Persuasive Influence Detection: The Role of Argument Sequencing
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.
Cite
Text
Hidey and McKeown. "Persuasive Influence Detection: The Role of Argument Sequencing." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12003Markdown
[Hidey and McKeown. "Persuasive Influence Detection: The Role of Argument Sequencing." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/hidey2018aaai-persuasive/) doi:10.1609/AAAI.V32I1.12003BibTeX
@inproceedings{hidey2018aaai-persuasive,
title = {{Persuasive Influence Detection: The Role of Argument Sequencing}},
author = {Hidey, Christopher and McKeown, Kathleen R.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2018},
pages = {5173-5180},
doi = {10.1609/AAAI.V32I1.12003},
url = {https://mlanthology.org/aaai/2018/hidey2018aaai-persuasive/}
}