Attention ANR

Detect online disinformation and counter through arguments

Start date: January 2022 (42 months)

CALL: ANR21-CE23-0037

Summary of the project

The widespread availability of the internet and social media platforms has fundamentally changed the way people consume and share information. In 2016, two-thirds of American adults read news via online channels and the primary platform for online social interaction and transmission of information is now social medium, giving rise to a new challenge:

Online Disinformation which refers to the deliberate spread of false or misleading information online.

The primary objectives of this project are:

1. Better identify online disinformation by integrating argumentation in fake news identification

2. Instead of blocking, design (semi-)automated systems to generate fact-based counter-arguments to fight against disinformation

3. Develop intelligent dialogue systems to debate with users, helping them develop the critical thinking

Publications

Saeed, M., & Papotti, P. (2022, December). You are my type! type embeddings for pre-trained language models. In Findings of the Association for Computational Linguistics: EMNLP 2022. (pp. 4583-4598).

Wang, X., Cabrio, E., & Villata, S. (2023, June). Argument and Counter-Argument Generation: A Critical Survey. In International Conference on Applications of Natural Language to Information Systems (pp. 500-510). Cham: Springer Nature Switzerland.

Advani, R., Papotti, P., & Asudeh, A. (2023, August). Maximizing Neutrality in News Ordering. In KDD 2023, 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.

Villata, S. (2023, June). Artificial intelligence at the service of society to analyse human arguments. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 13, pp. 15458-15458).

Goffredo, P., Espinoza, M., Villata, S., & Cabrio, E. (2023, December). Argument-based detection and classification of fallacies in political debates. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 11101-11112). Association for Computational Linguistics.

Badaro, G., Saeed, M., & Papotti, P. (2023). Transformers for Tabular Data Representation: A survey of models and applications. In Transactions of the Association for Computational Linguistics, 11, 227-249.

Bussotti, J. F., Veltri, E., Santoro, D., & Papotti, P. (2023). Generation of training examples for tabular natural language inference. In Proceedings of the ACM on Management of Data, 1(4), 1-27.

Advani, R., Papotti, P., & Asudeh, A. (2023, August). Maximizing Neutrality in News Ordering. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 11-24).

Glavic, B., Mecca, G., Miller, R. J., Papotti, P., Santoro, D., & Veltri, E. (2024). Similarity Measures For Incomplete Database Instances. In Advances in Database Technology-EDBT (Vol. 27, pp. 461-473). OpenProceedings. org.