{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-comparative-study-of-feature-selection","title":"A Comparative Study of Feature Selection Methods for Dialectal Arabic Sentiment Classification Using Support Vector Machine","arxiv_id":"1902.06242","date":"2019-02-17","proceeding":null,"authors":["Omar Al-Harbi"],"abstract":"Unlike other languages, the Arabic language has a morphological complexity\nwhich makes the Arabic sentiment analysis is a challenging task. Moreover, the\npresence of the dialects in the Arabic texts have made the sentiment analysis\ntask is more challenging, due to the absence of specific rules that govern the\nwriting or speaking system. Generally, one of the problems of sentiment\nanalysis is the high dimensionality of the feature vector. To resolve this\nproblem, many feature selection methods have been proposed. In contrast to the\ndialectal Arabic language, these selection methods have been investigated\nwidely for the English language. This work investigated the effect of feature\nselection methods and their combinations on dialectal Arabic sentiment\nclassification. The feature selection methods are Information Gain (IG),\nCorrelation, Support Vector Machine (SVM), Gini Index (GI), and Chi-Square. A\nnumber of experiments were carried out on dialectical Jordanian reviews with\nusing an SVM classifier. Furthermore, the effect of different term weighting\nschemes, stemmers, stop words removal, and feature models on the performance\nwere investigated. The experimental results showed that the best performance of\nthe SVM classifier was obtained after the SVM and correlation feature selection\nmethods had been combined with the uni-gram model.","url_abs":"http://arxiv.org/abs/1902.06242v1","url_pdf":"http://arxiv.org/pdf/1902.06242v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-comparative-study-of-feature-selection","repo_url":"https://github.com/anastasialavrova/bmstu_bachelor_qualification_work","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"arabic-sentiment-analysis","task_name":"Arabic Sentiment Analysis"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}