk](mailto:nina.dicara@bristol.ac.uk)
+ - Email: [n.zelenka@ucl.ac.uk](mailto:n.zelenka@ucl.ac.uk)
+ - Email: [huw.day@bristol.ac.uk](mailto:huw.day@bristol.ac.uk)
+```
+
diff --git a/site/contents/code-of-conduct.md b/site/code-of-conduct.md
similarity index 99%
rename from site/contents/code-of-conduct.md
rename to site/code-of-conduct.md
index 28fceab..c1feeba 100644
--- a/site/contents/code-of-conduct.md
+++ b/site/code-of-conduct.md
@@ -32,7 +32,7 @@ The below Do-s and Donβt-s are guidelines to remind us all of best standards o
## Reporting Procedure
If you have been subject to or witnessed unacceptable behaviour, either during a meeting or on this repository, then you can get in touch with either Natalie or Nina.
-Natalie: natalie.zelenka@bristol.ac.uk
+Natalie: n.zelenka@ucl.ac.uk
Nina: nina.dicara@bristol.ac.uk
If you would prefer to contact someone who is not directly involved in organising the group, then you can direct your concerns to John Newby ([JGI Manager](http://www.bristol.ac.uk/golding/people/team/)), at [John.Newby@bristol.ac.uk](mailto:John.Newby@bristol.ac.uk)
diff --git a/site/conf.py b/site/conf.py
index 6bd8b9b..54bf280 100644
--- a/site/conf.py
+++ b/site/conf.py
@@ -18,7 +18,7 @@
# -- Project information -----------------------------------------------------
project = "Data Hazards"
-copyright = "2023, Natalie Zelenka and Nina Di Cara"
+copyright = "2024, Natalie Zelenka and Nina Di Cara"
author = "Natalie Zelenka and Nina Di Cara"
# The full version, including alpha/beta/rc tags
@@ -31,8 +31,13 @@
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
- "myst_nb",
- "sphinx_panels",
+ "myst_parser",
+ "sphinx_design",
+]
+
+#Β Enable use of ::: https://myst-parser.readthedocs.io/en/latest/syntax/optional.html#code-fences-using-colons
+myst_enable_extensions = [
+ "colon_fence",
]
# Add any paths that contain templates here, relative to this directory.
@@ -51,6 +56,7 @@
#
html_theme = "pydata_sphinx_theme"
+html_baseurl = "datahazards.com"
html_theme_options = {
"use_edit_page_button": True,
@@ -73,7 +79,7 @@
],
"search_bar_text": "Search this site...",
"show_prev_next": False,
- "footer_items": ["license-footer", "sphinx-version"],
+ "footer_items": ["license-footer", "contact"],
"navbar_end": ["navbar-icon-links"], # removes light/dark mode
"logo": {
"text": "Data Hazards",
@@ -90,12 +96,13 @@
html_sidebars = {
"index": [],
- "contents/data-hazards": [],
- "contents/sign-up": [],
- "contents/contact": [],
+ "about": [],
+ "contact": [],
+ "labels": [],
}
html_favicon = "_static/favicon.png"
+html_logo = "_static/favicon.png"
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
diff --git a/site/contents/about.md b/site/contents/about.md
deleted file mode 100644
index d54c674..0000000
--- a/site/contents/about.md
+++ /dev/null
@@ -1,246 +0,0 @@
-# About
-
-Read more about the origin of the project and its ethos, contributors and timeline here.
-
-
-
-
-
-## How the project started
-
-The Data Hazards project started in 2021.
-We (Natalie Zelenka and Nina Di Cara) spoke together about wanting a way to communicate what might
-go wrong in data science projects, because we were frustrated by the repetitive themes we were seeing
-in harmful technologies that we talked about in [Data Ethics Club](https://dataethicsclub.com).
-We were also concerned that many projects that have significant societal impact do not have those impacts
-scrutinised by an ethics committee, because they do not technically have research participants.
-
-After this conversation we came up with the idea of Hazard labels for communicating these potential harms,
-and called them Data Hazards.
-We decided they should be visual, like COSHH chemical hazards are, and that they should be a way for
-people at all stages of data science technology development to communicate about the same potential
-outcomes (no matter how far away those outcomes might seem).
-
-You can see [the current Data Hazard labels here](data-hazards).
-You can [read our original proposal here](materials/misc/proposal).
-
-These days the project is bigger than just us, and we have many contributors who suggest new content,
-changes to the labels, help us to teach others about ethical hazards or run their own events.
-If you would like to get involved (we'd love you to!) then we've listed lots of ways
-you could on our [Contributing page](contribute).
-
-
-
-Once we had thought of the original list of Hazards we wanted a way for researchers to think about them in
-a format that encouraged them to reflect, invite different opinions and make them think more broadly about
-the potential ethical concerns from their project.
-This led to the development of our workshop format and [all the materials we have since made](materials)
-for self-reflection and teaching.
-All our resources are designed (and licensed) for re-use by others.
-
-
-## Ethos
-
-The Data Hazards are currently intended to be used creatively and flexibly, in whatever way they are useful
-to the user.
-Sometimes this means they are flashcards for teaching students about ethics, sometimes they are displayed with
-new research to communicate potential harms, and sometimes they are used in workshops as prompts.
-
-We believe it is important when using the Data Hazards to help investigate risks in a project, that people
-beyond the original researcher are consulted on potential hazards.
-This is because we believe that knowledge, including in the sciences, is not objective, and that our
-perspectives are shaped by our lived socio-political experiences (this is based on [standpoint theory](https://en.wikipedia.org/wiki/Standpoint_theory)).
-This means that ethical problems are not going to have a single correct answer, and that to get a well-rounded understanding of the ethical issues of any new technology we need people from lots of different standpoints to analyse it from their perspective.
-This is the best way we can understand the harms it could possibly cause.
-We also need to make sure that we are paying attention to how technology might be more likely to adversely affect people from minoritised backgrounds.
-
-We developed our [workshop format](materials/workshop) to help researchers to gather these different views.
-
-In summary, the Data Hazards exist to prompt discussion, reflection and thought.
-They are not a checkbox exercise, and there is no requirement for a group to come to a consensus.
-In an individual context you will likely come to a conclusion, but someone else may have a different view.
-We hope that the Data Hazards discussion and reflective activities will help researchers be aware of a broader variety of potential ethical risks in tech projects, and that ethics is complex, situational and worth discussing.
-
-
-## Contributors
-
-Our brilliant contributors are listed here, and you can [read more detail about our contributing process here](contribute).
-
-
-
-
-
-
-
-
-
-
-
-
-(project-timeline)=
-## Project timeline
-
-Here's a rough project timeline that tells the rough history of the project, and sometimes what we have coming up!
-
-````{panels}
-:container: timeline
-:column: col-6 p-0
-:card:
-
----
-:column: +left
----
-:column: +entry right
-
-__March-April 2021__: Behind the scenes plans
-^^^
-
-{fa}`check,text-success mr-1` Thinking, reading and planning.
-
-{fa}`check,text-success mr-1` Writing [proposal](materials/misc/proposal).
-
-{fa}`check,text-success mr-1` Getting feedback on initial ideas.
-
----
-:column: +entry left
-
-__May-Aug 2021__: Prepare for first Data Hazards workshop
-^^^
-
-{fa}`check,text-success mr-1` Launched the website.
-
-{fa}`check,text-success mr-1` Submitted ethics application.
-
-{fa}`check,text-success mr-1` Prepare materials and begin advertising.
-
-{fa}`check,text-success mr-1` Set up [Open Science Framework project](https://osf.io/3fv7t/) and [preregister](https://osf.io/pcv7j) analysis.
-
----
-:column: +right
----
-:column: +left
-
----
-:column: +entry right
-
-__Sept 2021__ Run first Data Hazards workshops (academic-focused)
-^^^
-
-{fa}`check,text-success mr-1` Ran the [first Data Hazards workshop](events/2021-09-21_workshop) on __21st Sept 2021__.
