I wonder how Natural Language Processing methods compare to traditional text analysis in social science research

Speaker(s):

Shunqi Zhang, University of Southampton

Abstract:

This lightning talk explores the strengths and limitations of Natural Language Processing (NLP) in social science research, drawn from our projects in education. We will begin with an introduction to NLP and key methods, followed by examples of how these techniques can complement traditional analytical approaches:

• Analysing public perceptions of mathematics through topic modelling and sentiment analysis of social media discussions.
• Applying NLP to interview data from existing projects to compare insights with those obtained through conventional qualitative analysis.

Our goal is to demystify NLP tools, highlight their potential applications, and critically examine their challenges.