Author:
Hidey Christopher,McKeown Kathleen
Abstract
Automatic detection of persuasion in online discussion is key to understanding how social media is used. Predicting persuasiveness is difficult, however, due to the need to model world knowledge, dialogue, and sequential reasoning. We focus on modeling the sequence of arguments in social media posts using neural models with embeddings for words, discourse relations, and semantic frames. We demonstrate significant improvement over prior work in detecting successful arguments. We also present an error analysis assessing novice human performance at predicting persuasiveness.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Analyzing the impact of conversation structure on predicting persuasive comments online;Journal of Ambient Intelligence and Humanized Computing;2024-09-02
2. Discourse-Aware Prompt for Argument Impact Classification;Proceedings of the 2023 15th International Conference on Machine Learning and Computing;2023-02-17
3. Do You Know My Emotion? Emotion-Aware Strategy Recognition Towards a Persuasive Dialogue System;Machine Learning and Knowledge Discovery in Databases;2023
4. Computational Approaches to Persuasion Detection and Potential of Use in Social Engineering;Proceedings of the Future Technologies Conference (FTC) 2023, Volume 4;2023
5. Argument Mining and Analytics in Archaeology;Discourse and Argumentation in Archaeology: Conceptual and Computational Approaches;2023