-
----
-:column: +entry left
-
-__Oct 2021__ Use workshop feedback to improve data hazards and present early results
-
-^^^
-
-{fa}`check,text-success mr-1` Presented early results from workshop at [AI Ethics Best Practices and the Future of Innovation](https://www.eventbrite.co.uk/e/ai-ethics-best-practices-and-the-future-of-innovation-tickets-173883098027) as part of [Bristol Tech Festival](https://bristoltechfest.org/) on __13th Oct 2021__ ([slides](events/bristol-tech-fest)).
-
-{fa}`check,text-success mr-1` Used workshop feedback to make improvements to the Hazard labels and workshop materials.
-
----
-:column: +right
-
----
-:column: +left
-
----
-:column: +entry right
-
-__Jan 2021__ Awarded Β£20,000 Enhancing Research Culture funding
-^^^
-{fa}`check,text-success mr-1` Set up our new project to deliver a 'train-the-trainer' for Data Hazards.
-
----
-:column: +entry left
-
-__Feb-May 2022__ Developed new labels and facilitator training materials
-^^^
-{fa}`check,text-success mr-1` Hired animator to create animated explainers for Data Hazards and new Hazard labels.
-
-{fa}`check,text-success mr-1` Developmed and released run-your-own workshop materials.
-
-{fa}`check,text-success mr-1` We went to MozFest 2022 to run a Data Hazards workshop!
----
-:column: +right
-
----
-:column: +left
-
----
-:column: +entry right
-
-__June 2022__: Run our facilitator workshops
-^^^
-{fa}`check,text-success mr-1` Ran a Data Hazards workshop as part of the Jean Golding Institute Showcase.
-
-{fa}`check,text-success mr-1` Ran our first Data Hazards facilitator workshop in-person as part of Bristol Data Week.
-
-{fa}`check,text-success mr-1` Ran our second (online) Data Hazards facilitator workshop.
-
----
-:column: +entry left
-
-__July-Dec 2022__: Prepare for first version release
-^^^
-
-{fa}`check,text-success mr-1` Analyse all the results and feedback from five total workshops.
-
-{fa}`check,text-success mr-1` Applied (successfully) for launch event funding from [UKRN](https://www.ukrn.org/about/).
-
-{fa}`check,text-success mr-1` Collect all previous suggestions for the project and think about future versions.
-
----
-:column: +right
-
----
-:column: +left
-
----
-:column: +entry right
-
-__March 2023__: Version 1.0 Release!
-^^^
-
-{fa}`check,text-success mr-1` Attend AI UK 2023 as exhibitors!
-
-- 29th March we will run the Data Hazards V1.0 Launch event!
-
-- We will release a pre-print of our first paper about the project!
-
-````
-
diff --git a/site/contents/contact.md b/site/contents/contact.md
deleted file mode 100644
index b39339d..0000000
--- a/site/contents/contact.md
+++ /dev/null
@@ -1,24 +0,0 @@
-# Contact
-
-The Data Hazards Project was founded by Dr Natalie Zelenka and Dr Nina Di Cara, and is now co-led by Natalie, Nina and Huw Day. Our details are provided below.
-We're always keen to hear from people interested in the project, or wanting to get involved. Feel free to send us both an email, or you can find us on Twitter!
-
-
-```{list-table}
-:header-rows: 1
-
-* - __Nina Di Cara__
- - __Natalie Zelenka__
- - __Huw Day__
-* - Senior Research Associate, School of Psychological Science, University of Bristol
- - Senior Research Fellow in Health Data Science, Institute of Health Informatics, University College London
- - Data Scientist, Jean Golding Institute, University of Bristol
-* - GitHub: [@ninadicara](https://github.com/ninadicara)
- - GitHub: [@NatalieZelenka](https://github.com/NatalieZelenka)
- - GitHub: [@HuwWDay](https://github.com/HuwWDay)
-* - Twitter/X: [@ninadicara](https://twitter.com/ninadicara)
- - Twitter/X: [@NatZelenka](https://twitter.com/NatZelenka)
- - Twitter/X: [@disco_huw](https://twitter.com/disco_huw)
-* - Email: [nina.dicara@bristol.ac.uk](mailto:nina.dicara@bristol.ac.uk)
- - Email: [n.zelenka@ucl.ac.uk](mailto:n.zelenka@ucl.ac.uk)
- - Email: [huw.day@bristol.ac.uk](mailto:huw.day@bristol.ac.uk)
diff --git a/site/contents/contribute/changelog.md b/site/contents/contribute/changelog.md
deleted file mode 100644
index 63e2299..0000000
--- a/site/contents/contribute/changelog.md
+++ /dev/null
@@ -1,25 +0,0 @@
-# Change log
-
-The change log records when changes that have been made to the project and gives a brief description of what the changes were.
-The change log started in March 2022.
-The most recent changes should be at the top of the list.
-
-
-
-## 06.12.2022: Update new Hazard labels
-[@ninadicara](https://github.com/ninadicara)
-Updated all the images of the Hazards with our new labels designed by the amazing [Yasmin Dwiputri](http://yasmindwiputri.com/)!
-
-
-## 07.03.2022: Move Data Hazards to individual pages
-[@ninadicara](https://github.com/ninadicara)
-Moved all of the Hazards to their own individual pages, and linked them from the original sphinx panels.
-Also capitalised all of the names so that they are consistently named.
-This should make it easier for people to contribute to a single Hazard and record their contribution against it :)
-
-
-
diff --git a/site/contents/contribute/contributors.md b/site/contents/contribute/contributors.md
deleted file mode 100644
index 8a0240c..0000000
--- a/site/contents/contribute/contributors.md
+++ /dev/null
@@ -1,96 +0,0 @@
-# Record of contributions
-
-The Data Hazards project exists because of the support and contributions of the many different people below.
-Please also note that people have also anonymously contributed ideas and resources to the project that Nina and Natalie have added on their behalf.
-
-
-
-
-
-
-
-
-
-
-This page is a place where anyone who has contributed to the project can be recognised for the time, effort and expertise they have given to Data Hazards.
-
-This page is based on a similar model used by [The Turing Way](https://github.com/alan-turing-institute/the-turing-way/blob/main/contributors.md) for recognising contributors to open source projects.
-
-We welcome anyone asking to be added to this page if they have made a contribution.
-You can read about different ways to contribute to the project in our [contributors guide](how-to-contribute).
-To be added, please [submit an issue](https://github.com/very-good-science/data-hazards/issues), make a pull request, or [send us an email](mailto:grp-ethicaldatascience@groups.bristol.ac.uk) which includes the following details:
-* Your Name
-* Your Role and Affiliation
-* (Optional) ORCID ID or other persistent identifier
-* (Optional) Personal contact details or website
-* Overview of your contribution to the Data Hazards Project - please don't be modest!
-
-
-## Contributors
-
-
-
-### Nina Di Cara
-* Role: Co-PI
-* ORCID [0000-0002-6179-1067](https://orcid.org/0000-0002-6179-1067)
-* GitHub: [ninadicara](https://github.com/ninadicara)
-> Along with Natalie I worked on the original idea for the Data Hazards, created resources around them (like teaching materials, slides, reflective prompts, illustrations), planned and delivered our workshops, and the website content. Jointly Natalie and I provide leadership for the project in terms of its next steps and uses. I care a lot about reducing the harm that technology can do to people who may not have power to fight back against, and hope this projects goes some way to making us all think more carefully about what we can all do as individuals to prevent harm. I am also thrilled to have been able to work with (and continue to work with) all the fantastic people who have got involved with this project!
-
-
-### Natalie Zelenka
-* Role: Co-PI
-* ORCID: [0000-0002-1007-0286](https://orcid.org/0000-0002-1007-0286)
-* GitHub: [NatalieZelenka](https://github.com/NatalieZelenka)
-> As a co-lead of the Data Hazards project, I developed the idea for Data Hazards with Nina, wrote lesson materials and proposals and drafted papers, designed images, found funding, and did lots of planning. Me and Nina shared these leadership and organisational tasks 50-50, but we are so grateful for everyone's contributions and support so far. I hope that - like some of the work that I'm [most](https://the-turing-way.netlify.app/) [inspired](https://reproducibilitea.org/) [by](https://carpentries.org/) - these materials *reduce barriers* for researchers. In this case, I hope Data Hazards makes it easier for data scientists to consider the ethical implications of their work and to make those decisions together with the communities who are affected by the work they are doing.
