Seminar: "NLP and CSS: Lessons from One for the Other"
Abstract
CSS as a field is of growing field with increasing importance. LLMs are powerful tools that can help conduct such analysis at scale but come with several caveats and biases of their own. In this talk, I will share some examples of past and ongoing work on using LLMs as a tool for analysis of societal phenomena and as tools for analysis of models themselves. I will share some lessons learnt on the way when using LLMs for subjective tasks and on ensuring a robust methodology.
Invited Speaker: Arnav Arora (University of Copenhagen)
Bio: Arnav Arora is a PhD Student studying Natural Language Processing (NLP) at the University of Copenhagen. His primary research interests lie at the intersection of NLP and Computational Social Science, focusing on online harms such as misinformation and hate speech in low resource scenarios. Through his work, he aims to contribute to the development of equitable technology. Prior to this, he spent some time in industry as a Research Engineer at Checkstep, a content moderation company.
