A Collaborative Dialogue Agent for

Peer Learning Interactions

About the project

People

Publications

Press Releases

Sponsors

About the project:

This project has three goals:
  1. elucidate our understanding of peer learning, by analyzing what constitutes effective knowledge sharing and effective explanations
  2. devise a computational model of peer learning interactions, and embody it by building an artificial peer dialogue agent
  3. contribute to Computer Science education by developing the peer dialogue agent in the domain of basic data structures and algorithms, and pushing students to develop abstract, generalizable knowledge about data structures and algorithms. 
The dialogue agent will provide a vehicle for studying different strategies to support and assess peer learning. The development of the dialogue agent will be informed by a detailed language analysis of peer interactions that the project will collect.  The dialogue agent will use natural language processing technology, but to avoid the possibly confounding effects of imperfect natural language understanding and generation, the experiments will include a human interpreter who will review and correct as necessary the system's interpretation of the student's inputs and the system's replies back to the student.

By first using the dialogue agent, KSC-PaL, (KSC stands for Knowledge Sharing and Construction) as a peer in computer science education, we hope to increase retention in undergraduate computer science programs, especially among female students.  Peer collaboration on programming tasks in classrooms and laboratory settings has been shown to benefit students of both genders.

This project is a collaboration between the University of Illinois at Chicago and the University of Pittsburgh.

Back to top


                                                                                    

Project People

University of Illinois at Chicago:

Lewis University:

University of Pittsburgh:

  • Pamela Jordan, Research Associate, PI
  • Sandra Katz, Research Associate, co-PI
  • Christine Wilson, Programmer
  • Brian (Moses) Hall, Programmer
DePaul University:
Back to top

Project Publications: 

  • Cynthia Howard, Barbara Di Eugenio, Pamela Jordan, and Sandra Katz. Using Initiative to Operationalize Knowledge Co-Construction During Collaborative Problem Solving. Cognitive Sciene. Accepted (2015).
  • Cynthia Howard, Pamela Jordan, Barbara Di Eugenio, and Sandra Katz. Shifting the Load: A Peer Dialogue Agent that Encourages Its Human Collaborator to Contribute More to Problem Solving. International Journal of Artificial Intelligence in Education, Special Issue on AI-supported Education in Computer Science. 2015.
  • Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan, and Sandra Katz. KSC-PaL: A Peer Learning Agent. The 10th International Conference, ITS 2010 . June 2010.
  • Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan, and Sandra Katz. KSC-PaL: A Peer Learning Agent. The 10th International Conference, ITS 2010 . June 2010.
  • Cynthia Kersey (Howard) (2009). Knowledge Co-construction and Initiative in Peer Learning Interactions. PhD dissertation. University of Illinois at Chicago, Department of Computer Science.
  • Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan, and Sandra Katz. Knowledge Co-construction and Initiative in Peer Learning Interactions . AIED 2009, The 14th International Conference on Artificial Intelligence in Education. Brighton, UK. July 2009.
  • Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan, and Sandra Katz. KSC-PaL: A Peer Learning Agent that Encourages Students to take the Initiative . NAACL-HLT 2009 Workshops,  The 4th Workshop on Innovative Use of NLP for Building Educational Applications. Boulder, Co. June 2009.
  • Modeling Knowledge Co-Construction for Peer Learning Interactions (2008) by Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan, and Sandra Katz.  ITS 2008, The 9th International Conference on Intelligent Tutoring Systems, Student Research Workshop. Montreal, Canada.
  • Impact of Initiative on Collaborative Problem Solving (2008) by Cynthia Kersey (Howard). ACL 2008, The 46th Annual Meeting of the Association for Computational Linguistics, Student Research Workshop. Columbus, OH.
  • Topic Initiative in a Simulated Peer Dialogue Agent. (2007) by Pamela W. Jordan.  In the Proceedings of AIED 2007, pp. 581-583.
  • Collaboration in Peer Learning Dialogues. (2007) by Cynthia Kersey (Howard), Barbara Di Eugenio, Pamela Jordan and Sandra Katz.  Presented at DECALOG - The 2007 Workshop on the Semantics and Pragmatics of Dialogue.

