Detecting covert disruptive behavior in online interaction by analyzing conversational features and norm violations

Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2024-01-29

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

ACM Transactions on Computer-Human Interaction

Abstract

Disruptive behavior is a prevalent threat to constructive online engagement. Covert behaviors, such as trolling, are especially challenging to detect automatically, because they utilize deceptive strategies to manipulate conversation. We illustrate a novel approach to their detection: analyzing conversational structures instead of focusing only on messages in isolation. Building on conversation analysis, we demonstrate that (1) conversational actions and their norms provide concepts for a deeper understanding of covert disruption, and that (2) machine learning, natural language processing and structural analysis of conversation can complement message-level features to create models that surpass earlier approaches to trolling detection. Our models, developed for detecting overt (aggression) as well as covert (trolling) behaviors using prior studies' message-level features and new conversational action features, achieved high accuracies (0.90 and 0.92, respectively). The findings offer a theoretically grounded approach to computationally analyzing social media interaction and novel methods for effectively detecting covert disruptive conversations online.

Description

Keywords

Additional Key Words and PhrasesDisruptive behavior, detection, machine learning, natural language processing, online aggression, online trolling

Other note

Citation

Paakki, H, Vepsäläinen, H, Salovaara, A & Zafar, B 2024, ' Detecting covert disruptive behavior in online interaction by analyzing conversational features and norm violations ', ACM Transactions on Computer-Human Interaction, vol. 31, no. 2, 20 . https://doi.org/10.1145/3635143