Conflict, bias, and sentiment in social media
This project develops methods for modeling, detecting and measuring civil conflict as reflected in social media, as well as the associated informational biases in the news media. The goal is to combine different measures of verbal and non-verbal user behavior and the associated network-scale effects in order to track conflict development over time.
We view the problems of conflict and bias detection as inherently intertwined, since conflicts often lead to biased interpretations on both sides. The goal is to evaluate the hypothesis that identifying user communities divided with respect to a set of polarizing issues will allow us to characterize relevant information sources in terms of ideological biases propagated by the opposing sides.
References
-
A. Rumshisky, M. Gronas, P. Potash, M. Dubov, A. Romanov, S. Kulshreshtha, A. Gribov. Combining Network and Language Indicators for Tracking Conflict Intensity. Proceedings of SocInfo 2017. Oxford, United Kingdom.
- P. Potash, A. Rumshisky. Towards Debate Automation: a Recurrent Model for Predicting Debate Winners Proceedings of EMNLP 2017. Denmark, Copenhagen.
- P. Potash, A. Romanov, A. Rumshisky, M. Gronas. Tracking Bias in News Sources Using Social Media: the Russia-Ukraine Maidan Crisis of 2013–2014. EMNLP 2017 Workshop "NLP Meets Journalism". Denmark, Copenhagen.
- P. Potash, A. Romanov,
A. Rumshisky. Here's
My Point: Joint Pointer Architecture for Argument Mining Proceedings of EMNLP 2017.
Denmark, Copenhagen.
- P. Potash, R. Bhattacharya,
A. Rumshisky. Length,
Interchangeability, and External Knowledge: Observations from Predicting Argument
Convincingness Proceedings of IJCNLP 2017. Taipei, Taiwan.
- A. Rogers, A. Romanov, A. Rumshisky, S. Volkova, M. Gronas, A. Gribov. RuSentiment: An Enriched Sentiment Analysis Dataset for Social Media in Russian. Proceedings of COLING 2018. Santa Fe, New Mexico. [bibtex] [project page] [data]