University of North Carolina at Chapel Hill
School of Information and Library Science
INLS 310
Human Computer Information Retrieval Seminar
Spring 2006
Syllabus
Time and Place Instructor: Gary Marchionini
6:00-8:30 Mondays Email: march@ils.unc.edu www.ils.unc.edu/~march
Room 214 Manning Hall Office 203 Manning Hall
Phone (919) 966-3611
Classical information retrieval had yielded novel techniques for applying computers to retrieval problems, including WWW search engines. The classical model of retrieval is one of matching queries to documents and ranking these matches. In the case of Web IR, the matching has become more dependent on anchor text in webpages and the evaluation less practical for recall and precision measures. It is apparent, however, that a new model of retrieval is needed as people access large-scale digital libraries of multimedia content and vast collections of unstructured data in the WWW. What is needed are ways to bring human intelligence and attention more actively into the search process. To this end, researchers are beginning to combine the lessons from designing highly interactive user interfaces with the lessons from human information behavior to create new kinds of search systems that depend on continuous human control of the search process. I call this hybrid approach to the challenges of information seeking, human computer interaction (HCIR). HCIR aims to empower people to explore large-scale information bases but demands that people also take responsibility for this control by expending cognitive and physical energy. This seminar will consider the underlying theoretical model for HCIR, some early designs that aim to support such interactions, and alternative evaluation paradigms. Students will read papers and lead discussions based on those papers, and work on a group project to design and pilot test a user study for an HCIR system.
.
No textbook is required. Required readings/viewings are online.
Term Project: class defined design and implementation or formal usability study (70%)
Readings/viewings and Class Participation (30%)
The UNC Honor Code prohibits giving or receiving unauthorized aid in the completion of assignments. Students are strongly encouraged to cooperate and assist one another and share insights and respective expertise in this course. I expect that you will acknowledge the support you receive from your colleagues (this may be done in acknowledgements at the end of assignments or projects). It is crucial, however, that in every case where you use the actual written words of others, that these be properly quoted and cited. When you build arguments upon the ideas of others, the originators of those ideas should also be cited. You should adopt a style guide (e.g., American Psychological Association, Council of Biology Editors, Modern Language Association, Chicago, Turabian, etc.) and use it for your written work. Any style guide is acceptable, as long as you use one and follow it consistently. As you use the SILS library and lab resources during the course of the semester, please remember that many of your fellow students also need to use the same material. Be considerate of others and follow the proper checkout procedures, return materials promptly, and share workstation time if necessary. Please also conserve resources by consciously managing your printing in the labs.
Tentative Schedule
Week 1 January 23. Introduction to the seminar and the SILS view of HCIR
What we will do:
Readings: Some assigned by instructor, suggest others for the group.
Collaborate on a term project (possible projects include)
a) Query expansion user study. A replication of White & Marchionini with google suggest as a fourth condition
b) BLS user study: baseline/RB/Endeca
c) Personal Health Record study
d) audio surrogate design/test for video retrieval
e) others
Assign: identify an interesting search system on WWW and be prepared to lead a tour in class, pointing out strengths and weaknesses (not google, yahoo, msn)
Read for next meeting
Saracevic, T. (1997). The stratified model of information retrieval interaction: Extension and applications. Proceedings of the American Society for Information Science, 34, 313-327. http://www.scils.rutgers.edu/~tefko/ProcASIS1997.doc
Optional
Belkin, N.J. (1996) Intelligent information retrieval: Whose intelligence? In: ISI '96: Proceedings of the Fifth International Symposium for Information Science. Konstanz: Universtaetsverlag Konstanz, 25-31. http://mariner.rutgers.edu/tipster3/iirs.html
Ingrewsen, P. Cognitive perspectives of information retrieval interaction: elements of a cognitive IR theory. In: Journal of Documentation, 52(1), 1996, pp. 3-50.
Marchionini, G. (1995) Information seeking in electronic environments. NY: Cambridge U Press. (Chapter 6 online)
Ellis, David. "Modeling the Information-Seeking Patterns of Academic Researchers: A Grounded Theory Approach." Library Quarterly 63, no. 4 (1993): 469-486.
Week 2 January 30 Interactive IR models
Discuss Saracevic
In class exploration and discussion of selected search systems (tours)
Read for next meeting
Choo, Chun Wei, Brian Detlor, Don Turnbull. 2000. Information Seeking on the Web. First Monday 5, no. 2, available online at http://firstmonday.org/issues/issue5_2/
White & Marchionini (SIGIR06 submission will be provided)
Optional
Koenemann, J. & Belkin, N. (1996). A case for interaction: a study of interactive information retrieval behavior and effectiveness, Proceedings of the SIGCHI conference on Human factors in computing systems: common ground, p.205-212, April 13-18, 1996
Taylor, R. (1968). Question-Negotiation and Information Seeking in Libraries, College and Research Libraries 29: 178-194.
