DiscussionTracker
A tool that helps teachers understand classroom discussions

The goal of this project is to develop an innovative technology called Discussion Tracker, a computer-based system for high school English teachers that uses recent advances in human language technologies (HLT) to provide teachers with automatically generated data and instructional guidance on the quality of students' collaborative argumentation in their classrooms. Discussion Tracker will provide teachers with visual representations of the significant features of their students' collaborative talk and tools for instructional reflection and future planning. The project will improve the teaching and learning of collaborative argumentation in high schools so that students will be prepared for collaborative problem-solving in future educational, workplace, and civic settings. This project leverages recent advances in human language technologies (HLT), data visualization/ analytics, and teacher learning to advance technology that provides automated feedback on classroom talk with the goal of improving teaching effectiveness and student achievement. It develops novel HLT methods for detecting three significant features of students' collaborative talk: argument moves (claim, evidence, explanation), specificity, and collaboration (e.g., building on, probing or challenging others' ideas).

The DiscussionTracker Team: Professors

Amanda Godley

Professor, School of Education, University of Pittsburgh

Home page

Diane Litman

Professor, Computer Science Department, Senior Scientist, Learning Research and Development Center Director, Intelligent Systems Program, University of Pittsburgh

Home page

Students

Tianzhi Zhang

Graduate Student, School of Education, University of Pittsburgh

Home page

Ashley Feiler

Undergraduate, English and Writing Majors, University of Pittsburgh

Alumni

Luca Lugini

Ph.D, Computer Science Deparment, University of Pittsburgh

Chris Olshefski

Ph.D, School of Education, University of Pittsburgh

Ravneet Singh

Graduate Student, Computer Science Department, University of Pittsburgh

Keshika Gopinathan

Undergraduate, Microbiology Major, University of Pittsburgh

Lindsey Rojtas

Undergraduate, Computer Science Deparment, University of Pittsburgh

Ilana Udler

Undergraduate, Computer Science Deparment, University of Pittsburgh

Calvin Yu

Undergraduate, Computer Science Deparment, University of Pittsburgh

Bowen Zheng

Undergraduate, Health Informatics Major, University of Pittsburgh

Maria Scanga

Undergraduate, Health Informatics Major, University of Pittsburgh

Publications

Conferences

  1. Zhang, T., Godley, A.J., Litman, D. & Singh, R. (2023). Using an Innovative Computer-Based System for Fostering High School English Teachers’ Learning about Collaborative Argumentation. Paper presented at the American Educational Research Association Annual Meeting. Chicago, IL.
  2. Godley, A. J., Olshefski, C. A., Litman, D. & Lugini, L. (2021) Development of an Automated Tool to Track Secondary English Students' Collaborative Argumentation European Conference for Research on Learning and Instruction (EARLI 2021). Online.
  3. Luca Lugini and Diane Litman, Contextual Argument Component Classification for Class Discussions, Proceedings of the 28th International Conference on Computational Linguistics (COLING), Online, December 2020
  4. Luca Lugini, Christopher Olshefski, Ravneet Singh, Diane Litman and Amanda Godley, Discussion Tracker: Supporting Teacher Learning about Students' Collaborative Argumentation in High School Classrooms, Proceedings of the 28th International Conference on Computational Linguistics (COLING), Online, December. (System Demonstration) 2020
  5. Godley, A. J., Olshefski, C. A., Litman, D. & Lugini, L. (2020, Apr 17 - 21) Toward a Computational Analysis of Students' Collaborative Argumentation in English Language Arts Classrooms [Symposium]. AERA Annual Meeting San Francisco, CA (Conference Canceled)
  6. Christopher Olshefski, Luca Lugini, Ravneet Singh, Diane Litman, Amanda Godley, The Discussion Tracker Corpus of Collaborative Argumentation, Proceedings of the 12th International Conference on Language Resources and Evaluation, Marseille, France, May 2020.
  7. Godley, A.J., Olshefski, C., Lugini, L. & Litman, D., Toward a Computational Analysis of Students’ Collaborative Argumentation in English Language Arts Classrooms. Paper to be presented at the 2020 Annual Meeting of the American Educational Research Association, San Francisco, CA, April 2020.
  8. Godley, A. J. & Olshefski, C., Promises and Limitations of Applying NLP to Classroom Discourse Analysis. Paper presented at the 2019 Annual Meeting of the American Educational Research Association, Toronto, Ontario, April 2019.
  9. Luca Lugini and Diane Litman, Argument Component Classification for Classroom Discussions, Proceedings of the 5th Workshop on Argument Mining, pp. 57-67, Brussels, Belgium, November 2018.
  10. Luca Lugini, Diane Litman, Amanda Godley, and Christopher Olshefski, Annotating Student Talk in Text-based Classroom Discussions, Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 110-116, New Orleans, LA, June 2018.
  11. Luca Lugini and Diane Litman, Predicting Specificity in Classroom Discussion, Proceedings of the Twelfth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 52-61, Copenhagen, Denmark, September 2017.
  12. Godley, A. J. & Olshefski, C., Leveraging NLP to Assess and Improve Text-Based Discussions in English Language Arts. Paper presented at the Connecting Language, Interaction and Education in Digital Environments Conference, State College, PA, September 2017.
  13. Olshefski, C. & Godley, A. J., The role of argument moves, specificity and evidence type in meaningful literary discussions across diverse secondary classrooms. Paper presented at the Literacy Research Association Annual Conference, Tampa, FL, November 2017.

Dissertations

  1. Luca Lugini, Analysis of Collaborative Argumentation in Text-Based Classroom Discussions, Ph.D dissertation, Department of Computer Science, University of Pittsburgh, Pittsburgh, 2020

Corpus

Made available under the terms of GNU General Public License. The corpus is distributed without any warranty.

To access the DiscussionTracker corpus, please fill out the following form. We respect your privacy and will only use your information for the purpose assessing interest in the resource.

Code

The source code for experiments detailed in [3] is available at the following at the following links: The source code for the web version of the Web App detailed in [2] is available here

Acknowledgments

This work was supported by the National Science Foundation (EAGER 1842334 and 1917673) and by the University of Pittsburgh Learning Research & Development Center.

Discussion Tracker Web App

Discussion Tracker Web App Demo

To access the Discussion Tracker Web App Demo head over to the App at discussiontracker.lrdc.pitt.edu.

The username to log in to the system is `T2D_Demo` and the password is `secretPassword`. Once logged in you will be taken to the overview page of the demo transcript and you will be able to interact with the interface as a teacher.

Contact

For questions regarding to the corpus, please send an email to discussiontracker19@gmail.com