XRCE: Hybrid Classification for Aspect-based Sentiment Analysis

Abstract

In this paper, we present the system we have developed for the SemEval-2014 Task 4 dedicated to Aspect-Based Sentiment Analysis. The system is based on a robust parser that provides information to feed different classifiers with linguistic features dedicated to aspect categories and aspect categories polarity classification. We mainly present the work which has been done on the restaurant domain 1 for the four subtasks, aspect term and category detection and aspect term and category polarity.