Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Analysis of Collaborative Argumentation in Text-based Classroom Discussions

Lugini, Luca (2021) Analysis of Collaborative Argumentation in Text-based Classroom Discussions. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

Download (8MB) | Preview


Collaborative argumentation can be defined as the process of building evidence-based, reasoned knowledge through dialogue and it is the foundation for text-based, student-centered classroom discussions. Previous studies for analyzing classroom discussions, however, have not focused on the actual content of student talk.
In this thesis, we develop a framework for analyzing student talk in multi-party, text-based classroom discussions to understand how students interact and collaboratively build arguments. The proposed framework will simultaneously consider multiple features, namely argumentation, specificity and collaboration.
We additionally propose computational models to investigate three aspects: 1) automatically predicting specificity; 2) automatically predicting argument components, and investigating the importance of speaker-dependent context; 3) using multi-task learning to jointly predict all aspects of student talk and improve reliability.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Lugini, Lucaluca.lugini@gmail.comlul320000-0002-0411-043X
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairLitman, Dianedlitman@pitt.edudlitman
Committee MemberKovashka,
Committee MemberWalker, Erinewalker@pitt.eduewalker
Committee MemberAshley, Kevinashley@pitt.eduashley
Date: 7 June 2021
Date Type: Publication
Defense Date: 16 July 2020
Approval Date: 7 June 2021
Submission Date: 11 May 2021
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 166
Institution: University of Pittsburgh
Schools and Programs: School of Computing and Information > Computer Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Natural Language Processing, Argument Mining, Collaborative Argumentation, Specificity
Date Deposited: 07 Jun 2021 20:49
Last Modified: 07 Jun 2021 20:49


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item