[Paper Review] In the Service of Online Order: Tackling Cyber-Bullying with Machine Learning and Affect Analysis

Michał Ptaszyński, Paweł Dybała+5 more|arXiv (Cornell University)|Mar 4, 2022

Bullying, Victimization, and Aggression15 references50 citations

TL;DR

The paper develops an automatic system to detect cyber-bullying entries on unofficial Japanese school sites using affect analysis and SVM, achieving an 88.2% balanced F-score.

ABSTRACT

One of the burning problems lately in Japan has been cyber-bullying, or slandering and bullying people online. The problem has been especially noticed on unofficial Web sites of Japanese schools. Volunteers consisting of school personnel and PTA (Parent-Teacher Association) members have started Online Patrol to spot malicious contents within Web forums and blogs. In practise, Online Patrol assumes reading through the whole Web contents, which is a task difficult to perform manually. With this paper we introduce a research intended to help PTA members perform Online Patrol more efficiently. We aim to develop a set of tools that can automatically detect malicious entries and report them to PTA members. First, we collected cyber-bullying data from unofficial school Web sites. Then we performed analysis of this data in two ways. Firstly, we analysed the entries with a multifaceted affect analysis system in order to find distinctive features for cyber-bullying and apply them to a machine learning classifier. Secondly, we applied a SVM based machine learning method to train a classifier for detection of cyber-bullying. The system was able to classify cyber-bullying entries with 88.2% of balanced F-score.

Motivation & Objective

• Motivate tools to help PTA members perform Online Patrol more efficiently.
• Collect cyber-bullying data from unofficial school websites for analysis.
• Explore affective features to distinguish cyber-bullying from benign content.
• Evaluate a machine learning classifier for cyber-bullying detection.

Proposed method

• Assemble cyber-bullying data from unofficial school web sites.
• Apply a multifaceted affect analysis system to extract distinctive features.
• Train a support vector machine (SVM) classifier using the affect features.
• Evaluate classification performance using balanced F-score.

Experimental results

Research questions

• RQ1 Can affective features distinguish cyber-bullying entries from other online content?
• RQ2 How effective is an SVM classifier with affect-based features in detecting cyber-bullying on school-related forums?
• RQ3 What is the classification performance (balanced F-score) of the proposed system?

Key findings

• The system uses multifaceted affect analysis to derive features for cyber-bullying detection.
• An SVM classifier trained on these features detects cyber-bullying with an 88.2% balanced F-score.
• The approach targets aiding Online Patrol efforts by automating harmful-content spotting.
• Data were collected from unofficial school websites for analysis.