---
title: "TEC: A Time Evolving Contextual Graph Model for Speaker State Analysis in Political Debates"
authors:
  - "Ramit Sawhney"
  - "Shivam Agarwal"
  - "Arnav Wadhwa"
  - "Rajiv Shah"
doi: "10.24963/ijcai.2021/489"
url: "https://ijcai.org/proceedings/2021/489"
pdf: "https://ijcai.org/proceedings/2021/0489.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "3552-3558"
track: "Main Track"
keywords:
  - "Natural Language Processing: NLP Applications and Tools"
  - "Machine Learning Applications: Humanities"
---

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

Ramit Sawhney, Shivam Agarwal, Arnav Wadhwa, Rajiv Shah

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 3552-3558. DOI: [10.24963/ijcai.2021/489](https://doi.org/10.24963/ijcai.2021/489)

## 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.