-
-### Ismael Kherrouvi Garcia
-
-* Role: Workshop facilitator (and huge fan!)
-* ORCID: [0000-0002-6850-8375](https://doi.org/0000-0002-6850-8375)
-* Find me on :octocat: [Ismael-KG](https://github.com/Ismael-KG), and Twitter ([@hermeneuticist](https://twitter.com/hermeneuticist))
-> In September 2021, I was delighted to facilitate a workshop alongside [@NatalieZelenka](https://github.com/NatalieZelenka) and [@ninadicara](https://github.com/ninadicara) to [test the Data Hazard labels](https://www.bristol.ac.uk/golding/events/2021/data-hazards-workshop---21-september-2021.html) with researchers from diverse backgrounds. This meant working with Natalie and Nina to familiarise myself with [the prompts they had prepared](https://github.com/very-good-science/data-hazards/blob/ae2ecfad7f85fe48670ed6221a6563353d31e77b/images/worst-case-prompt.png), and then keeping the conversation flowing during breakout rooms with workshop participants. I had previously gathered feedback from The Alan Turing Institute's [Ethics Advisory Group](https://www.turing.ac.uk/research/data-ethics/ethics-advisory-group) (EAG) for the Data Hazard labels. My time with the Turing's EAG allowed me to appreciate the value of the Data Hazard labels, both in the context of training data scientists on questions of ethics, and for preparing documentation for the review of research ethics committees.
-
-
-### Melanie I Stefan
-
-* Role: Early adopter
-* ORCID: [0000-0002-6086-7357](https://orcid.org/my-orcid?orcid=0000-0002-6086-7357)
-* GitHub: [MelanieIStefan](https://github.com/MelanieIStefan)
-> I was introduced to Data Hazards by the wonderful [@Susana465](https://susana465.github.io/), and it has informed my thinking and practice ever since. I helped facilitate a workhop on Data Hazards at [COMBINE 2022 in Berlin](https://co.mbine.org/author/combine-2022/), and also talked about how I use the Data Hazards framework to flag up potential issues with my own lecture materials at the [Data Hazards, Ethics and Reproducibility One-Day Symposium](https://www.eventbrite.com/e/online-data-hazards-ethics-and-reproducibility-one-day-symposium-tickets-517490858087) at the Turing Institute in 2023. I am also involved in the discussion on the Data Hazards labels themselves.
-
-### Susana Roman Garcia
-
-* Role: Workshop facilitator, content developer of the Data Hazards application to different settings, especially Neuroscience, PhD case study application of Data Hazards
-* ORCID ID: [0009-0004-6967-7754](https://orcid.org/0009-0004-6967-7754)
-* [Personal website](https://susana465.github.io/website/)
-> I came across the Data Hazards project as I looked for a way to embed thinking about ethics into my PhD, around 2021/22. Since then, I have attended a facilitator training workshop given by Nina and Natalie; and applied the Data Hazards framework to my PhD as I go along. To showcase this, I made a [poster presentation](https://github.com/Susana465/Bias-and-Reproducibility-Poster/blob/main/README.md) for the [COMBINE](https://combine-org.github.io/events/) and [ICSB](https://www.icsb2022.berlin/home) 2022 conferences.
->I have also facilitated a couple of Data Hazards workshops, information for how I prepared can be found here [Data_Hazards_workshops](https://github.com/Susana465/Data_Hazards_workshops). I have also co-organised and co-hosted a [one-day symposium around Data Hazards, Ethics and Reproducibility in 2023](https://github.com/Susana465/der_symposium_20230310).
-> Likewise, I also worked with the Data Hazards team to create a [poster](https://github.com/Susana465/DH_Project_CaseStudy) for AI UK 2023, in which I showcased my PhD work for people at the conference to discuss what Data Hazard labels they thought applied.
-> I have also worked on adding a chapter to the [Turing Way Booklet](https://the-turing-way.netlify.app/index.html) about Data Hazards, which is currently still in the process of being reviewed and published as of January 2024 (see info [here](https://github.com/the-turing-way/the-turing-way/pull/3435)).
-
diff --git a/site/contents/data-hazards.md b/site/contents/data-hazards.md
index ea14565..f1a68a8 100644
--- a/site/contents/data-hazards.md
+++ b/site/contents/data-hazards.md
@@ -1,162 +1 @@
-# Data Hazard labels
-
-This page contains the Data Hazard labels themselves.
-These labels, descriptions, examples, and safety precautions will evolve as we develop the hazard labels with the communities who will use them.
-We welcome you to suggest changes, so please check our [contribution guidelines](contribute) if you would like to.
-
-You can [download a printable set of Data Hazards cards here](../_static/DataHazards_PrintableCards.pdf).
-
-Each hazard has:
-- __Hazard__ image, title, and description which represents and describes the risk.
-- __Examples__ to clarify what the hazard covers.
-- __Safety Precautions__ - things that we would want to see done **before** the research is deployed.
-
-They are designed to help us think about the different types of hazards.
-
-We also collect a series of mitigation resources and tools (scroll down) to help apply the safety precautions to your project.
-
-````{panels}
-:container: container-fluid
-:column: col-6 p-3
-:img-top-cls: p-3 bg-warning
-:header: bg-warning
-:body: bg-warning
-:footer: bg-warning
-
-:img-top: /images/hazards/general-hazard.png
-
-```{link-button} hazards/general-hazard.html
-:text:
-:classes: stretched-link
-```
-__Data Hazard__
-
-Data Science is being used in this output, and any negative outcome of using this work are not the fault of "the algorithm" or "the software".
-
-This hazard applies to __all__ Data Science research outputs.
-
----
-:img-top: /images/hazards/reinforce-bias.png
-
-```{link-button} hazards/reinforces-biases.html
-:text:
-:classes: stretched-link
-```
-__Reinforces Existing Biases__
-
-Reinforces unfair treatment of individuals and groups. This may be due to for example input data, algorithm or software design choices, or society at large.
-
-__Note:__ this is a hazard in it's own right, even if it isn't then used to harm people directly, due to e.g. reinforcing stereotypes.
-
----
-:img-top: /images/hazards/classifies-people.png
-
-```{link-button} hazards/ranks-classifies.html
-:text:
-:classes: stretched-link
-```
-__Ranks Or Classifies People__
-
-Ranking and classifications of people are hazards in their own right and should be handled with care.
-
-To see why, we can think about what happens when the ranking/classification is inaccurate, when people disagree with how they are ranked/classified, as well as who the ranking/classification is and is not working for, how it can be gamed, and what it is used to justify or explain.
-
----
-:img-top: /images/hazards/environment.png
-
-```{link-button} hazards/high-environmental-cost.html
-:text:
-:classes: stretched-link
-```
-__High Environmental Cost__
-
-This hazard is appropriate where methodologies are energy-hungry, data-hungry (requiring more and more computation), or require special hardware that require rare materials.
-
----
-:img-top: /images/hazards/lacks-community.png
-
-```{link-button} hazards/lacks-community-involvement.html
-:text:
-:classes: stretched-link
-```
-__Lacks Community Involvement__
-
-This applies when technology is being produced without input from the community it is supposed to serve.
-
----
-:img-top: /images/hazards/misuse.png
-
-```{link-button} hazards/danger-of-misuse.html
-:text:
-:classes: stretched-link
-```
-__Danger Of Misuse__
-
-There is a danger of misusing the algorithm, technology, or data collected as part of this work.
-
----
-:img-top: /images/hazards/difficult-to-understand.png
-
-```{link-button} hazards/difficult-to-understand.html
-:text:
-:classes: stretched-link
-```
-__Difficult To Understand__
-
-There is a danger that the technology is difficult to understand.
