An ML-Based Classification Scheme for Analyzing the Social Network Reviews of Yemeni People

The international arab journal of information technology

article

Emran Al-Buraihy¹  Wang Dan¹  Rafi Ullah Khan²  Mohib Ullah² 

[1] Faculty of information Technology, Beijing University of Technology;Institute of Computer Science and Information Technology, The University of Agriculture Peshawar

关键词: Social network;    sentiment analysis;    Arabic sentiment analysis;    MSA;    data mining;    supervised machine learning;   

DOI  :  10.34028/iajit/19/6/8

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

The social network allows individuals to create public and semi-public web-based profiles to communicate withother users in the network and online interaction sources. Social media sites such as Facebook, Twitter, etc., are primeexamples of the social network, which enable people to express their ideas, suggestions, views, and opinions about a particularproduct, service, political entity, and affairs. This research introduces a Machine Learning-based (ML-based) classificationscheme for analyzing the social network reviews of Yemeni people using data mining techniques. A constructed datasetconsisting of 2000 MSA and Yemeni dialects records used for training and testing purposes along with a test dataset consistingof 300 Modern Standard Arabic (MSA) and Yemeni dialects records used to demonstrate the capacity of our scheme. Foursupervised machine learning algorithms were applied and a comparison was made of performance algorithms based onAccuracy, Recall, Precision and F-measure. The results show that the Support Vector Machine algorithm outperformed theothers in terms of Accuracy on both training and testing datasets with 90.65% and 90.00, respectively. It is further noted thatthe accuracy of the selected algorithms was influenced by noisy and sarcastic opinions.

【 授权许可】

Unknown