Summary of Conversation Derailment Forecasting with Graph Convolutional Networks, by Enas Altarawneh et al.
Conversation Derailment Forecasting with Graph Convolutional Networks
by Enas Altarawneh, Ammeta Agrawal, Michael Jenkin, Manos Papagelis
First submitted to arxiv on: 22 Jun 2023
Categories
- Main: Computation and Language (cs.CL)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper proposes a novel approach to forecasting online conversation derailment using graph convolutional neural networks (GCNNs). The model takes into account dialogue user dynamics and public perception influences on utterances, departing from traditional sequence-based models that treat dialogues as text streams. Empirical evaluations demonstrate the effectiveness of this approach in capturing conversation dynamics, outperforming state-of-the-art methods on benchmark datasets such as CGA and CMV by 1.5% and 1.7%, respectively. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a world where online conversations can quickly go awry, researchers are working to predict when these conversations might take a turn for the worse. To do this, they need to understand what makes certain comments or messages “toxic.” This new approach uses special kinds of computer models called graph convolutional neural networks to analyze online chats and identify patterns that might lead to trouble. By doing so, it can help moderators step in before things get out of hand. |
