Investigating the Use of Machine Learning Algorithms in Detecting Gender of the Arabic Tweet Author

Abstract

Abstract-Twitter is one of the most popular social network sites on the Internet to share opinions and knowledge extensively. Many advertisers use these Tweets to collect some features and attributes of Tweeters to target specific groups of highly engaged people. Gender detection is a sub-field of sentiment analysis for extracting and predicting the gender of a Tweet author. In this paper, we aim to investigate the gender of Tweet authors using different classification mining techniques on Arabic language, such as Naïve Bayes (NB), Support vector machine (SVM), Naïve Bayes Multinomial (NBM), J48 decision tree, KNN. The results show that the NBM, SVM, and J48 classifiers can achieve accuracy above to 98%, by adding names of Tweet author as a feature. The results also show that the preprocessing approach has negative effect on the accuracy of gender detection. In nutshell, this study shows that the ability of using machine learning classifiers in detecting the gender of Arabic Tweet author.

A Comprehensive Study of Learning Approaches for Author Gender Identification

“…In a subsequent study, Deitrick et al [21] showed that exploiting feature selection methods improves the results substantially on n-gram features. Several studies [5,6,37,39,42,47,59,61] also presented models for author gender detection of writers of the social media in different languages.…”

Sehaa: A Big Data Analytics Tool for Healthcare Symptoms and Diseases Detection Using Twitter, Apache Spark, and Machine Learning

“…There are several challenges that hinder the development of tools for Twitter data analytics in the Arabic language, the greatest being the complexity of the language itself. Research on Twitter data analytics in Arabic has begun to appear in recent years in various application domains (detecting authors' genders [12], detecting traffic related events [18,20,38], finding restaurants' reputations [13]) but the progress has been slow. Moreover, some works are available in Modern Standard Arabic (MSA), but in general (not specific to healthcare), the works on Arabic dialects are very limited in number and scope [10,14].…”

Author Profiling Tracks at FIRE

“…Subsequently, the authors in [2] extend their work by experimenting with different machine learning algorithms, data subsets and feature selection methods, reporting accuracies up to 94%. The authors in [1] manually annotate tweets from Jordanian dialects with gender information. They show how the name of the author of the tweet can significantly improve the performance.…”