I’m an Assistant Professor in the Quantitative Theory and Methods department of Emory University. My research is in the area of natural language processing and cultural analytics to answer questions in social sciences and humanities. This work often involves the use of methods in machine learning, text analysis, and network science.
Before Emory, I received my PhD in the School of Interactive Computing at Georgia Institute of Technology, where I was advised by Jacob Eisenstein. My PhD thesis was on using computational methods to model and quantify network influence in the process of language change. I was also a postdoctoral scholar in the School of Information at the University of California, Berkeley, advised by David Bamman. During my postdoc, I worked on building natural language processing methods for literature.
Aug 2023 | I joined the Quantitative Theory and Methods department at Emory University as Assistant Professor |
May 2023 | Our paper, Grounding Characters and Places in Narrative Texts is accepted to ACL 2023. Joint work with Amanpreet Sihra, Elizabeth F. Evans, Matthew Wilkens, and David Bamman. |
Apr 2023 | New preprint Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4 of our work on the limitations of GPT-4. Joint work with Kent Chang, Mackenzie Cramer, and David Bamman. |
Oct 2022 | Our paper, Predicting Long-Term Citations using Short-Term Linguistic Influence is accepted to Findings@EMNLP 2022. Joint work with David Bamman and Jacob Eisenstein. |
Sandeep Soni, Amanpreet Sihra, Elizabeth F. Evans, Matthew Wilkens, and David Bamman (2023), Grounding Characters and Places in Narrative Texts, Association of Computational Linguistics, PDF
Sandeep Soni, David Bamman, and Jacob Eisenstein (2022), Predicting Long-Term Citations from Short-Term Linguistic Influence, Findings of EMNLP, Preprint
Sandeep Soni, Lauren Klein, and Jacob Eisenstein (2021), Abolitionist Networks: Modeling Language Change in Nineteenth-Century Activist Newspapers, Journal of Cultural Analytics Link
Sandeep Soni, Kristina Lerman, and Jacob Eisenstein (2020), Follow the Leader: Documents on the Leading Edge of Semantic Change Get More Citations, Journal of the Association for Information Science and Technology, PDF
Rahul Goel, Sandeep Soni, Naman Goyal, John Paparizzos, Hanna Wallach, Fernando Diaz, and Jacob Eisenstein (2016), The Social Dynamics of Language Change in Online Networks, Social Informatics, PDF