# How Did We Get Here? Summarizing Conversation Dynamics

arXiv: https://arxiv.org/abs/2404.19007 · HTML: https://mlsanity.com/paper/2404.19007/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 66 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 30 of 36)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [A Computational Approach to Politeness with Application to Social Factors](https://mlsanity.com/paper/1306.6078/) (2013)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [ConvoKit: A Toolkit for the Analysis of Conversations](https://mlsanity.com/paper/2005.04246/) (2020)
- [Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2010.01672/) (2020)
- [A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods](https://mlsanity.com/paper/2104.00054/) (2021)
- [Learning to Summarize Radiology Findings](https://mlsanity.com/paper/1809.04698/) (2018)
- [Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts](https://mlsanity.com/paper/1809.05715/) (2018)
- [Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop](https://mlsanity.com/paper/1909.01362/) (2019)
- [Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs](https://mlsanity.com/paper/2104.08400/) (2021)
- [Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation](https://mlsanity.com/paper/1802.06613/) (2018)
- [Exploring the Role of Argument Structure in Online Debate Persuasion](https://mlsanity.com/paper/2010.03538/) (2020)
- [Something's Brewing! Early Prediction of Controversy-causing Posts from Discussion Features](https://mlsanity.com/paper/1904.07372/) (2019)
- [TalkDown: A Corpus for Condescension Detection in Context](https://mlsanity.com/paper/1909.11272/) (2019)
- [Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations](https://mlsanity.com/paper/2102.08368/) (2021)
- [Conversational Markers of Constructive Discussions](https://mlsanity.com/paper/1604.07407/) (2016)
- [Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game](https://mlsanity.com/paper/1506.04744/) (2015)
- [Dynamic Forecasting of Conversation Derailment](https://mlsanity.com/paper/2110.05111/) (2021)
- [Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support](https://mlsanity.com/paper/2211.16525/) (2022)
- [Forecasting the presence and intensity of hostility on Instagram using linguistic and social features](https://mlsanity.com/paper/1804.06759/) (2018)
- [Thread With Caution: Proactively Helping Users Assess and Deescalate Tension in Their Online Discussions](https://mlsanity.com/paper/2212.01401/) (2022)
- [Studying Politeness across Cultures Using English Twitter and Mandarin Weibo](https://mlsanity.com/paper/2008.02449/) (2020)
- [What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process](https://mlsanity.com/paper/2002.03536/) (2020)

## Built on by (most cited first, 6 of 6)

- [Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations](https://mlsanity.com/paper/2409.18602/) (2024)
- [What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma](https://mlsanity.com/paper/2505.12727/) (2025)
- [Forecasting Conversation Derailments Through Generation](https://mlsanity.com/paper/2504.08905/) (2025)
- [Conversational DNA: A Visual Language and Interactive Atlas of Human and AI Dialogue](https://mlsanity.com/paper/2508.07520/) (2025)
- [Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition](https://mlsanity.com/paper/2607.14769/) (2026)
- [Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment Forecasting](https://mlsanity.com/paper/2608.25359/) (2026)

## Abstract (arXiv)

Throughout a conversation, the way participants interact with each other is in constant flux: their tones may change, they may resort to different strategies to convey their points, or they might alter their interaction patterns. An understanding of these dynamics can complement that of the actual facts and opinions discussed, offering a more holistic view of the trajectory of the conversation: how it arrived at its current state and where it is likely heading. In this work, we introduce the task of summarizing the dynamics of conversations, by constructing a dataset of human-written summaries, and exploring several automated baselines. We evaluate whether such summaries can capture the trajectory of conversations via an established downstream task: forecasting whether an ongoing conversation will eventually derail into toxic behavior. We show that they help both humans and automated systems with this forecasting task. Humans make predictions three times faster, and with greater confidence, when reading the summaries than when reading the transcripts. Furthermore, automated forecasting systems are more accurate when constructing, and then predicting based on, summaries of conversation dynamics, compared to directly predicting on the transcripts.