Research

How meaning, belief, and influence are encoded in language at scale.

Building the computational tools to detect distortion, model its spread, and audit the systems that amplify it.

Information Integrity & Misinformation at Scale

I model misinformation not as a monolith but as a set of community-specific rhetorical strategies that spread through algorithmic and social feedback loops. My current work combines self-exciting point processes (Hawkes models) for diffusion, causal audits of algorithmic amplification, and cross-genre/cross-platform retrieval to move from describing misinformation to quantifying how and where it gains traction. This line is directly relevant to trust-and-safety and platform-governance settings.

Projects:

The anatomy of belief-driven distortion [ supported by the Society of Family Planning ]
Pragmatic Language Understanding [ supported by the U.S. National Science Foundation and the AI Innovation Institute ]
Semantic Drift in Medical Information [ supported by the U.S. National Science Foundation ]
Propaganda, Fallacies, and Media Integrity [ supported by the AI Innovation Institute ]

Selected Publications:

A Longitudinal, Multinational, and Multilingual Corpus of News Coverage of the Russo-Ukrainian War. 2026.
Dikshya Mohanty, Taisiia Sabadyn, Jelwin Rodrigues, Chenlu Wang, Abhishek Kalugade, and Ritwik Banerjee
Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC)
doi : 10.63317/5ecxdux9s9ft
HDCR: Cross-lingual Medical Misinformation Detection through Contrastive Claim-Evidence Reasoning. 2025.
Chaoyuan Zuo and Ritwik Banerjee
International Conference on Bioinformatics and Biomedicine (BIBM)

doi: 10.1109/BIBM66473.2025.11356375

Seeing Should Probably not be Believing: The Role of Deceptive Support in COVID-19 Misinformation on Twitter. 2022.

Chaoyuan Zuo, Ritwik Banerjee, Fateme Hashemi Chaleshtori, Hossein Shirazi, and Indrakshi RayACM Journal of Data and Information Quality, Vol. 15, No. 1, Article 9 (Dec 2022)doi : 10.1145/3546914

Beyond belief: a cross-genre study on perception and validation of health information online. 2022.

Chaoyuan Zuo, Kritik Mathur, Dhruv Kela, Noushin Salek Faramarzi, and Ritwik BanerjeeInternational Journal of Data Science and Analytics, Vol. 13, No. 4 (Feb 2022)doi : 10.1007/s41060-022-00310-7

Querying Across Genres for Medical Claims in News. 2020.

Chaoyuan Zuo, Narayan Acharya, and Ritwik BanerjeeProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)doi : 10.18653/v1/2020.emnlp-main.139

Pragmatics and Computational Argumentation

Much online influence operates beyond literal meaning: through deflection, fallacy, framing, and stance. I build models for these pragmatic phenomena, drawing on argumentation theory (Toulmin, rhetorical structure theory) and pragmatic language inference to detect things like whataboutism and fallacious reasoning that are missed by purely semantic analysis.

Projects:

The anatomy of belief-driven distortion [ supported by the Society of Family Planning ]
Pragmatic Language Understanding [ supported by the U.S. National Science Foundation and the AI Innovation Institute ]
Propaganda, Fallacies, and Media Integrity [ supported by the AI Innovation Institute ]

Selected Publications:

Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse. 2024.

Khiem Phi, Noushin Salek Faramarzi, Chenlu Wang, and Ritwik BanerjeeFindings of the Association for Computational Linguistics ACLdoi : 10.18653/v1/2024.findings-acl.750

Claim Extraction and Dynamic Stance Detection in COVID-19 Tweets. 2023.

Noushin Salek Faramarzi, Fateme Hashemi Chaleshtori, Hossein Shirazi, Indrakshi Ray, and Ritwik BanerjeeWWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023doi : 10.1145/3543873.3587643

Privacy, Law, and Regulatory Compliance

I study how natural-language systems can reason about, and be held accountable to, privacy law and regulatory constraints — from auditing the fidelity of stated app permissions to investigating medical data against privacy statutes.

Projects:

A Framework for Investigating Live Medical Data against Privacy Laws [ supported by the U.S. National Science Foundation ]

Selected Publications:

Local Privacy Laws in a Globalized World. 2026.

Shantanu Sharma, Lorenzo De Carli, Ethan Myers, Ritwik Banerjee, and Indrakshi RayThe 16th ACM Conference on Data and Application Security and Privacy (CODASPY)[ to appear ]

Harnessing Language Models to Analyze Android App Permission Fidelity. 2025.

Yunik Tamrakar, Ritwik Banerjee, Ethan Myers, Lorenzo De Carli, and Indrakshi Ray22nd Annual International Conference on Privacy, Security, and Trust (PST)doi: 10.1109/PST65910.2025.11268849

AI for Biomedical and Clinical Knowledge

I apply the methods above to biomedical and clinical text: verifying health claims against the scientific literature, extracting clinical events, and supporting downstream prediction tasks.

Projects:

Computational Linguistics and AI for Patients (CLAP) [ supported by a SUNY Small Team Multidisciplinary Award and a SUNY Seed Grant. ]

Selected Publications:

Large-scale Biomedical Expert Finding for Health Claim Verification: A PubMed-based Retrieval Framework. 2025.
Chaoyuan Zuo, Chenlu Wang, and Ritwik Banerjee
International Conference on Bioinformatics and Biomedicine (BIBM)

doi: 10.1109/BIBM66473.2025.11356094

HDCR: Cross-lingual Medical Misinformation Detection through Contrastive Claim-Evidence Reasoning. 2025.
Chaoyuan Zuo and Ritwik Banerjee
International Conference on Bioinformatics and Biomedicine (BIBM)

doi: 10.1109/BIBM66473.2025.11356375

Natural language processing for kidney ultrasound analysis: correlating imaging reports with chronic kidney disease diagnosis. 2025.
Chenlu Wang, Ritwik Banerjee, Harry Kuperstein, Hamza Malick, Ruqiyya Bano, Robin L. Cunningham, Janos Hajagos and Farrukh M. Koraishy
Renal Failure, Vol. 47, No. 1, 2539938, Aug 2025
doi: 10.1080/0886022X.2025.2539938

Page updated

Google Sites

Report abuse