-This could be because of the technology itself is hard to interpret (e.g. neural nets), or problems with it's implementation (i.e. code is not provided, or not documented).
-
-Depending on the circumstances of its use, this could mean that incorrect results are hard to identify, or that the technology is inaccessible to people (difficult to implement or use).
-
----
-:img-top: /images/hazards/direct-harm.png
-
-```{link-button} hazards/direct-harm.html
-:text:
-:classes: stretched-link
-```
-__May Cause Direct Harm__
-
-The application area of this technology means that it is capable of causing direct physical or psychological harm to someone even if used correctly e.g. healthcare and driverless vehicles may be expected to directly harm someone unless they have 100% accuracy.
-
----
-:img-top: /images/hazards/privacy.png
-
-```{link-button} hazards/risk-to-privacy.html
-:text:
-:classes: stretched-link
-```
-__Risk To Privacy__
-
-This technology may risk the privacy of individuals whose data is processed by it.
-
----
-:img-top: /images/hazards/automates-decision-making.png
-
-```{link-button} hazards/automates-decision-making.html
-:text:
-:classes: stretched-link
-```
-__Automates Decision Making__
-
-Automated decision making can be hazardous for a number of reasons, and these will be highly dependent on the field in which it is being applied.
-We should ask ourselves whose decisions are being automated, what automation can bring to the process, and who is benefitted/harmed from this automation.
-
----
-:img-top: /images/hazards/lacks-informed-consent.png
-
-```{link-button} hazards/lacks-informed-consent.html
-:text:
-:classes: stretched-link
-```
-__Lacks Informed Consent__
-
-This hazard applies to datasets or algorithms that use data which has not been provided with the explicit consent of the data owner/creator. This data often lacks
-other contextual information which can also make it difficult to understand how the dataset may be biased.
-
-````
-
-## Related resources
-
-You can find our [list of useful tools and resources to help you implement the Data Hazard safety resources here](mitigation-resources.md).
-You can also [download a printable set of Data Hazards cards here](../_static/DataHazards_PrintableCards.pdf).
+
diff --git a/site/contents/materials/teaching/students.md b/site/contents/materials/teaching/students.md
deleted file mode 100644
index db8fe6b..0000000
--- a/site/contents/materials/teaching/students.md
+++ /dev/null
@@ -1,33 +0,0 @@
-# Data Hazards Student Overview
-
-This page contains some handy links about the Data Hazards project that might be useful to you throughout the session.
-
-## Slido link
-
-[Link to the Slido](https://app.sli.do/event/wes4zth7)
-
-Alternatively you can access it by going to https://slido.com and entering the code `#192908`.
-
-## Data Hazard label names
-
-Here is a short list of all the names of the Hazards to use as a reference.
-You can get the full detail of all the Data Hazards with their additional info and safety precautions [from this link](../../data-hazards), or by clicking on the link in the menu bar.
-
-* Data hazard
-* Reinforces exising biases
-* Ranks or classifies people
-* High environmental cost
-* Lacks community involvement
-* Danger of misuse
-* Difficult to understand
-* May cause direct harm
-* Privacy
-* Automates decision making
-* Lacks informed consent
-
-
-## Slides
-
-You can find [the slides we were presenting here](https://docs.google.com/presentation/d/1KzTdvnL8wk9oZ-h7C_yNWHtA4ki5i6moij8y-gP-z0s/edit?usp=sharing) (and below) in case you would like access to them later.
-
-
diff --git a/site/contents/presenting/github-badge.md b/site/contents/presenting/github-badge.md
deleted file mode 100644
index 4a181ce..0000000
--- a/site/contents/presenting/github-badge.md
+++ /dev/null
@@ -1 +0,0 @@
-# GitHub badges for Data Hazards
\ No newline at end of file
diff --git a/site/contents/presenting/image-app.md b/site/contents/presenting/image-app.md
deleted file mode 100644
index 195ce82..0000000
--- a/site/contents/presenting/image-app.md
+++ /dev/null
@@ -1 +0,0 @@
-# Generate a Data Hazards summary image
\ No newline at end of file
diff --git a/site/contents/contribute.md b/site/contribute.md
similarity index 79%
rename from site/contents/contribute.md
rename to site/contribute.md
index ee98c54..36bdb79 100644
--- a/site/contents/contribute.md
+++ b/site/contribute.md
@@ -1,4 +1,4 @@
-# Contributing
+# Contribute
```{toctree}
:maxdepth: 1
@@ -7,7 +7,6 @@ contribute/style-guide
contribute/how-to-contribute
contribute/credit-for-contributions
contribute/contributors
-contribute/changelog
```
The Data Hazards project is always welcoming new contributors!
@@ -15,8 +14,7 @@ This page gives you an overview of how you can get involved.
You can see all of our wonderful existing contributors in our [Record of contributions](contribute/contributors).
We strongly welcome first-time GitHub users and are very happy to provide support if you would like to learn how to edit the repository.
-Please just [get in touch by email][dec-email] if that is the case.
-You could also come to our [community co-working calls](events/coworking)!
+Please just [get in touch by email][email] if that is the case.
All our content is created and shared under a [CC-BY 4.0 license](https://creativecommons.org/licenses/by/4.0/), and so if you do contribute to the repository your work will also be shared under this license.
@@ -26,15 +24,14 @@ All our content is created and shared under a [CC-BY 4.0 license](https://creati
We would absolutely love your input on the following:
-1. General feedback on our [Data Hazard Labels](data-hazards), which you can send to us through email or on [GitHub Discussions](https://github.com/very-good-science/data-hazards/discussions/new?category=feedback).
+1. General feedback on our [Data Hazard Labels](labels), which you can send to us through [email][email] or as a [GitHub Issue][issues].
2. Suggestions for new Data Hazard labels, or changes to them.
For example you might suggest:
- Ways of rewording Data Hazard label descriptions or titles.
- New examples of Data Hazards.
- New/updated "Safety Precautions" (ways of combatting Data Hazards).
- Ideas for new Data Hazards.
-3. Join one of [upcoming events](events) or (in development) asynchonous mailing lists to provide Data Hazards reviews on different projects.
-4. Contribute to [any of our materials](materials) or share ideas for new materials to help others use the Hazards.
+3. Contribute to [any of our materials](materials) or share ideas for new materials to help others use the Hazards.
This could include:
- Fixing a typo or a broken link.
- Sharing a link to materials you have made.
@@ -59,4 +56,5 @@ Check out our [Credit for contributions](contribue/../contribute/credit-for-cont
---
[issues]: https://github.com/very-good-science/data-hazards/issues
-[dec-email]: mailto:grp-ethicaldatascience@groups.bristol.ac.uk
+[email]: mailto:data-hazards-project@bristol.ac.uk
+
diff --git a/site/contribute/contributors.md b/site/contribute/contributors.md
new file mode 100644
index 0000000..41157d9
--- /dev/null
+++ b/site/contribute/contributors.md
@@ -0,0 +1,125 @@
+# Record of contributions
+
+The Data Hazards project exists because of the support and contributions of the many different people below.
+Please also note that people have also anonymously contributed ideas and resources to the project that Nina and Natalie have added on their behalf.
+
+
+
+
+
+
+
+
+
+
+This page is a place where anyone who has contributed to the project can be recognised for the time, effort and expertise they have given to Data Hazards.
+
+This page is based on a similar model used by [The Turing Way](https://github.com/alan-turing-institute/the-turing-way/blob/main/contributors.md) for recognising contributors to open source projects.
+
+We welcome anyone asking to be added to this page if they have made a contribution.
+You can read about different ways to contribute to the project in our [contributors guide](how-to-contribute).
+To be added, please [submit an issue](https://github.com/very-good-science/data-hazards/issues), make a pull request, or [send us an email](mailto:grp-ethicaldatascience@groups.bristol.ac.uk) which includes the following details:
+* Your Name
+* Your Role and Affiliation
+* (Optional) ORCID ID or other persistent identifier
+* (Optional) Personal contact details or website
+* Overview of your contribution to the Data Hazards Project - please don't be modest!
