Polarity/emotion detection in social media data

Kyle Minter,
BSc Forensic Computing

Emotions are part and parcel of human life and highly influence decision making.  Computers have been used for decision making for quite some time now but have traditionally relied on factual information.  In this project, a machine learning approach was used to recognize 10 basic emotions (Empty, Fun, Happiness, Hate, Love, Neutral, relief, sadness, surprise and worry) using a heterogeneous emotion-annotated dataset which was collected from twitter.  From this results were collected and analysed to show the effects of punctuation and numbers. Further analysis showed how the program has assigned the emotions to the text and where it has made mistakes.

 

This entry was posted in SC2018 and tagged , , , . Bookmark the permalink.