72.065-7 - Computational Methods for Qualitative Learning Sciences Research: Affording Materiality to Text-Based Data

• In Event: 72.065 - Roundtable Session 30

Session Type: Roundtable Session

Abstract

This session aims to demonstrate the practical and theoretical usefulness of computational natural language processing (NLP) methods for learning sciences researchers doing qualitative research with text or discourse data. We will do so by presenting 4 different studies, each deploying NLP methods in different domains and for different purposes. Across these differences, each study demonstrates the usefulness of computational methods for rigorously studying complex social or cognitive processes involved in learning. We will argue that these methods change the nature of the data with which we typically work, thus broadening our modes of interacting with and interpreting text-based data.

Sub Unit

• SIG-Learning Sciences

Chair

• Bruce Sherin, Northwestern University

Papers

• Using Text Analysis and Clustering to Reveal Processes of Change in Engineering Knowledge and Innovation - Taylor Martin, O'Reilly Media; Philip Janisiewicz, The University of Texas - Austin

• Discovering How Language Patterns Evolve in Online Discourse - Matthew W. Berland, University of Wisconsin - Madison; Benjamin Snyder, University of Wisconsin - Madison

• Interest Generators for Scientific Knowledge Building - Christina R. Krist, Northwestern University

• Mechanism-Focused Approaches to Studying Student Thinking About Social Policy - Arthur Hjorth, Northwestern University