+
+
+## Contributors
+
+
+
+### Nina Di Cara
+* Role: Co-PI
+* ORCID [0000-0002-6179-1067](https://orcid.org/0000-0002-6179-1067)
+* GitHub: [ninadicara](https://github.com/ninadicara)
+> Along with Natalie I worked on the original idea for the Data Hazards, created resources around them (like teaching materials, slides, reflective prompts, illustrations), planned and delivered our workshops, and the website content. Jointly Natalie and I provide leadership for the project in terms of its next steps and uses. I care a lot about reducing the harm that technology can do to people who may not have power to fight back against, and hope this projects goes some way to making us all think more carefully about what we can all do as individuals to prevent harm. I am also thrilled to have been able to work with (and continue to work with) all the fantastic people who have got involved with this project!
+
+
+### Natalie Zelenka
+* Role: Co-PI
+* ORCID: [0000-0002-1007-0286](https://orcid.org/0000-0002-1007-0286)
+* GitHub: [NatalieZelenka](https://github.com/NatalieZelenka)
+> As a co-lead of the Data Hazards project, I developed the idea for Data Hazards with Nina, wrote lesson materials and proposals and drafted papers, designed images, found funding, and did lots of planning. Me and Nina shared these leadership and organisational tasks 50-50, but we are so grateful for everyone's contributions and support so far. I hope that - like some of the work that I'm [most](https://the-turing-way.netlify.app/) [inspired](https://reproducibilitea.org/) [by](https://carpentries.org/) - these materials *reduce barriers* for researchers. In this case, I hope Data Hazards makes it easier for data scientists to consider the ethical implications of their work and to make those decisions together with the communities who are affected by the work they are doing.
+
+### Ismael Kherrouvi Garcia
+
+* Role: Workshop facilitator (and huge fan!)
+* ORCID: [0000-0002-6850-8375](https://doi.org/0000-0002-6850-8375)
+* Find me on :octocat: [Ismael-KG](https://github.com/Ismael-KG), and Twitter ([@hermeneuticist](https://twitter.com/hermeneuticist))
+> In September 2021, I was delighted to facilitate a workshop alongside [@NatalieZelenka](https://github.com/NatalieZelenka) and [@ninadicara](https://github.com/ninadicara) to [test the Data Hazard labels](https://www.bristol.ac.uk/golding/events/2021/data-hazards-workshop---21-september-2021.html) with researchers from diverse backgrounds. This meant working with Natalie and Nina to familiarise myself with [the prompts they had prepared](https://github.com/very-good-science/data-hazards/blob/ae2ecfad7f85fe48670ed6221a6563353d31e77b/images/worst-case-prompt.png), and then keeping the conversation flowing during breakout rooms with workshop participants. I had previously gathered feedback from The Alan Turing Institute's [Ethics Advisory Group](https://www.turing.ac.uk/research/data-ethics/ethics-advisory-group) (EAG) for the Data Hazard labels. My time with the Turing's EAG allowed me to appreciate the value of the Data Hazard labels, both in the context of training data scientists on questions of ethics, and for preparing documentation for the review of research ethics committees.
+
+
+### Melanie I Stefan
+
+* Role: Early adopter
+* ORCID: [0000-0002-6086-7357](https://orcid.org/my-orcid?orcid=0000-0002-6086-7357)
+* GitHub: [MelanieIStefan](https://github.com/MelanieIStefan)
+> I was introduced to Data Hazards by the wonderful [@Susana465](https://susana465.github.io/), and it has informed my thinking and practice ever since. I helped facilitate a workhop on Data Hazards at [COMBINE 2022 in Berlin](https://co.mbine.org/author/combine-2022/), and also talked about how I use the Data Hazards framework to flag up potential issues with my own lecture materials at the [Data Hazards, Ethics and Reproducibility One-Day Symposium](https://www.eventbrite.com/e/online-data-hazards-ethics-and-reproducibility-one-day-symposium-tickets-517490858087) at the Turing Institute in 2023. I am also involved in the discussion on the Data Hazards labels themselves.
+
+### Susana Roman Garcia
+
+* Role: Workshop facilitator, content developer of the Data Hazards application to different settings, especially Neuroscience, PhD case study application of Data Hazards
+* ORCID ID: [0009-0004-6967-7754](https://orcid.org/0009-0004-6967-7754)
+* [Personal website](https://susana465.github.io/website/)
+> I came across the Data Hazards project as I looked for a way to embed thinking about ethics into my PhD, around 2021/22. Since then, I have attended a facilitator training workshop given by Nina and Natalie; and applied the Data Hazards framework to my PhD as I go along. To showcase this, I made a [poster presentation](https://github.com/Susana465/Bias-and-Reproducibility-Poster/blob/main/README.md) for the [COMBINE](https://combine-org.github.io/events/) and [ICSB](https://www.icsb2022.berlin/home) 2022 conferences.
+>I have also facilitated a couple of Data Hazards workshops, information for how I prepared can be found here [Data_Hazards_workshops](https://github.com/Susana465/Data_Hazards_workshops). I have also co-organised and co-hosted a [one-day symposium around Data Hazards, Ethics and Reproducibility in 2023](https://github.com/Susana465/der_symposium_20230310).
+> Likewise, I also worked with the Data Hazards team to create a [poster](https://github.com/Susana465/DH_Project_CaseStudy) for AI UK 2023, in which I showcased my PhD work for people at the conference to discuss what Data Hazard labels they thought applied.
+> I have also worked on adding a chapter to the [Turing Way Booklet](https://the-turing-way.netlify.app/index.html) about Data Hazards, which is currently still in the process of being reviewed and published as of January 2024 (see info [here](https://github.com/the-turing-way/the-turing-way/pull/3435)).
+
diff --git a/site/contents/contribute/credit-for-contributions.md b/site/contribute/credit-for-contributions.md
similarity index 100%
rename from site/contents/contribute/credit-for-contributions.md
rename to site/contribute/credit-for-contributions.md
diff --git a/site/contents/contribute/how-to-contribute.md b/site/contribute/how-to-contribute.md
similarity index 90%
rename from site/contents/contribute/how-to-contribute.md
rename to site/contribute/how-to-contribute.md
index 3bc2210..0ce237f 100644
--- a/site/contents/contribute/how-to-contribute.md
+++ b/site/contribute/how-to-contribute.md
@@ -8,9 +8,8 @@ You can also come to our [open community co-working calls](../events/coworking)
## Suggesting new or improved Data Hazards
-In the first instance please [start a Discussion with your idea](https://github.com/very-good-science/data-hazards/discussions/new?category=ideas) in the 'Ideas' category.
+In the first instance [please start a new Issue with your idea][issues], and label it with the `data-hazard-ideas` category.
We can then chat openly on GitHub about the suggestion, and this gives other people the opportunity to weigh-in on any changes we are considering.
-Once changes have been agreed then you can follow the process below for making changes to the website.
If you would rather you can also [email us][dh-email] to discuss.
@@ -36,7 +35,7 @@ These require some Python packages to run.
You may want to set up a [virtual environment](https://docs.python.org/3/library/venv.html) first, so that you don't install these packages system-wide.
