A Hybrid Approach for Aspect-Based Sentiment Analysis Using a Lexicalized Domain Ontology and Attentional Neural Models

This work focuses on sentence-level aspect-based sentimentanalysis for restaurant reviews. A two-stage sentiment analysis algorithmis proposed. In this method, first a lexicalized domain ontology is used topredict the sentiment and as a back-up algorithm a neural network witha rotatory attention mechanism (LCR-Rot) is utilized. Furthermore, twofeatures are added to the backup algorithm. The first extension changesthe order in which the rotatory attention mechanism operates (LCRRot-inv). The second extension runs over the rotatory attention mechanism for multiple iterations (LCR-Rot-hop). Using the SemEval-2015and SemEval-2016 data, we conclude that the two-stage method outperforms the baseline methods, albeit with a small percentage. Moreover,we find that the method where we iterate multiple times over a rotatoryattention mechanism has the best performance.