Zenodo (CERN European Organization for Nuclear Research) · 2020 · 13 citations · 0 references
Language StudiesArabicLinguisticsComputational LinguisticsNatural Language ProcessingText AnalyticsEmotion RecognitionOpinion MiningSentiment AnalysisLexicon-based Sentiment AnalysisSentiment Lexicon ConstructionTweet Sentiment Analysis
Recently, Sentiment Analysis applied to social media data has gradually become one of the significant<br> research interest in the data mining domain due to the large volume of data available on social media<br> networks. Sentiment Analysis is concerned with analyzing text to identify opinions or emotions and<br> categorizing them as positive, negative or neutral. Applying sentiment analysis to short texts such as Twitter<br> messages is a challenging task because tweets might contain a combination of formal and informal language,<br> special characters, emojis and symbols. Therefore, it is often difficult to understand the semantics of the text<br> and it is complex to extract the proper emotions expressed by users.<br> In this paper, sentiment analysis approaches, namely: lexicon-based and machine learning approaches, are<br> applied and evaluated on an Arabic tweets dataset (short texts) regarding the Syrian civil war and crises. The<br> experimental results revealed that machine learning approaches outperformed the lexicon-based in the<br> context of predicting the subjectivity of tweets. In terms of machine learning, five popular machine learning<br> algorithms were applied and evaluated. According to the experimental results, the Logistic Model Trees<br> (LMT) algorithm achieved the highest performance results, followed by the simple logistic and the SVM<br> algorithms, respectively. The results also showed that there are enhancements in performance when utilizing<br> feature selection approaches. Based on all performance evaluation measures, the LMT algorithms reported<br> the best performance results (Acc= 85.55, F1= 0.92 and AUC= 0.86).