LICD: A Language-Independent Approach for Aspect Category Detection

Abstract

Aspect-based sentiment analysis (ABSA) deals with processing and summarizing customer reviews and has been a topic of interest in recent years. Given a set of predefined categories, Aspect Category Detection (ACD), as a subtask of ABSA, aims to assign a subset of these categories to a given review sentence. Thanks to the existence of websites such as Yelp and TripAdvisor, there exist a huge amount of reviews in several languages, and therefore the need for language-independent methods in this task seems necessary. In this paper, we propose Language-Independent Category Detector (LICD), a supervised method based on text matching without the need for any language-specific tools and hand-crafted features for identifying aspect categories. For a given sentence, our proposed method performs ACD based on two hypotheses: First, a category should be assigned to a sentence if there is a high semantic similarity between the sentence and a set of representative words of that category. Second, a category should be assigned to a sentence if sentences with high semantic and structural similarity to that sentence belong to that category. To apply the former hypothesis, we used soft cosine measure, and for the latter, word mover’s distance measure is utilized. Using these two measures, for a given sentence we calculate a set of similarity scores as features for a one-vs-all logistic regression classifier per category. Experimental results on the multilingual SemEval-2016 datasets in the restaurant domain demonstrate that our approach outperforms baseline methods in English, Russian, and Dutch languages, and obtains competitive results with the strong deep neural network-based baselines in French, Turkish, and Spanish languages.