Pith. sign in

REVIEW 1 cited by

Twitter Users' Behavioral Response to Toxic Replies

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2210.13420 v1 pith:3KMXTPK3 submitted 2022-10-24 cs.SI cs.CY

classification cs.SIcs.CY
keywords toxicconversationstoxicityrepliesvictimslikelyauthorsbehavioral
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Online toxic attacks, such as harassment, trolling, and hate speech have been linked to an increase in offline violence and negative psychological effects on victims. In this paper, we studied the impact of toxicity on users' online behavior. We collected a sample of 79.8k Twitter conversations. Then, through a longitudinal study, for nine weeks, we tracked and compared the behavioral reactions of authors, who were toxicity victims, with those who were not. We found that toxicity victims show a combination of the following behavioral reactions: avoidance, revenge, countermeasures, and negotiation. We performed statistical tests to understand the significance of the contribution of toxic replies toward user behaviors while considering confounding factors, such as the structure of conversations and the user accounts' visibility, identifiability, and activity level. Interestingly, we found that compared to other random authors, victims are more likely to engage in conversations, reply in a toxic way, and unfollow toxicity instigators. Even if the toxicity is directed at other participants, the root authors are more likely to engage in the conversations and reply in a toxic way. However, victims who have verified accounts are less likely to participate in conversations or respond by posting toxic comments. In addition, replies are more likely to be removed in conversations with a larger percentage of toxic nested replies and toxic replies directed at other users. Our results can assist further studies in developing more effective detection and intervention methods for reducing the negative consequences of toxicity on social media.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Adding six rhetorical codetype descriptions to frozen LLM embeddings improves implicit hate speech detection on Chinese and English benchmarks, though prompt-based gains are inconsistent.

Pith tools