WarwickDCS : from phrase-based to target-specific sentiment recognition

Townsend, Richard; Tsakalidis, Adam; Zhou, Yiwei; Wang, Bo; Liakata, M.; Zubiaga, Arkaitz; Cristea, A.I.; Procter, Rob

Abstract

We present and evaluate several hybrid systems for sentiment identification for Twitter, both at the phrase and document (tweet) level. Our approach has been to use a novel combination of lexica, traditional NLP and deep learning features. We also analyse techniques based on syntactic parsing and tokenbased association to handle topic specific sentiment in subtask C. Our strategy has been to identify subphrases relevant to the designated topic/target and assign sentiment according to our subtask A classifier. Our submitted subtask A classifier ranked fourth in the SemEval official results while our BASELINE and µPARSE classifiers for subtask C would have ranked second.

Citation

Townsend, R., Tsakalidis, A., Zhou, Y., Wang, B., Liakata, M., Zubiaga, A., Cristea, A., & Procter, R. (2015, June). WarwickDCS : from phrase-based to target-specific sentiment recognition. Presented at 9th International Workshop on Semantic Evaluation (SemEval 2015), Denver

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 9th International Workshop on Semantic Evaluation (SemEval 2015)
• Publication Date: Jun 1, 2015
• Deposit Date: Jul 11, 2018
• Publicly Available Date: Jul 31, 2018
• Publisher: Association for Computational Linguistics
• Pages: 657-663
• Book Title: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).
• DOI: https://doi.org/10.18653/v1/s15-2110
• Public URL: https://durham-repository.worktribe.com/output/1145180
• Related Public URLs: http://wrap.warwick.ac.uk/71340/