Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling

Huije Lee, Hoyun Song, Jisu Shin, Sukmin Cho, SeungYoon Han, Jong C. Park

TL;DR

A methodology for generating counter-responses to trolls by recommending appropriate RSs is introduced, supported by a dataset aligning these strategies with human preferences across various troll contexts, and demonstrates that the proposed approach guides constructive discussion and reduces the negative effects of trolls, thereby enhancing the online community environment.

Abstract

Trolling in online communities typically involves disruptive behaviors such as provoking anger and manipulating discussions, leading to a polarized atmosphere and emotional distress. Robust moderation is essential for mitigating these negative impacts and maintaining a healthy and constructive community atmosphere. However, effectively addressing trolls is difficult because their behaviors vary widely and require different response strategies (RSs) to counter them. This diversity makes it challenging to choose an appropriate RS for each specific situation. To address this challenge, our research investigates whether humans have preferred strategies tailored to different types of trolling behaviors. Our findings reveal a correlation between the types of trolling encountered and the preferred RS. In this paper, we introduce a methodology for generating counter-responses to trolls by recommending appropriate RSs, supported by a dataset aligning these strategies with human preferences across various troll contexts. The experimental results demonstrate that our proposed approach guides constructive discussion and reduces the negative effects of trolls, thereby enhancing the online community environment.

Towards Effective Counter-Responses: Aligning Human Preferences with Strategies to Combat Online Trolling

TL;DR

A methodology for generating counter-responses to trolls by recommending appropriate RSs is introduced, supported by a dataset aligning these strategies with human preferences across various troll contexts, and demonstrates that the proposed approach guides constructive discussion and reduces the negative effects of trolls, thereby enhancing the online community environment.

Abstract

Trolling in online communities typically involves disruptive behaviors such as provoking anger and manipulating discussions, leading to a polarized atmosphere and emotional distress. Robust moderation is essential for mitigating these negative impacts and maintaining a healthy and constructive community atmosphere. However, effectively addressing trolls is difficult because their behaviors vary widely and require different response strategies (RSs) to counter them. This diversity makes it challenging to choose an appropriate RS for each specific situation. To address this challenge, our research investigates whether humans have preferred strategies tailored to different types of trolling behaviors. Our findings reveal a correlation between the types of trolling encountered and the preferred RS. In this paper, we introduce a methodology for generating counter-responses to trolls by recommending appropriate RSs, supported by a dataset aligning these strategies with human preferences across various troll contexts. The experimental results demonstrate that our proposed approach guides constructive discussion and reduces the negative effects of trolls, thereby enhancing the online community environment.
Paper Structure (31 sections, 4 equations, 5 figures, 15 tables)

This paper contains 31 sections, 4 equations, 5 figures, 15 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Data Collection
  5. Data Annotation
  6. Investigation of Human Preference
  7. Counter-Response Generation
  8. Experiments
  9. Experimental Setup
  10. Models
  11. Test Dataset
  12. Evaluation Metrics
  13. Experimental Results and Discussions
  14. Preference
  15. Constructiveness
  16. ...and 16 more sections

Figures (5)

  • Figure 1: Distribution of preferred RS relative to the TS. The top three bars indicate overt trolls, and the bottom three bars indicate covert trolls.
  • Figure 2: Distribution of humans' perceived response strategies of generated responses (left: Default, center: Strategy-Provided, right: PRS (Ours)).
  • Figure 3: Visualization of the rank test for preference.
  • Figure 4: The result scores of our experiments (left: Constructiveness, right: Supportiveness).
  • Figure 5: Interface snapshots for evaluation of three models.