- Browse/Search the Program
Search
Browse By Day
Browse By Time
Browse By Person
Browse By Mini-Conference
Browse By Division
Browse By Session or Event Type
Browse Sessions by Fields of Interest
Browse Papers by Fields of Interest
- Information Menu
Search Tips
Conference
Location
About APSA
- Navigation and Settings Menu
Personal Schedule
Change Preferences / Time Zone
Sign In
- Social Media Menu
Twitter
Facebook
Advances in Text-as-Data Models
Thu, September 5, 10:00 to 11:30am, Pennsylvania Convention Center (PCC), 112ASession Submission Type: Created Panel
Session Description
This panel presents cutting-edge computational techniques reshaping text analysis in the social sciences, emphasizing advancements in digitizing historical documents, improving topic modeling accuracy, and refining keyword extraction. The papers highlight novel approaches to addressing challenges in topic interpretability, the extraction of relevant keywords with minimal user input, the digitalization of existing documents, and the application of large language models (LLMs) for analyzing political discourse.
Sub Unit
Individual Presentations
1,000 Speeches vs. GPT-4: Analyzing Position Shifting in the European Parliament - Tobias Hofmann, Free University of Berlin; Jim Wagner, Free University of Berlin
Extracting Keywords from Unlabeled Corpora Using Word Embeddings - Patrick Chester, University of California, San Diego
Interpretable LDA Topic Models with Near-Optimal Posterior Probability - Adam Breuer, Dartmouth
The Power of Transfer Learning: Using New LLMs for Large, Multilingual Datasets - Will Horne, Clemson University; Gregory Love, University of Mississippi; Ryan Carlin, Georgia State University
Validating Automatic Text Digitization - Blake Miller, London School of Economics and Political Science; Michael Thompson-Brusstar, University of California, San Diego