Mariam Biltawi, Wael Etaiwi, Sara Tedmori, Adnan Shaout. (2019) Fuzzy Based Sentiment Classification in the Arabic Language. In: Arai K., Kapoor S., Bhatia R. (eds) Intelligent Systems and Applications. IntelliSys 2018. Advances in Intelligent Systems and Computing, vol 868. Springer, Cham

Abstract

Sentiment Analysis is the task of identifying individuals’ positive and negative opinions, emotions and evaluations concerning a specific object. Fuzzy logic in the field of sentiment analysis can be employed to classify the polarity of sentences or documents. Although some efforts have been made by researchers who applied fuzzy logic for Sentiment Analysis on English texts, to the best of the authors’ knowledge, no efforts have been made targeting Arabic texts. This paper proposes a lexicon based approach to extract sentiment polarity from Arabic text using a fuzzy logic approach. The proposed approach consists of two main phases. In the first phase, Arabic text is assigned weights, while in the second phase fuzzy logic is employed to assign the polarity to the inputted sentence. Experiments were conducted on Large Scale Arabic Book Reviews Dataset (LABR), and the results showed 94.87%, 84.04%, 80.59% and 89.13% for recall, precision, accuracy, and F1-measure, respectively.