Twitter Bot Detection Using Diverse Content Features and Applying Machine Learning Algorithms

Fawaz Khaled Alarfaj (), Hassaan Ahmad, Hikmat Ullah Khan (), Abdullah Mohammaed Alomair, Naif Almusallam and Muzamil Ahmed
Additional contact information
Fawaz Khaled Alarfaj: Management Information Systems, School of Business, King Faisal University, Hofuf 31982, Saudi Arabia
Hassaan Ahmad: Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt 47040, Pakistan
Hikmat Ullah Khan: Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt 47040, Pakistan
Abdullah Mohammaed Alomair: Management Information Systems, School of Business, King Faisal University, Hofuf 31982, Saudi Arabia
Naif Almusallam: Management Information Systems, School of Business, King Faisal University, Hofuf 31982, Saudi Arabia
Muzamil Ahmed: Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt 47040, Pakistan

Sustainability, 2023, vol. 15, issue 8, 1-17

Abstract: A social bot is an intelligent computer program that acts like a human and carries out various activities in a social network. A Twitter bot is one of the most common forms of social bots. The detection of Twitter bots has become imperative to draw lines between real and unreal Twitter users. In this research study, the main aim is to detect Twitter bots based on diverse content-specific feature sets and explore the use of state-of-the-art machine learning classifiers. The real-world data from Twitter is scrapped using Twitter API and is pre-processed using standard procedure. To analyze the content of tweets, several feature sets are proposed, such as message-based, part-of-speech, special characters, and sentiment-based feature sets. Min-max normalization is considered for data normalization and then feature selection methods are applied to rank the top features within each feature set. For empirical analysis, robust machine learning algorithms such as deep learning (DL), multilayer perceptron (MLP), random forest (RF), naïve Bayes (NB), and rule-based classification (RBC) are applied. The performance evaluation based on standard metrics of precision, accuracy, recall, and f-measure reveals that the proposed approach outperforms the existing studies in the relevant literature. In addition, we explore the effectiveness of each feature set for the detection of Twitter bots.

Keywords: bot detection; machine learning; deep learning; feature engineering; cyber security (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/8/6662/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/8/6662/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:8:p:6662-:d:1123645

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().