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

Abstract

The aim of this research is to detect and classify websites based on their content if it encourages spreading hate speech toward Islam and Muslims, or Islamophobia using sentiment analysis and web text mining techniques. In this research, a large dataset corpus has been collected, to identify and classify anti-Islamic online contents. Our target is to automatically detect the content of those websites that are hostile to Islam and transmitting extremist ideas against it. The main purpose is to reduce the spread of those webpages that give the wrong idea about Islam. The proper dataset is collected from different sources, and the two datasets for the Arabic language (balanced and unbalanced) have been produced. The framework of the proposed approach has been described. The approach used in this framework is based on supervised Machine Learning (ML) approach using Support Vector Machines (SVM) and Multinomial Naive Bayes (MNB) models as classifiers, and Term Frequency-Inverse Document Frequency (TF-IDF) as feature extraction. Different experiments including word level and trigram level on the two datasets have been conducted, and compared the obtained results. The experimental results shows that the supervised ML approach using word level is the finest approach for both datasets that produce high accuracy with 97% applied on the balanced Arabic dataset using SVM algorithm with TF-IDF as feature extraction. Finally, an interactive webapplication prototype has been developed and built in order to detect and classify toxic language such as anti-Islamic online textcontents.

MR-FNC: A Fake News Classification Model to Mitigate Racism

“…Because of embedment of deep and text attributes, the SVM model offers an accuracy more than 95% on the validation data. Alraddadi et al [17] categorized text utilizing sentiment and text analysis techniques. Arabic dataset obtained for the 3 months of 2021is based on news articles and publications from famous search engines.…”

Federated-Learning Topic Modeling Based Text Classification Regarding Hate Speech During COVID-19 Pandemic

“…Khan et al [17] collected 8438 English and 8790 Hindi tweets from Twitter, and used Word2Vec, GloVe, BERT, and n-gram methods for the classification of tweets polarity classes. Alraddadi et al [18] performed Arabic text classification using a dataset compiled using the Octoparse scrapping tool, and utilized ML algorithms such as KNN,SVM, LR, MNB, and NB for data classification. Vidgen and Yasseri [19] proposed a technique for classifying Islamophobic hate speech using KNN, SVM, LR, MNB, and CNN.…”

“…but it is still not being given due attention and consideration as a global issue. The internet and social media are one of the primary means of disseminating fake news and false information around the world [2], [3], [4], [5]. Consequetenly, Muslim community is facing several challenges in their daily as well as professional life where they are in minority in different parts of the world [6].…”

Sentiment Analysist of the TPKS Law on Twitter Using InSet Lexicon with Multinomial Naïve Bayes and Support Vector Machine Based on Soft Voting

“…Naïve Bayes is known as a simple powerful model, especially in the field of document classification and disease prediction [9], while the support vector machine is a machine learning algorithm that has a good and efficient training stage, hence good performance is obtained [10]. Previous study using multinomial naïve Bayes and support vector machines has been done by [11]. The study discusses the classification of anti-Islamic texts in Arabic by comparing several algorithms, such as k-NN, decision tree, random forest, logistic regression, multinomial naïve Bayes and support vector machine.…”