Then you can install the packages using `pip install -r requirements.txt`
-## Adding slides
+
---
[issues]: https://github.com/very-good-science/data-hazards/issues
diff --git a/site/contents/contribute/style-guide.md b/site/contribute/style-guide.md
similarity index 100%
rename from site/contents/contribute/style-guide.md
rename to site/contribute/style-guide.md
diff --git a/site/contents/events.md b/site/events.md
similarity index 100%
rename from site/contents/events.md
rename to site/events.md
diff --git a/site/contents/events/2021-09-21_workshop.md b/site/events/2021-09-21_workshop.md
similarity index 100%
rename from site/contents/events/2021-09-21_workshop.md
rename to site/events/2021-09-21_workshop.md
diff --git a/site/contents/events/bristol-tech-fest.md b/site/events/bristol-tech-fest.md
similarity index 100%
rename from site/contents/events/bristol-tech-fest.md
rename to site/events/bristol-tech-fest.md
diff --git a/site/contents/events/coworking.md b/site/events/coworking.md
similarity index 100%
rename from site/contents/events/coworking.md
rename to site/events/coworking.md
diff --git a/site/contents/events/jgi-showcase-events.md b/site/events/jgi-showcase-events.md
similarity index 100%
rename from site/contents/events/jgi-showcase-events.md
rename to site/events/jgi-showcase-events.md
diff --git a/site/contents/events/mozfest2022.md b/site/events/mozfest2022.md
similarity index 100%
rename from site/contents/events/mozfest2022.md
rename to site/events/mozfest2022.md
diff --git a/site/contents/hazards/automates-decision-making.md b/site/hazards/automates-decision-making.md
similarity index 90%
rename from site/contents/hazards/automates-decision-making.md
rename to site/hazards/automates-decision-making.md
index f86a0f4..82e7ee3 100644
--- a/site/contents/hazards/automates-decision-making.md
+++ b/site/hazards/automates-decision-making.md
@@ -1,7 +1,7 @@
# Hazard: Automates Decision Making
-```{image} ../../images/hazards/automates-decision-making.png
-:alt: A red diamond shaped outline (like a warning sign) with two connected cogs that have two arrows coming out of the top of them.
+```{image} ../images/hazards/automates-decision-making.png
+:alt: A red diamond shaped outline (like a warning sign) with two connected cogs that have arrows coming out of the top of them.
:width: 250px
```
diff --git a/site/contents/hazards/danger-of-misuse.md b/site/hazards/danger-of-misuse.md
similarity index 91%
rename from site/contents/hazards/danger-of-misuse.md
rename to site/hazards/danger-of-misuse.md
index 9cad6d1..c19d833 100644
--- a/site/contents/hazards/danger-of-misuse.md
+++ b/site/hazards/danger-of-misuse.md
@@ -1,7 +1,7 @@
# Hazard: Danger Of Misuse
-```{image} ../../images/hazards/misuse.png
-:alt: A red diamond shaped outline (like a warning sign) with a hammer raised above a screw in the middle.
+```{image} ../images/hazards/misuse.png
+:alt: A red diamond shaped outline (like a warning sign) with a hammer raised above a bent screw in the middle.
:width: 250px
```
diff --git a/site/contents/hazards/difficult-to-understand.md b/site/hazards/difficult-to-understand.md
similarity index 97%
rename from site/contents/hazards/difficult-to-understand.md
rename to site/hazards/difficult-to-understand.md
index 0646e74..ef2d3aa 100644
--- a/site/contents/hazards/difficult-to-understand.md
+++ b/site/hazards/difficult-to-understand.md
@@ -1,6 +1,6 @@
# Hazard: Difficult To Understand
-```{image} ../../images/hazards/difficult-to-understand.png
+```{image} ../images/hazards/difficult-to-understand.png
:alt: A red diamond shaped outline (like a warning sign) with an image of a closed box and a question mark next to it.
:width: 250px
```
diff --git a/site/contents/hazards/direct-harm.md b/site/hazards/direct-harm.md
similarity index 96%
rename from site/contents/hazards/direct-harm.md
rename to site/hazards/direct-harm.md
index 8187803..524f407 100644
--- a/site/contents/hazards/direct-harm.md
+++ b/site/hazards/direct-harm.md
@@ -1,6 +1,6 @@
# Hazard: May Cause Direct Harm
-```{image} ../../images/hazards/direct-harm.png
+```{image} ../images/hazards/direct-harm.png
:alt: A red diamond shaped outline (like a warning sign) with a skull in the middle.
:width: 250px
```
diff --git a/site/contents/hazards/general-hazard.md b/site/hazards/general-hazard.md
similarity index 94%
rename from site/contents/hazards/general-hazard.md
rename to site/hazards/general-hazard.md
index 392432c..365daa1 100644
--- a/site/contents/hazards/general-hazard.md
+++ b/site/hazards/general-hazard.md
@@ -1,6 +1,6 @@
# Hazard: General Data Hazard
-```{image} ../../images/hazards/general-hazard.png
+```{image} ../images/hazards/general-hazard.png
:alt: A red diamond shaped outline (like a warning sign) with an exclamation mark in the middle.
:width: 250px
```
diff --git a/site/contents/hazards/hazard-template.md b/site/hazards/hazard-template.md
similarity index 81%
rename from site/contents/hazards/hazard-template.md
rename to site/hazards/hazard-template.md
index 462c51f..9ea891f 100644
--- a/site/contents/hazards/hazard-template.md
+++ b/site/hazards/hazard-template.md
@@ -1,6 +1,6 @@
# Hazard:
-```{image} ../../images/hazards/XX
+```{image} ../images/hazards/XX
:alt: A red diamond shaped outline (like a warning sign) with .....
:width: 250px
```
diff --git a/site/contents/hazards/high-environmental-cost.md b/site/hazards/high-environmental-cost.md
similarity index 89%
rename from site/contents/hazards/high-environmental-cost.md
rename to site/hazards/high-environmental-cost.md
index 8f5a412..563f582 100644
--- a/site/contents/hazards/high-environmental-cost.md
+++ b/site/hazards/high-environmental-cost.md
@@ -1,7 +1,7 @@
# Hazard: High Environmental Cost
-```{image} ../../images/hazards/environment.png
-:alt: A red diamond shaped outline (like a warning sign) with an image of a globe in the middle.
+```{image} ../images/hazards/environment.png
+:alt: A red diamond shaped outline (like a warning sign) with an image of a globe on fire in the middle.
:width: 250px
```
diff --git a/site/contents/hazards/lacks-community-involvement.md b/site/hazards/lacks-community-involvement.md
similarity index 92%
rename from site/contents/hazards/lacks-community-involvement.md
rename to site/hazards/lacks-community-involvement.md
index 38b64ad..540afd5 100644
--- a/site/contents/hazards/lacks-community-involvement.md
+++ b/site/hazards/lacks-community-involvement.md
@@ -1,7 +1,7 @@
# Hazard: Lacks Community Involvement
-```{image} ../../images/hazards/lacks-community.png
-:alt: A red diamond shaped outline (like a warning sign) with figures in the middle who have empty speech bubbles above their heads.
+```{image} ../images/hazards/lacks-community.png
+:alt: A red diamond shaped outline (like a warning sign) with figures in the middle who have a speech bubble above their heads with a big cross through it.
:width: 250px
```
diff --git a/site/contents/hazards/lacks-informed-consent.md b/site/hazards/lacks-informed-consent.md
similarity index 81%
rename from site/contents/hazards/lacks-informed-consent.md
rename to site/hazards/lacks-informed-consent.md
index 506f455..4738b31 100644
--- a/site/contents/hazards/lacks-informed-consent.md
+++ b/site/hazards/lacks-informed-consent.md
@@ -1,7 +1,7 @@
# Hazard: Lacks Informed Consent
-```{image} ../../images/hazards/lacks-informed-consent.png
-:alt: A red diamond shaped outline (like a warning sign) with an icon of a form in the middle.
+```{image} ../images/hazards/lacks-informed-consent.png
+:alt: A red diamond shaped outline (like a warning sign) containing a magnifying glass hovering over a cross on a piece of paper.
:width: 250px
```
diff --git a/site/contents/hazards/ranks-classifies.md b/site/hazards/ranks-classifies.md
similarity index 89%
rename from site/contents/hazards/ranks-classifies.md
rename to site/hazards/ranks-classifies.md
index 6527582..7fc319d 100644
--- a/site/contents/hazards/ranks-classifies.md
+++ b/site/hazards/ranks-classifies.md
@@ -1,7 +1,7 @@
# Hazard: Ranks Or Classifies People
-```{image} ../../images/hazards/classifies-people.png
-:alt: A red diamond shaped outline (like a warning sign) with a set of weighing scales in the middle, and a person sitting on each side of the scale.
