Target-dependent sentiment analysis on Twitter has attracted increasing research attention. Most previous work relies on syntax, such as automatic parse trees, which are subject to noise for informal text such as tweets. In this paper, we show that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features. In particular, we split a tweet into a left context and a right context according to a given target, using distributed word representations and neural pooling functions to extract features. Both sentiment-driven and standard embeddings are used, and a rich set of neural pooling functions are explored. Sentiment lexicons are used as an additional source of information for feature extraction. In standard evaluation, the conceptually simple method gives a 4.8% absolute improvement over the state-of-the-art on three-way targeted sentiment classification, achieving the best reported results for this task.
Vo Duy Tin is currently a graduate student in Singapore University of Technology and Design. He received his Bachelor of Engineering in Electronics and Telecommunication from CanTho University, Vietnam in 2011. His research interests are in natural language processing, signal and image processing.