IITPB at SemEval-2017 Task 5: Sentiment Prediction in Financial Text
Kumar Abhishek, Abhishek Rajkumar Sethi, Md Shad Akhtar, Asif Ekbal, Chris Biemann, Pushpak Bhattacharyya · 2017
This paper reports team IITPB's participation in the SemEval 2017 Task 5 on 'Fine-grained sentiment analysis on financial microblogs and news'.We developed 2 systems for the two tracks.One system is based on an ensemble of Support Vector Classifier and Logistic Regression.This system relis on Distributional Thesaurus (DT), word embeddings and lexicon features to predict a continuous sentiment value between -1 and +1.The other system is based on Support Vector Regression using word embeddings, lexicon features, and PMI scores as features.Our systems are ranked 5 th in track 1 and 8 th in track 2.