Project Related Publications:

  • Minimal Feedback During Tutorial Dialogue (2008). by P. Jordan and D. Litman (2008).  The Intelligent Tutoring Systems 9th International Conference, ITS 2008, pp. 671-673.
  • Reinforcement Learning-based Feature Selection For Developing Pedagogically Effective Tutorial Dialogue Tactics (2008). by M. Chi, P. Jordan, K. VanLehn, and M. Hall. EDM'08 1st International Conference on Educational Data Mining. Pages 258-265.  (best poster award).
  • Learning Linked Lists: Experiments with the iList System (2008). by D. Fossati, B. DiEugenio, C. Brown and S. Ohlsson.  ITS 2008, the 9th International Conference on Intelligent Tutoring Systems, vol. LNCS 50 p. 80.
  • Simple but effective feedback generation to tutor abstract problem solving (2008) by X. Lu, B. DiEugenio, S. Ohlsson and D. Fossati.  INLG 2008, 5th International Natural Language Generation Conference.
  • Beyond the code-and-count analysis of tutoring dialogues (2007). by S. Ohlsson, B. DiEugenio, B. Chow, D. Fossati, X. Lu and T.C. Kershaw.  The 13th International Conference on AI in Education.
  • Expert vs. Non-expert Tutoring: Dialogue Moves, Interaction Patterns and Multi-Utterance Turns (2007). by X. Lu, B. DiEugenio, T.C. Kershaw, S. Ohlsson and A. Corrigan-Halpern.  CICLing-2007, the Eight International Conference on Intelligent Text processing and Computational Linguistics.
  • Learning Tutorial Rules uisng Classification Based on Associations (2007). by X. Lu, B. DiEugenio and S. Ohlsson.  The 13th International Conference on AI in Education.
  • When are Tutorial Dialogues More Effective than Reading? (2007). by K. VanLehn, A. Graesser, G.T. Jackson, P. Jordan, A. Olney and C. Rose.  Cognitive Science, vol. 31.
  • Tools for Authoring a Dialogue Agent that Participates in Learning Studies (2007). by P. Jordan, B. Hall, M. Ringenberg, Y. Cui and C. Rose.  The 13th International Conference on AI in Education.
  • Developing pedagogically effective tutorial dialogue tactics: Experiments and a testbed.  (2007) by VanLehn, Kurt, Pamela Jordan, Diane Litman.  In proceedings of SLaTE Workshop on Speech and Language Technology in Education ISCA Tutorial and Research Workshop.
  • Rapidly Developing Dialogue Systems that Support Learning Studies. by Pamela W. Jordan, Michael Ringenberg and Brian Hall.  In the Proceedings of ITS06 Workshop on Teaching with Robots, Agents, and NLP, 2006.
  • The Agreement Process: An Empirical Investigation of Human-human Computer-mediated Collaborative Dialogues. by Barbara Di Eugenio, Pamela W. Jordan, Richmond H. Thomason and Johanna D. Moore. International Journal of Human-Computer Studies, vol 53, no 6, pgs 1017-1076, December 2000.
  • An Empirical Investigation of Proposals in Collaborative Dialogues by Barbara Di Eugenio, Pamela W. Jordan, Johanna D. Moore and Richmond H. Thomason. Project Note. In the Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98). Montréal, Canada, pp 325-329, 1998.
  • Control and Initiative in Collaborative Problem Solving Dialogues. by Pamela W. Jordan and Barbara Di Eugenio. In the Proceedings of the AAAI Spring Symposium on Computational Models for Mixed Initiative, Stanford, CA, March, 1997.

Back to top

Press Releases:

Back to top

Sponsors:

  • The National Science Foundation through award number 0536959 (Pitt) and 0536968 (UIC)
Back to top