Abstract

In the ultra-connected age of information, online social media platforms have become an indispensable part of our daily routines. Recently, this online public space is getting largely occupied by suspicious and manipulative social media bots. Such automated deceptive bots often attempt to distort ground realities and manipulate global trends, thus creating astroturfing attacks on the social media online portals. Moreover, these bots often tend to participate in duplicitous activities, including promotion of hidden agendas and indulgence in biased propagation meant for personal gain or scams. Thus, online bots have eventually become one of the biggest menaces for social media platforms. Therefore, we have proposed an AI-driven social media bot identification framework, namely TweezBot, which can identify fraudulent Twitter bots. The proposed bot detection method analyzes Twitter-specific user profiles having essential profile-centric features and several activity-centric characteristics. We have constructed a set of filtering criteria and devised an exhaustive bag of words for performing language-based processing. In order to substantiate our research, we have performed a comparative study of our model with the existing benchmark classifiers, such as Support Vector Machine, Categorical Naïve Bayes, Bernoulli Naïve Bayes, Multilayer Perceptron, Decision Trees, Random Forest and other automation identifiers.

Highlights

  • Tweets were originally comprised of 140 characters, but with the growing popularity of Twitter in the domain of social media, the limit was eventually increased to 280 characters for non-CJK languages, that is, the languages consisting of Chinese, Japanese and Korean characters

  • The machine learning models used for comparative analysis include Random Forest, Decision Tree, Bernoulli Naïve Bayes, Categorical Naïve Bayes, Support Vector Classifier and Multi-layer Perceptron (ANN) [27,28]

  • With the increase in traffic on social media, there has been a considerable increase in the existence of automated bots that often try to replicate and mimic user choices and behavior for commercial purposes

Read more

Summary

Introduction

Twitter is a microblogging site which was founded in 2006 with the motive to create an online platform for interactive discourse. With the incredible amount of tweets sent out every day, amounting to billions every year, the chance of various forms of cyber threats began to erupt. This includes fraud, scam, spamming, and duplicitous behaviour over online social media platforms [2]. Aggressive marketing and advertising has led to a flux of bots using the Twitter API in a malicious manner. Our research initiative is to tackle the menace of cyber threats posed by online bots on Twitter social media. Our proposed TweezBot model aims at revealing the automated tweeting behavior of online Twitter bots.

Related Work
Research Methodologies
Correlation Statistics
Decision Trees
Random Forest Classifier
Bernoulli Naïve Bayes
Categorical Naïve-Bayes
Support Vector Machine
Multi-Layer Perceptron
Proposed Framework
Experimental Outcomes
Feature Analysis
Exploratory Data Analysis
Assessing Bot Behaviour
Comparative Performance Evaluation
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call