Resumen

BRAHIMI, Belgacem; TOUAHRIA, Mohamed  y  TARI, Abdelkamel. Improving Arabic Sentiment Classification Using a Combined Approach. Comp. y Sist. [online]. 2020, vol.24, n.4, pp.1403-1414.  Epub 11-Jun-2021. ISSN 2007-9737.  https://doi.org/10.13053/cys-24-4-3154.

The aim of sentiment analysis is to automatically extract and classify a textual review as expressing a positive or negative opinion. In this paper, we study the sentiment classification problem in the Arabic language. We propose a method that attempts to extract subjective parts of document reviews. First, we select explicit opinions related to given aspects. Second, a semantic approach is used to find implicit opinions and sentiments in reviews. Third, we combine the extracted aspect opinions with the sentiment words returned by the lexical approach. Finally, a feature reduction technique is applied. To evaluate the proposed method, support vector machines (SVM) classifier is applied for the classification task on two datasets. Our results indicate that the proposed approach provides superior performance in terms of classification measures.

Palabras llave : Text mining; opinion mining; sentiment classification; supervised learning; review extraction; combined approach.

        · texto en Inglés     · Inglés ( pdf )