Seernet at EmoInt-2017: Tweet Emotion Intensity Estimator
This work addresses emotion analysis in social media for applications like sentiment tracking, but it is incremental as it builds on existing methods without major breakthroughs.
The authors tackled the problem of estimating emotion intensity in tweets by developing an ensemble system that combines lexical, syntactic, and word embedding features, achieving 3rd place out of 22 systems in the WASSA-2017 Shared Task leaderboard.
The paper describes experiments on estimating emotion intensity in tweets using a generalized regressor system. The system combines lexical, syntactic and pre-trained word embedding features, trains them on general regressors and finally combines the best performing models to create an ensemble. The proposed system stood 3rd out of 22 systems in the leaderboard of WASSA-2017 Shared Task on Emotion Intensity.