Research Team
Principle Investigators
Jihie Kim, Principle
Erin Shaw, Co-PI
Carole Beal, Co-PI (moved)

Ph.D. Candidate Researchers
Sujith Ravi (past)
Erin Tavano (past)

Grad Student Programmers
Jeon-Hyung Kang
Srujankumar Vegesna
Taehwan Kim (past)
Suradej Integorn (past)
Pachara Supanakoon (past)
Aniwat Arromratana (past)
Sattawat Suppalertporn (past)
Pankaj Sarda (past)
P. Balasubramanian (past)
Roshan Herbert (past)

Directed Research Students
Rajiv Prithvi (past)
Siddarth Ranka (past)

Undergrad CompSci Interns
Meera Srinivasan (past)
Robert Ward (past)
Grace Chern (past)
Bernadette Aurelio (past)
David Lin (past)

Undergrad CogSci Interns
Saul Wyner (UCLA)
Nathan Pepper (UCLA, past)

Visiting Scholars
Jia Li (Shanghai Jiatong U., past)
Contact Information
For project information contact
jihie at isi dot edu or
shaw at isi dot edu.
Interested students: We require excellent grades and/or a rec- ommendation from your TA or Instructor in a related course. We are always looking for students with excellent skills in natural language processing and machine learning. For programming positions, PHP and SQL skills are desired.

Pedagogical Discourse is a new study (8/2006) aimed at scaffolding and assessing student interactions within online discussion boards. Using analyses of the discourse, course ontologies and student profiles, we will scaffold learning opportunities by connecting students to each other and to related course material and discussions. We will work with undergraduate computer science students. Participating institutions include USC, UC Irvine and Tulane University.

Discussion board screenshot

The project is funded by a National Science Foundation CCLI-Phase 2 (Expansion) grant [Award #0618859].

Motivation As web-enhanced and distance education approaches become increasingly integrated in engineering courses, discussion boards offer a promising avenue for supporting collaborative interaction and reflective problem solving. However, existing systems for on-line discussion are often not fully effective in promoting learning in undergraduate courses, and pedagogical interventions can be necessary to keep collaborative discussions focused and productive.

Goal The goal of the project is to design, deploy and evaluate software tools that automatically structure and scaffold student interactions within on-line discussion boards. Our tools will analyze graduate student contributions to past discussion topics and recommend the contributions that are useful, relevant or of interest to undergraduates who are contributing to a current discussion topic. The system will provide guidance using tutorial scaffolding strategies such as generating questions and comments, inviting participation and clarification, and referring students to past discussions of a related topic. Student profiles will be used to encourage individual students to contribute to particular topics. Evaluation studies conducted at three institutions will focus on the effects of different versions of discussion board on student performance, interest in engineering topics and retention rates.


J. Kim & E. Shaw, Pedagogical Discourse: Connecting students to past discussions and peer mentors within an online discussion board. 21st Annual Conference on Innovative Applications of Artificial Intelligence, Pasadena (IAAI-09), 2009.

S. Wyner, E. Shaw, T. Kim, J. Li & J. Kim, Sentiment Analysis of a Student Q&A Board for Computer Science, Workshop on Computational Models for Natural Argument (CMNA), Joint Int'l Conference on Artificial Intelligence (IJCAI), 2009.

J. Kim, T. Kim & J. Lee, Identifying unresolved issues in online students discussions: A multi-phase dialogue classification approach, Proc. of the AI in Education Conference, 2009.

E. Shaw, J. Kim & P. Supanakoon, MentorMatch: Using student mentors to scaffold participation and learning within an online discussion board, Proc. of the AI in Education Conference, 2009.

J. Kim, E. Shaw, S. Ravi, E. Tavano, A. Arromratana & P. Sarda, Scaffolding of On-line Discussions with Past Discussions: An Analysis and Pilot Study of PedaBot, Proc. of 9th International Conference on Intelligent Tutoring Systems (ITS'08).

J. Kim, E. Shaw, E. Tavano, A. Arromratana, P. Sarda & C. Beal, Towards Automatic Scaffolding of On-line Discussions in Engineering Courses, Annual Meeting of the American Educational Research Association (AERA 2008).

S. Ravi & J. Kim, Profiling Student Interactions in Threaded Discussions with Speech Act Classifiers, Proc. of the AI in Education Conference, 2007.

J. Kim, E. Shaw, G. Chern & R. Herbert, Novel tools for assessing student discussions: Modeling threads and participant roles using speech act and course topic analysis, Proc. of the AI in Education Conference, 2007.

J. Kim, G. Chern, E. Shaw & D. Feng, An Intelligent Discussion-Bot for Guiding Student Interactions in Threaded Discussions , Proc. of the AAAI 2007 Spring Symposium on Interaction Challenges for Intelligent Assistants, 2007.

J. Kim, G. Chern & E. Shaw, Towards automatic assessment of on-line discussions: Analyzing student "speech acts" , American Educational Research Association (AERA 2007).

D. Feng, J. Kim, E. Shaw & E. Hovy, Towards Modeling Threaded Discussions through Ontology-based Analysis, In Proc. of National Conference on Artificial Intelligence (AAAI-2006).

D. Feng, E. Shaw, J. Kim & E. Hovy, Learning to Detect Conversation Focus of Threaded Discussions, In Proc. of the Joint Human Language Tech. Conf./Annual Meeting of the North Amer. Chap. of the Assoc. for Computational Linguistics (HLT-NAACL 2006) .

D. Feng, E. Shaw, J. Kim & E. Hovy, An Intelligent Discussion-Bot for Answering Student Queries in Threaded Discussions, Proc. of the Int'l Conf. on Intelligent User Interfaces (IUI-2006), 2006.

J. Kim, G. Chern, D. Feng, E. Shaw & Eduard Hovy, Mining and Assessing Discussions on the Web through Speech Act Analysis, Proc. of the ISWC'06 Workshop on Web Content Mining with Human Language Technologies, 2006.

J. Kim, E. Shaw, D. Feng, C. Beal & E. Hovy, Modeling and Assessing Student Activities in On-Line Discussions, Proc. of the AAAI Workshop on Educational Data Mining, 2006.

J. Kim & C. Beal, Turning quantity into quality: Supporting automatic assessment of on-line discussion contributions, American Educational Research Association (AERA 2006), 2006.

E. Shaw, Assessing and Scaffolding Threaded Discussions, Proc. of the AI in Ed Conf, 2005.