Research
My current research interests are broadly within Computational Social Science, and span several topics including pluralistic alignment, scalable oversight and algorithms with pro-social objectives.
Much of my past research deals with strategic information operations and political influencing in the Global South. This includes studies on rumours, conspiracies and other forms of online influencing, primarily on X (formerly, Twitter).
"The work is mysterious and important." — Mark S, Lumon Industries
Ongoing Work
-
Scaling up crowd-sourced fact-checking (Community Notes) using LLMs: As an extension of the Supernotes paper, I am building a writing assistant that helps Community Note writers write better notes by giving them real-time feedback on the predicted performance of a note. Along with other collaborators, I am also testing out different ways to use LLMs to support note raters on social media discern fact-checking note quality more efficiently and accurately.
-
Algorithmic re-ranking of social media feeds: In 2024, we were one of the three winning interventions in the Prosocial Ranking Challenge, hosted by CHAI, Berkeley – and our proposed feed re-ranking algorithm was used an one of 5 experimental arms in a four-month long field study across several social media platforms. Currently, we are working on analysing the experimental data, as well as the observational data collected as a part of the experiment to better understand (a) the impact of feed re-ranking algorithms on people and (b) the overall information/engagement environment across these social media platforms during the time of the experiment.
Published Work
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking
The ACM Web Conference. 2025
On the Influence and Political Leaning of Overlap between Propaganda Communities
ACM Journal on Computing and Sustainable Societies (JCSS). 2024
Networks and Influencers in Online Propaganda Events: A Comparative Study of Three Cases in India
Proceedings of the 27th ACM Conference on Computer-Supported Cooperative Work and Social Computing. 2024
FeedSpan: A bridging-based prosocial feed reranking algorithm
The Prosocial Ranking Challenge. 2024
DISMISS: Database of Indian Social Media Influencers on Twitter
Proceedings of the 16th International AAAI Conference on Web and Social Media (ICWSM). 2022
Closed Ranks: The Discursive Value of Military Support for Indian Politicians
Proceedings of the 12th International Conference on Information & Communication Technologies and Development (ICTD). 2022
Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking
The ACM Web Conference. 2025
On the Influence and Political Leaning of Overlap between Propaganda Communities
ACM Journal on Computing and Sustainable Societies (JCSS). 2024
Networks and Influencers in Online Propaganda Events: A Comparative Study of Three Cases in India
Proceedings of the 27th ACM Conference on Computer-Supported Cooperative Work and Social Computing. 2024
Enhancing Crowd-Sourced Fact-Checking Using LLM-Driven Consensus
The 10th International Conference on Computational Social Science. 2024
FeedSpan: A bridging-based prosocial feed reranking algorithm
The Prosocial Ranking Challenge. 2024
Sustaining Discourse in a Rumour Network on Twitter
The 9th International Conference on Computational Social Science. 2023
Social Media and Society in India
Proceedings of SMSI 2023, University of Michigan. 2023
DISMISS: Database of Indian Social Media Influencers on Twitter
Proceedings of the 16th International AAAI Conference on Web and Social Media (ICWSM). 2022
Closed Ranks: The Discursive Value of Military Support for Indian Politicians
Proceedings of the 12th International Conference on Information & Communication Technologies and Development (ICTD). 2022
Poster: Experiences of Journalists on Twitter in India
ACM SIGCHI Symposum for HCI and Friends. 2022
Media Coverage
Exploring the Intersection between Computer Science and Social Development
Ashoka University. 2023
Coordinated campaign? India #1 source for pro-Russia tweets amid Ukraine war, says Ashoka study
The Print. 2022
Who are BJP's favourite journalists? What about Congress and AAP? A Michigan study reveals
Newslaundry. 2022