TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates

Abstract

Political discourses provide a forum for representatives to express their opinions and contribute towards policy making. Analyzing these discussions is crucial for recognizing possible delegates and making better voting choices in an independent nation. A politician's vote on a proposition is usually associated with their past discourses and impacted by cohesion forces in political parties. We focus on predicting a speaker's vote on a bill by augmenting linguistic models with temporal and cohesion contexts. We propose TEC, a time evolving graph based model that jointly employs links between motions, speakers, and temporal politician states. TEC outperforms competitive models, illustrating the benefit of temporal and contextual signals for predicting a politician's stance.

Cite

Text

Sawhney et al. "TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/489

Markdown

[Sawhney et al. "TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/sawhney2021ijcai-tec/) doi:10.24963/IJCAI.2021/489

BibTeX

@inproceedings{sawhney2021ijcai-tec,
  title     = {{TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates}},
  author    = {Sawhney, Ramit and Agarwal, Shivam and Wadhwa, Arnav and Shah, Rajiv Ratn},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {3552-3558},
  doi       = {10.24963/IJCAI.2021/489},
  url       = {https://mlanthology.org/ijcai/2021/sawhney2021ijcai-tec/}
}