TwitterHawk - a Twitter Sentiment Analysis System

TwitterHawk is an open-source natural language processing system for Twitter sentiment analysis. This system was developed for the SemEval-2015 Task 10: Sentiment Analysis in Twitter. The system placed 1st in topic-based sentiment classification (Subtask C), and ranked 6th out of 40 in identifying the sentiment of sarcastic tweets (for Subtask B). The system also placed 5th/11 for Subtask A (sentiment of a tweet's sub-phrase), 10th/40 for Subtask B (sentiment of a full tweet), and 3rd/6 for Subtask D (summarization of Subtask C). TwitterHawk implements two classifiers, one for message-level sentiment, and one of phrase-level sentiment detection.


W. Boag P. Potash A. Rumshisky TwitterHawk: A Feature Bucket Based Approach to Sentiment Analysis. The 9th International Workshop on Semantic Evaluation (SemEval-2015). NAACL HLT 2015.

@inproceedings{boag2015twitterhawk, title={TwitterHawk: A feature bucket based approach to sentiment analysis}, author={Boag, William and Potash, Peter and Rumshisky, Anna}, booktitle={Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)}, pages={640–646}, year={2015} }