Skip to content

Classification of tweets into racial or sexist tweets and normal tweets using different classification algorithms and different word embeddings.

Notifications You must be signed in to change notification settings

mrlydv/Twitter_sentiment_analysis

Repository files navigation

Twitter_sentiment_analysis

•Cleaned and analysed a dataset of 31000 tweets containing normal and sexist/racial tweets.

•Used BOWandTFIDF features for word vectorization and Word2Vec and Doc2Vec for word embeddings.

•Applied different classification algorithms like logistic regression, support vector machines,random forest and XGBoost algorithm with each of the word embeddings.

•Analysed the result for each combination with the help of F1-score and performed hyperparameter tuning using gridsearch cross validation to improve the mode

About

Classification of tweets into racial or sexist tweets and normal tweets using different classification algorithms and different word embeddings.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published