Title: Lexicon-based sentiment analysis of Arabic tweets

Authors: Mahmoud Al-Ayyoub; Safa Bani Essa; Izzat Alsmadi

Addresses: Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan ' Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan ' Computer Science Department, Boise State University, Boise, ID, USA

Abstract: Sentiment analysis (SA) and opinions mining (OM) are used to evaluate users' feedbacks and comments on issues related to news, products, services, etc. This topic has received increasing interests over the last decade due to the spread and expansion of social networks. SA for online reviews poses challenges to researchers and decision makers because such comments are written in unstructured formats with usually informal languages, expressions and possibly mixed languages. For Arabic, further challenges exist due to the language complexity and the limited number of research publications and datasets collected and analysed for such purpose. In SA, two approaches are generally used to determine the polarity of reviews: supervised (corpus-based) and unsupervised (lexicon-based). In this work, we follow the second approach and build a very large sentiment lexicon and a lexicon-based SA tool. The results show that the proposed tool performs very well.

Keywords: sentiment analysis; natural language processing; NLP; sentiment lexicon; sentiment vector; Arabic tweets; social networking; Twitter.

DOI: 10.1504/IJSNM.2015.072280

International Journal of Social Network Mining, 2015 Vol.2 No.2, pp.101 - 114

Received: 24 Jun 2013
Accepted: 30 Jun 2014
Published online: 08 Oct 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article