mlsanityData to 7 Oct 2026

ConvoKit: A Toolkit for the Analysis of Conversations

arXiv 2005.04246 ↗First posted 8 May 2020cs.CL cs.SIcited by 71

Not on the map. Why?

Abstract (arXiv)

This paper describes the design and functionality of ConvoKit, an open-source toolkit for analyzing conversations and the social interactions embedded within. ConvoKit provides an unified framework for representing and manipulating conversational data, as well as a large and diverse collection of conversational datasets. By providing an intuitive interface for exploring and interacting with conversational data, this toolkit lowers the technical barriers for the broad adoption of computational methods for conversational analysis.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 10; 2023: 6; 2024: 13; 2025: 21; 2026: 14.

71 papers.

Sort:

By area:

  1. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  2. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 115
  3. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 83
  4. 2023When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Datasetcited by 51
  5. 2021Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attentioncited by 26
  6. 2024"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversationscited by 24
  7. 2024WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wildcited by 20
  8. 2021I Beg to Differ: A study of constructive disagreement in online conversationscited by 18
  9. 2021Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Stylescited by 18
  10. 2021The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identitycited by 16
  11. 2022Computationally Identifying Funneling and Focusing Questions in Classroom Discoursecited by 15
  12. 2022Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Supportcited by 15
38 more
  1. 2023''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Textcited by 15
  2. 2025How Deep Is Representational Bias in LLMs? The Cases of Caste and Religioncited by 14
  3. 2024Edu-ConvoKit: An Open-Source Library for Education Conversation Datacited by 11
  4. 2023HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysiscited by 10
  5. 2024An LLM Feature-based Framework for Dialogue Constructiveness Assessmentcited by 9
  6. 2025What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Textcited by 9
  7. 2021The structure of online social networks modulates the rate of lexical changecited by 8
  8. 2023Opening up Minds with Argumentative Dialoguescited by 8
  9. 2025Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guaranteescited by 8
  10. 2026OdysSim: Building Foundation Models for Human Behavior Simulationcited by 8
  11. 2026Evaluating Decision Models for Text Annotation in Computational Social Sciencecited by 8
  12. 2022Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Surveycited by 6
  13. 2023Assessing the efficacy of large language models in generating accurate teacher responsescited by 6
  14. 2024Deal, or no deal (or who knows)? Forecasting Uncertainty in Conversations using Large Language Modelscited by 6
  15. 2024How Did We Get Here? Summarizing Conversation Dynamicscited by 6
  16. 2022Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?cited by 5
  17. 2022Shedding New Light on the Language of the Dark Webcited by 5
  18. 2024Taking a turn for the better: Conversation redirection throughout the course of mental-health therapycited by 5
  19. 2025Sycophantic AI Decreases Prosocial Intentions and Promotes Dependencecited by 5
  20. 2025Residualized Similarity for Faithfully Explainable Authorship Verificationcited by 4
  21. 2025so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMscited by 4
  22. 2022RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generatorscited by 3
  23. 2024ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Promptscited by 3
  24. 2025Social Story Frames: Contextual Reasoning about Narrative Intent and Receptioncited by 3
  25. 2026CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Trackingcited by 3
  26. 2026Learning User Simulators with Turing Rewardscited by 3
  27. 2022Building and curating conversational corpora for diversity-aware language science and technologycited by 2
  28. 2025Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Modelscited by 2
  29. 2025From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiationcited by 2
  30. 2021Open-Mindedness and Style Coordination in Argumentative Discussionscited by 1
  31. 2021Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Modelscited by 1
  32. 2024The Branch Not Taken: Predicting Branching in Online Conversationscited by 1
  33. 2024Using RL to Identify Divisive Perspectives Improves LLMs Abilities to Identify Communities on Social Mediacited by 1
  34. 2024Real World Conversational Entity Linking Requires More Than Zeroshotscited by 1
  35. 2024Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysiscited by 1
  36. 2025A Similarity Measure for Comparing Conversational Dynamicscited by 1
  37. 2025Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learningcited by 1
  38. 2025AITutor-EvalKit: Exploring the Capabilities of AI Tutorscited by 1

50 most cited of 71 All 71 (JSON)