Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Finalize mapping from moodid to circumplex affects #19

Open
coryschillaci opened this issue Mar 11, 2015 · 5 comments
Open

Finalize mapping from moodid to circumplex affects #19

coryschillaci opened this issue Mar 11, 2015 · 5 comments
Assignees

Comments

@coryschillaci
Copy link
Contributor

No description provided.

@coryschillaci
Copy link
Contributor Author

@anasrferreira and @peparedes Should also upload their manual responses, then we need a strategy to merge with the Mech Turk data.

@peparedes
Copy link
Contributor

I can also get more mturk data (re - law of large numbers :)

Let's merge what we have... My personal assessment is also already very
biased by the mturk data analysis.

P

@coryschillaci
Copy link
Contributor Author

More turk data won't hurt if there's money to pay for it! If you do run, can you put a test that they correctly identify most of the moodids that occur as circumplex affects as well in order to get credit? The ones that occur in both lists are:

  • happy
  • excited
  • nervous
  • stressed
  • sad
  • depressed
  • bored
  • calm
  • relaxed
  • content (contented in circumplex)

@coryschillaci
Copy link
Contributor Author

I checked the idea of scoring the MT responders by percent of the above list that they assigned correctly to the identical circumplex affect. The majority vote gets 100%, which is good. It looks like the first five do much better than the last five.
screen shot 2015-03-11 at 9 56 53 pm

@peparedes
Copy link
Contributor

yeah, so we need more day data... i will not post then the job till tomorrow

thanks

p

On Wednesday, March 11, 2015, coryschillaci [email protected]
wrote:

FYI I checked the idea of scoring the MT responders by percent of the
above list that they assigned correctly to the identical circumplex affect.
The majority vote gets 100%, which is good. It looks like the first five do
much better than the last five.

<
https://ci3.googleusercontent.com/proxy/hdHELUEAbwMkB7S0QDrbQ1LJWsnWLurg-DFJ6R3gtKidyLO5bRg468E4yDhu2Hax0r7R8XB6WHjkqZwTZ-zuZPEIHlw0KzGIzmL1pnTLRxw8nF2x-HO8kvjoKEZvDILJ0q_8SBefuK9TaVYS0A71BeYUftAv-ozy=s0-d-e1-ft#https://cloud.githubusercontent.com/assets/717954/6612449/937aa58c-c839-11e4-81bb-5e96ac6dd354.png


Reply to this email directly or view it on GitHub.<
https://ci6.googleusercontent.com/proxy/Rvffjd-RDYE66Qhd3XqWI38TS3UGQcDIlCu_EcYJHLCV_lxK8J5LxGqnw7ssBpGkWI7xMp755bYWfV2eRZ2bXUQjkg5bGFF0z7UtvPsX-dwmHrGn-bvgQpOtiK1Xtc0c6UW1Qc6rruIL5K0jVp9-MdQ_hzsW9g=s0-d-e1-ft#https://github.com/notifications/beacon/AAxWcS70p-hXZXawKVeyhdrVMW1KOFuVks5n0RRNgaJpZM4DtFWf.gif

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants