This paper reports our submission to the Aspect-Based Sentiment Analysis task of SemEval 2016. It covers the prediction of sentiment for a given set of aspects (e.g., subtask 1, slot 2) for the English language using discourse analysis. To that end, a discourse parser implementing the Rhetorical Structure Theory is employed and the resulting information is used to determine the context of each aspect, as well as to compute the expressed sentiment in that context by weighing the discourse relations between words. While discourse analysis yields high level linguistic information that can be used to better predict sentiment, the proposed algorithm does not yet stack up to the high-performing machine learning approaches that are commonly exploited for this task.

Additional Metadata
Persistent URL hdl.handle.net/1765/103220
Conference 10th International Workshop on Semantic Evaluation, SemEval 2016
Citation
Schouten, K, & Frasincar, F. (2016). COMMIT at SemEval-2016 task 5: Sentiment analysis with rhetorical structure theory. In SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings (pp. 356–360). Retrieved from http://hdl.handle.net/1765/103220