mlsanityData to 7 Oct 2026

Conversations Gone Awry: Detecting Early Signs of Conversational Failure

arXiv 1805.05345 ↗First posted 14 May 2018cs.CL cs.AI cs.CYcited by 73

Not on the map. Why?

Abstract (arXiv)

One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged. To this end, we develop a framework for capturing pragmatic devices---such as politeness strategies and rhetorical prompts---used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 8; 2023: 14; 2024: 10; 2025: 10; 2026: 13.

73 papers.

Sort:

By area:

  1. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  2. 2023CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotationcited by 93
  3. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  4. 2021Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contextscited by 56
  5. 2023Rehearsal: Simulating Conflict to Teach Conflict Resolutioncited by 54
  6. 2022Neural Approaches to Conversational Information Retrievalcited by 41
  7. 2023Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Modelscited by 37
  8. 2021Civil Rephrases Of Toxic Texts With Self-Supervised Transformerscited by 32
  9. 2022Robust Conversational Agents against Imperceptible Toxicity Triggerscited by 23
  10. 2021Artificial intelligence in communication impacts language and social relationshipscited by 22
  11. 2021Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversationscited by 20
  12. 2021Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detectioncited by 19
38 more
  1. 2021I Beg to Differ: A study of constructive disagreement in online conversationscited by 18
  2. 2021Detecting Community Sensitive Norm Violations in Online Conversationscited by 18
  3. 2024Accounting for Sycophancy in Language Model Uncertainty Estimationcited by 18
  4. 2021Dynamic Forecasting of Conversation Derailmentcited by 16
  5. 2022Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Supportcited by 15
  6. 2021An Exploratory Analysis of the Relation Between Offensive Language and Mental Healthcited by 14
  7. 2021CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detectioncited by 14
  8. 2023Watch Your Language: Investigating Content Moderation with Large Language Modelscited by 14
  9. 2021Countering Online Hate Speech: An NLP Perspectivecited by 12
  10. 2021Decision-Focused Summarizationcited by 11
  11. 2022Thread With Caution: Proactively Helping Users Assess and Deescalate Tension in Their Online Discussionscited by 11
  12. 2025BASIL: Bayesian Assessment of Sycophancy in LLMscited by 11
  13. 2024An LLM Feature-based Framework for Dialogue Constructiveness Assessmentcited by 9
  14. 2024Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversationscited by 9
  15. 2022Automated Identification of Toxic Code Reviews Using ToxiCRcited by 8
  16. 2024Computational Politeness in Natural Language Processing: A Surveycited by 8
  17. 2025Evaluation and Facilitation of Online Discussions in the LLM Era: A Surveycited by 8
  18. 2026Evaluating Decision Models for Text Annotation in Computational Social Sciencecited by 8
  19. 2023CPL-NoViD: Context-Aware Prompt-based Learning for Norm Violation Detection in Online Communitiescited by 7
  20. 2021WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spanscited by 6
  21. 2021Toxicity Detection can be Sensitive to the Conversational Contextcited by 6
  22. 2022How to disagree well: Investigating the dispute tactics used on Wikipediacited by 6
  23. 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarizationcited by 6
  24. 2023Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationshipscited by 6
  25. 2024Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Modelscited by 6
  26. 2022Predicting the Type and Target of Offensive Social Media Posts in Marathicited by 5
  27. 2025Echoes of Discord: Forecasting Hater Reactions to Counterspeechcited by 5
  28. 2025Towards a Perspectivist Turn in Argument Quality Assessmentcited by 5
  29. 2021Linguistic Characterization of Divisive Topics Online: Case Studies on Contentiousness in Abortion, Climate Change, and Gun Controlcited by 4
  30. 2025Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communicationcited by 4
  31. 2024Putting Context in Context: the Impact of Discussion Structure on Text Classificationcited by 3
  32. 2021A Survey of Online Hate Speech through the Causal Lenscited by 2
  33. 2023Conversation Modeling to Predict Derailmentcited by 2
  34. 2023A Deeper (Autoregressive) Approach to Non-Convergent Discourse Parsingcited by 2
  35. 2023Dimensions of Online Conflict: Towards Modeling Agonismcited by 2
  36. 2024Social Orientation: A New Feature for Dialogue Analysiscited by 2
  37. 2025Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Modelscited by 2
  38. 2025Learning When to Quit in Sales Conversationscited by 2

50 most cited of 73 All 73 (JSON)