+```{image} ../images/hazards/classifies-people.png
+:alt: A red diamond shaped outline (like a warning sign) with three people standing on a podium of first, second and third place.
:width: 250px
```
diff --git a/site/contents/hazards/reinforces-biases.md b/site/hazards/reinforces-biases.md
similarity index 76%
rename from site/contents/hazards/reinforces-biases.md
rename to site/hazards/reinforces-biases.md
index 437c383..6159a74 100644
--- a/site/contents/hazards/reinforces-biases.md
+++ b/site/hazards/reinforces-biases.md
@@ -1,7 +1,7 @@
# Hazard: Reinforces Existing Biases
-```{image} ../../images/hazards/reinforce-bias.png
-:alt: A red diamond shaped outline (like a warning sign) around two arrows pointing to each other in a circle.
+```{image} ../images/hazards/reinforce-bias.png
+:alt: A red diamond shaped outline (like a warning sign) with a dark head and shoulders, who has a white triangle in their mind. They are looking out at a black circle, a black square and a larger white triangle just ahead of them. This indicates that the largest shape is the one that they think of.
:width: 250px
```
@@ -9,7 +9,7 @@
Reinforces unfair treatment of individuals and groups. This may be due to for example input data, algorithm or software design choices, or society at large.
-__Note:__ this is a hazard in it's own right, even if it isn't then used to harm people directly, due to e.g. reinforcing stereotypes.
+__Note:__ this is a Hazard in it's own right, even if it isn't then used to harm people directly, due to e.g. reinforcing stereotypes.
## Examples
diff --git a/site/contents/hazards/risk-to-privacy.md b/site/hazards/risk-to-privacy.md
similarity index 94%
rename from site/contents/hazards/risk-to-privacy.md
rename to site/hazards/risk-to-privacy.md
index ce09f0f..cff557f 100644
--- a/site/contents/hazards/risk-to-privacy.md
+++ b/site/hazards/risk-to-privacy.md
@@ -1,6 +1,6 @@
# Hazard: Risk To Privacy
-```{image} ../../images/hazards/privacy.png
+```{image} ../images/hazards/privacy.png
:alt: A red diamond shaped outline (like a warning sign) with a picture of a surveillance camera in the middle.
:width: 250px
```
diff --git a/site/images/label-anatomy.jpg b/site/images/label-anatomy.jpg
new file mode 100644
index 0000000..2d838ef
Binary files /dev/null and b/site/images/label-anatomy.jpg differ
diff --git a/site/index.md b/site/index.md
index b640e1a..8d0ab6f 100644
--- a/site/index.md
+++ b/site/index.md
@@ -1,59 +1,98 @@
# The Data Hazards Project
-[//]: # (TODO: Include all alt text)
-
-
-
-Data Hazards is a project about worst-case scenarios of data science.
+Data Hazards is a project to help us all identify the hazards of using data science.
Data scientists are great at selling our work, for example communicating the gains in efficiency and accuracy, but we are less well-practiced in thinking about the ethical implications of our work.
The ethical implications go beyond most ethics Institutional Review Boards, to questions about the wider societal impact of data science and algorithms work.
-### Aims
-We aim to __create resources__ to:
-1. Create a shared vocabulary of Data Hazards in the form of [Data Hazard Labels](contents/data-hazards).
-2. Make ethical and future-thinking more accessible to data scientists, computer scientists and applied mathematicians - to apply to their own work.
-3. Enable bringing together and respecting diverse and interdisciplinary viewpoints to this work, through workshops or mailing lists.
-4. Find out what circumstances, and for who, these resources work best.
-
-### How
-To support our aims we will:
-1. Get feedback on our [Data Hazard labels](contents/data-hazards), to develop them with the communities who will be using them.
-2. Create resources that help data scientists reflect on their own work, by creating prompts, frameworks, and forms for them to consider.
-3. Run workshops and mailing lists where data scientists can listen to diverse perspectives and grow their ideas of what is possible, and where interdisciplinary researchers and the public can both be heard, respected, and listened to by the people who are doing computational and mathematical work.
-4. Listen to our community's feedback through surveys.
-
-```{admonition} Why are the Hazard Labels so scary-looking?
-We know that the [Data Hazards labels](contents/data-hazards) are a bit frightening. Argh, there's a skull!
-Please know that __we don't want these labels to scare anyone away from considering ethics or from doing data science__, and we will do everything that we can to make applying Data Hazards labels as welcoming and approachable as possible, but also have some good reasons for choosing these images.
-
-We chose this format because of the similarity to [COSHH hazard labels](https://www.hse.gov.uk/chemical-classification/labelling-packaging/hazard-symbols-hazard-pictograms.htm) - hazard labels for chemicals.
-We made this choice because we want a similar response from people:
-1. Attention-grabbing, asking people to stop and think, and take the safety precautions seriously, rather than as an optional extra.
-2. We're asking people to "handle with care", not to stop doing the work. We still use chemicals, but we think about how it can be done safely and how to avoid emergencies.
-3. They are familiar, especially to scientists, who (within universities) tend to have the least experience of applying ethics.
-
+```{admonition} Project Aims
+1. Create a __community-driven open-source vocabulary__ of ethical hazards for data-intensive research and development, in the form of [Data Hazard labels](contents/data-hazards).
+2. Make ethical and future-thinking __more accessible__ to data scientists, computer scientists and applied mathematicians to apply to their own work.
+3. Enable bringing together and respecting __diverse and interdisciplinary viewpoints__ to this work, and produce resources to do this.
+4. Find out in what circumstances, and for who, these resources work best.
```
+## Contributors
+
+Our brilliant contributors are listed here, and you can [read more detail about our contributing process here](contribute).
+
+
+
+
+
+
+
+
+
```{toctree}
:maxdepth: 2
:hidden:
-contents/data-hazards
-contents/about
-contents/materials
-contents/contribute
-contents/contact
+labels
+about
+materials
+contribute
```
+
+:::::{grid} 1 2 3 3
+:margin: 4 4 0 0
+:gutter: 2
+
+::::{grid-item-card} General Data Hazard
+:img-top: images/hazards/general-hazard.png
+:img-alt: A red diamond shaped outline (like a warning sign) with an exclamation mark in the middle.
+:link: /hazards/general-hazard
+:link-type: doc
+
+Data Science is being used in this output, and any negative outcome of using this work are not the fault of "the algorithm" or "the software".
+::::
+
+::::{grid-item-card} Automates Decision Making
+:img-top: /images/hazards/automates-decision-making.png
+:img-alt: A red diamond shaped outline (like a warning sign) with two connected cogs that have arrows coming out of the top of them.
+:link: hazards/automates-decision-making
+:link-type: doc
+
+Automated decision making can be hazardous for a number of reasons, and these will be highly dependent on the field in which it is being applied.
+::::
+
+::::{grid-item-card} Danger Of Misuse
+:img-top: /images/hazards/misuse.png
+:img-alt: A red diamond shaped outline (like a warning sign) with a hammer raised above a bent screw in the middle.
+:link: hazards/danger-of-misuse
+:link-type: doc
+
+There is a danger of misusing the algorithm, technology, or data collected as part of this work.
+::::
+
+::::{grid-item-card} Difficult to Understand
+:img-top: /images/hazards/difficult-to-understand.png
+:img-alt: A red diamond shaped outline (like a warning sign) with an image of a closed box and a question mark next to it.
+:link: hazards/difficult-to-understand
+:link-type: doc
+
+This may apply if the technology itself is hard to interpret (e.g. neural nets), or documentation is poor/unavailable.
+::::
+
+::::{grid-item-card} High Environmental Cost
+:img-top: images/hazards/environment.png
+:img-alt: A red diamond shaped outline (like a warning sign) with an image of a globe on fire in the middle.
+:link: hazards/high-environmental-cost
+:link-type: doc
+
+Indicates methodologies that are energy-hungry, data-hungry, or require special hardware with rare materials.
