Date of Award

2019

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Dr. Jung Hee Kim

Abstract

This project measures different collaborative dialogue acts between students who are working together to solve problems in a computer programming class. In COMPS (Computer-Mediated Problem Solving) exercises students work together via online typed-chat. Transcripts of these conversations were annotated with four categories of collaborative utterance: sharing ideas, negotiating ideas, regulating problem-solving, and maintaining communication. The annotated transcripts were then applied to answer four different research questions. A) Among the several students in a conversation, there are measurable quantitative differences in dialogue behavior that correlate with the relative preparedness for solving the problem. The most prepared student not only talks more but uses a different mixture of dialogue acts than the least prepared student. B) Different Teaching Assistants have different ways of interacting with the student groups when they join the conversations. This TA’s behaviors are observable from dialogue act statistics, which ultimately correlate with a more didactic and a more Socratic style. C) The patterns of short two-turn sequences of dialogues are tabulated. The higher-probability two-turn conversational exchanges form the start of a probabilistic model of dialogue behavior. D) It proved possible to train machine classifiers to recognize the different dialogue acts, with only moderate accuracy. Using the previous turns of conversational text did little to improve accuracy. The COMPS software package was considerably enhanced during the course of this work in service of collecting more and better data. The enhanced software automatically administers 2 pre- and post-tests, aids in forming student groups that incorporate more and less prepared students, and organizes and links the data collected during a COMPS lab session. This research advances toward computer assessment of student collaboration skills and aids in the understanding of collaborative learning.

Download

Share

COinS