Quantify the Political Bias in News Edits: Experiments with Few-Shot Learners (Student Abstract)

Preetika Verma, Hansin Ahuja, Kokil Jaidka

AAAI 2023 pp. 16354-16355

doi:10.1609/AAAI.V37I13.27037 /aaai/2023/verma2023aaai-quantify/

Abstract

The rapid growth of information and communication technologies in recent years, and the different forms of digital connectivity, have profoundly affected how news is generated and consumed. Digital traces and computational methods offer new opportunities to model and track the provenance of news. This project is the first study to characterize and predict how prominent news outlets make edits to news frames and their implications for geopolitical relationships and attitudes. We evaluate the feasibility of training few-shot learners on the editing patterns of articles discussing different countries, for understanding their wider implications in preserving or damaging geopolitical relationships.

PDF AAAI Semantic Scholar

Cite

Text

Verma et al. "Quantify the Political Bias in News Edits: Experiments with Few-Shot Learners (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27037

Markdown

[Verma et al. "Quantify the Political Bias in News Edits: Experiments with Few-Shot Learners (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/verma2023aaai-quantify/) doi:10.1609/AAAI.V37I13.27037

BibTeX

@inproceedings{verma2023aaai-quantify,
  title     = {{Quantify the Political Bias in News Edits: Experiments with Few-Shot Learners (Student Abstract)}},
  author    = {Verma, Preetika and Ahuja, Hansin and Jaidka, Kokil},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16354-16355},
  doi       = {10.1609/AAAI.V37I13.27037},
  url       = {https://mlanthology.org/aaai/2023/verma2023aaai-quantify/}
}