+::::
+
+::::{grid-item-card} Lacks Community Involvement
+:img-top: /images/hazards/lacks-community.png
+:img-alt: A red diamond shaped outline (like a warning sign) with figures in the middle who have a speech bubble above their heads with a big cross through it.
+:link: hazards/lacks-community-involvement
+:link-type: doc
+
+This applies when technology is being produced without input from the community it is supposed to serve.
+::::
+
+::::{grid-item-card} Lacks Informed Consent
+:img-top: /images/hazards/lacks-informed-consent.png
+:img-alt: A red diamond shaped outline (like a warning sign) containing a magnifying glass hovering over a cross on a piece of paper.
+:link: hazards/lacks-informed-consent
+:link-type: doc
+
+This hazard applies to datasets or algorithms that use data which has not been provided with the explicit consent of the data owner/creator.
+::::
+
+::::{grid-item-card} May Cause Direct Harm
+:img-top: /images/hazards/direct-harm.png
+:img-alt: A red diamond shaped outline (like a warning sign) with a skull in the middle.
+:link: hazards/direct-harm
+:link-type: doc
+
+The application area of this technology means that it is capable of causing direct physical or psychological harm to someone even if used correctly.
+::::
+
+::::{grid-item-card} Ranks Or Classifies People
+:img-top: images/hazards/classifies-people.png
+:img-alt: A red diamond shaped outline (like a warning sign) with three people standing on a podium of first, second and third place.
+:link: hazards/ranks-classifies
+:link-type: doc
+
+Ranking and classifications of people are hazards in their own right and should be handled with care.
+::::
+
+::::{grid-item-card} Reinforces Existing Biases
+:img-top: images/hazards/reinforce-bias.png
+:img-alt: A red diamond shaped outline (like a warning sign) with a dark head and shoulders, who has a white triangle in their mind. They are looking out at a black circle, a black square and a larger white triangle just ahead of them. This indicates that the largest shape is the one that they think of.
+:link: hazards/reinforces-biases
+:link-type: doc
+
+Reinforces unfair treatment of individuals and groups. This may be due to for example input data, algorithm or software design choices, or society at large.
+::::
+
+::::{grid-item-card} Risk to Privacy
+:img-top: /images/hazards/privacy.png
+:img-alt: A red diamond shaped outline (like a warning sign) with a picture of a surveillance camera in the middle.
+:link: hazards/risk-to-privacy
+:link-type: doc
+
+This technology may risk the privacy of individuals whose data is processed by it.
+::::
+
+:::::
+
+
+## Future development
+
+Suggestions for future versions of the Data Hazard labels are curated as GitHub Issues. [Click here to see the current suggestions.](https://github.com/very-good-science/data-hazards/labels/hazard-label-idea)
+
+
+## Change log
+
+The change log records when changes that have been made to the project and gives a brief description of what the changes were.
+The change log started in March 2022.
+The most recent changes should be at the top of the list.
+
+
+
+__29.05.2024: Put labels in alphabetical order__
+[@ninadicara](https://github.com/ninadicara)
+
+
+__06.12.2022: Update new Hazard labels__
+[@ninadicara](https://github.com/ninadicara)
+Updated all the images of the Hazards with our new labels designed by the amazing [Yasmin Dwiputri](http://yasmindwiputri.com/)!
+
+
+__07.03.2022: Move Data Hazards to individual pages__
+[@ninadicara](https://github.com/ninadicara)
+Moved all of the Hazards to their own individual pages, and linked them from the original sphinx panels.
+Also capitalised all of the names so that they are consistently named.
+This should make it easier for people to contribute to a single Hazard and record their contribution against it :)
+
+
+
diff --git a/site/contents/materials.md b/site/materials.md
similarity index 86%
rename from site/contents/materials.md
rename to site/materials.md
index 1b94d95..0f4d773 100644
--- a/site/contents/materials.md
+++ b/site/materials.md
@@ -12,15 +12,16 @@ materials/teaching
materials/self-assessment
materials/presenting
materials/examples
+materials/mitigation-resources
```
-On this page you will find materials we have made to help people to use or apply the [Data Hazard labels](data-hazards).
+On this page you will find materials we have made to help people to use or apply the [Data Hazard labels](labels).
This includes a workshop format, a teaching/lecture based format, and an asychronous format which can be adapted to just be an individual exercise.
You are welcome to use any of the materials we share here, which (like all of our content) are available to use with a [CC-BY 4.0 license](https://creativecommons.org/licenses/by/4.0/).
This means, roughly, they can be re-used and adapted as long as you credit this repository.
-We are currently developing all these materials so please do get in touch with us through the [Contact](contact) tab above if you have any thoughts or examples of how you have used the materials!
+We are currently developing all these materials so please do [get in touch with us](about) if you have any thoughts or examples of how you have used the materials!
Alternatively if you have changes in mind that you would like to make then check out [How to contribute](contribute) - we always welcome new contributors!
diff --git a/site/contents/materials/examples.md b/site/materials/examples.md
similarity index 100%
rename from site/contents/materials/examples.md
rename to site/materials/examples.md
diff --git a/site/contents/materials/misc/geno_to_pheno_example.md b/site/materials/misc/geno_to_pheno_example.md
similarity index 100%
rename from site/contents/materials/misc/geno_to_pheno_example.md
rename to site/materials/misc/geno_to_pheno_example.md
diff --git a/site/contents/materials/misc/proposal.md b/site/materials/misc/proposal.md
similarity index 100%
rename from site/contents/materials/misc/proposal.md
rename to site/materials/misc/proposal.md
diff --git a/site/contents/materials/misc/workshop-21092021.md b/site/materials/misc/workshop-21092021.md
similarity index 100%
rename from site/contents/materials/misc/workshop-21092021.md
rename to site/materials/misc/workshop-21092021.md
diff --git a/site/contents/mitigation-resources.md b/site/materials/mitigation-resources.md
similarity index 100%
rename from site/contents/mitigation-resources.md
rename to site/materials/mitigation-resources.md
diff --git a/site/contents/materials/presenting.md b/site/materials/presenting.md
similarity index 100%
rename from site/contents/materials/presenting.md
rename to site/materials/presenting.md
diff --git a/site/contents/materials/seedcorn.md b/site/materials/seedcorn.md
similarity index 100%
rename from site/contents/materials/seedcorn.md
rename to site/materials/seedcorn.md
diff --git a/site/contents/materials/self-assessment.md b/site/materials/self-assessment.md
similarity index 100%
rename from site/contents/materials/self-assessment.md
rename to site/materials/self-assessment.md
diff --git a/site/contents/materials/teaching.md b/site/materials/teaching.md
similarity index 97%
rename from site/contents/materials/teaching.md
rename to site/materials/teaching.md
index e957651..7df58ce 100644
--- a/site/contents/materials/teaching.md
+++ b/site/materials/teaching.md
@@ -18,12 +18,6 @@ We suggest starting with a 10-15 minute presentation to introduce the Data Hazar
The lecturer should then present a case study that the students can discuss in small groups.
Prior to the discussion, students should have the opportunity to ask clarifying questions about the project.
-We provided a summary page for students too, to use during the seminar.
-```{toctree}
-:maxdepth: 1
-teaching/students
-```
-
## Timings
17:00 - 17:05 - Settling in
diff --git a/site/contents/materials/workshop.md b/site/materials/workshop.md
similarity index 94%
rename from site/contents/materials/workshop.md
rename to site/materials/workshop.md
index 6f2dbb0..b0bfcac 100644
--- a/site/contents/materials/workshop.md
+++ b/site/materials/workshop.md
@@ -4,7 +4,7 @@ The Data Hazards were originally designed around a workshop format.
This was to allow a series of _Project Owners_ to present a research project to _Audience Members_, who would give them feedback on the ethics of their project.
This could be in any context, like a team meeting, a seminar or a scoping exercise.
-You can [download a printable set of Data Hazards cards here](../../_static/DataHazards_PrintableCards.pdf).
+You can [download a printable set of Data Hazards cards here](../_static/DataHazards_PrintableCards.pdf).