A Machine Learning Approach For Classifying Sentiments in Arabic tweets

Abstract

Nowadays, sentiment analysis methods become more and more popular especially with the proliferation of social media platform users number. In the same context, this paper presents a sentiment analysis approach which can faithfully translate the sentimental orientation of Arabic Twitter posts, based on a novel data representation and machine learning techniques. The proposed approach applied a wide range of features: lexical, surface-form, syntactic, etc. We also made use of lexicon features inferred from two Arabic sentiment words lexicons. To build our supervised sentiment analysis system, we use several standard classification methods (Support Vector Machines, K-Nearest Neighbour, Naïve Bayes, Decision Trees, Random Forest) known by their effectiveness over such classification issues.In our study, Support Vector Machines classifier outperforms other supervised algorithms in Arabic Twitter sentiment analysis. Via an ablation experiments, we show the positive impact of lexicon based features on providing higher prediction performance.CCS Concepts • Computing methodologies➝Artificial intelligence➝Natural language processing➝Language resources • Computing methodologies➝Machine learning approaches.

Arabic CyberBullying Detection Using Arabic Sentiment Analysis

“…In the recent past, the application of SA is made on the classification of text with the English language [18]- [23]. However, there is a research gap in the application of SA for the Arabic language; we have very rare research such as [24]- [27]. In the use of SA, the researchers worked on the movie review, forums, news articles, and data of social media [28].…”

“…They compared their proposed method with the baseline methods of TF-IDF and semantic [31]. In addition to this, Bouchlaghem et al [27] developed an approach based on the semantic analysis in order to translate the Arabic tweet orientation that is used for terroristic acts. They have developed a data representation method by using the N-gram features, "sentence-level features," linguistic features, syntactic features, and "tweets specific features.…”

Anti-Islamic Arabic Text Categorization using Text Mining and Sentiment Analysis Techniques

“…Moreover, some words appear in a domain that changes the polarity depending on the domain in which they are. In addition, some opinions are expressed in a sarcastic way, which causes inaccuracies in the polarity of the word [9].…”

“…Detection of Arabic fake news is considered a rough task as the Arabic sentiment resources are limited as well as the corpora and lexicon of Arabic language. Therefore, some researchers [6], [7], [8], [9], [12] and [13] have spent some time trying to solve these issues and implement fake news detection for Arabic texts. Alkhair et al [12] classified Arabic YouTube comments into rumor and not-rumor.…”

“…Bouchlaghem et al [9] focused on sentiment analysis for MSA on a dataset consisting of Twitter posts. They used several sentiment features including lexicon features, linguistic features and sentence specific features.…”