Week 3 February 6. User Behavior: Needs, Tasks, Searches, Queries, Discrete acts
Discuss readings
Complete search system tours
Read for next meeting
Kelly, D. and Teevan, J. (2003). Implicit feedback for inferring user preference. SIGIR Forum, 37(2), 18-28.
Anick, P. (2003). Using terminological feedback for web search refinement: a log-based study. In Proceedings of the 26th Annual ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 88-95.
Optional
Allan, J. (1996). Incremental relevance feedback. In Proceedings of the 19th International Conference on Research and Development in Information Retrieval, pp. 298-306.
Harman, D. (1988). Towards interactive query expansion. In Proceedings of the 11th Annual ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 321-331.
Week 4 February 13 Feedback, Query Expansion, and Query Quality
Discuss readings and the RealTime QE user study
Use the google suggest extension
Read for next meeting
Marchionini Exploratory search (preprint)
Broder. A taxonomy of Web search. SIGIR Forum, 36(2), Fall 2002. URL http://sigir.org/forum/F2002/broder.pdf.
Tanin, E., Shneiderman, B., & Xie, H. (in press). Browsing Large Online Data Tables Using Generalized Query Previews. Information Systems. (pdf will be supplied)
Optional
Hendry, D. & Harper, D. (1997). An information information-seeking environment. JASIST
Pirolli, P. and Card, S. K. (1999). Information Foraging. Psychological Review 106(4): 643-675. http://www2.parc.com/istl/groups/uir/pubs/items/UIR-1999-05-Pirolli-Report-InfoForaging.pdf
Week 5. February 20. Tasks and Interfaces
Discuss readings
Each participant presents an example (online) of an interesting UI for retrieval
Read for next meeting
Azari, D., Horvitz, E., Dumais, S., & Brill,E. (2004). Actions, answers, and uncertainty: a decision-makingperspective on Web-based question answering. IP&M 40(5), 849-868.
W. R. Hersh, M. K. Crabtree, D. H. Hickam, L. Sacherek, C. P. Friedman, P. Tidmarsh, C. Moesback, and D. Kraemer. Factors associated with success for searching MEDLINE and applying evidence to answer clinical questions. J. of the American Medical Informatics Association, 9(3):283–293,
May/June 2002. URL http://medir.ohsu.edu/~hersh/jamia-02-irfactors.pdf.
Optional
Lin, J., Quan, D., Sinha, V., Bakshi, K., Huynh, D., Katz, B., & Krager, D. R. (2003). What makes a good answer? The role of context in question answering systems. Proceedings of INTERACT.
Week 6 February 27. Assessing Searcher Behavior
Discuss evaluation studies
How can browsing be evaluated?
Read for next meeting
S. Brin and L. Page. The anatomy of a large-scale hypertextual web search engine. In P. Thistlewaite and H. Ashman, editors, Proc. 7th World Wide Web Conf. (WWW7), pages 107–117, Brisbane, Australia, April 1998. URL http://decweb.ethz.ch/WWW7/1921/com1921.htm.
Week 7 March 6. Sources of Evidence for Retrieval
Authors, publishers, readers, searchers, and systems: Toward a theory of relationships
Read for next meeting
Hawking, D. & Zobel, J. (2005). JASIST preprint
Marchionini et al. BLS final report
Optional
Bulterman, D. 2004. Is it time for a moratorium on metadata? IEEE Multimedia, Oct-Dec, 2004. 10-17
Week 8 March 13 (Spring Break)
Week 9 March 20. Metadata
Classical metadata
Folksonomies and tagging
Text mining
Read for next meeting
Yee, K-P., Swearingen, K., Li, K., and Hearst, M., Faceted Metadata for Image Search and Browsing, in CHI 2003. http://bailando.sims.berkeley.edu/papers/flamenco-chi03.pdf
Yang, M., Wildemuth, B. M., Marchionini, G., Wilkens, T., Geisler, G., Hughes, A., Gruss, R., and Webster, C. (2003). “Measuring User Performance During Interactions with Digital Video Collections.” Proceedings of the 66th Annual Meeting of the American Society for Information Science and Technology (ASIST 2003), pp. 3-11.
Optional
Wildemuth, B., Marchionini, G., Yang. M., Geisler, G., Wilkens, T., Hughes, A., & Gruss, R. (2003). How fast is too fast? Evaluating fast forward surrogates for digital video. Proceedings of the ACM/IEEE Joint Conference on Research on Digital Libraries (Houston, TX: May 27-31, 2003)., Los Alamitos, CA: IEEE. pp. 221-230.
Week 10. March 27 Interactive Multimedia Retrieval
QBE models
Multimedia surrogates
Read for next meeting
Zamir, O. & Etzioni, O. (1999). Grouper: A Dynamic Clustering Interface to Web Search Results (WWW8 1999 ) http://www.cs.washington.edu/homes/etzioni/papers/www8.pdf
Hearst, M. & Pedersen, J. (1966). Reexamining the cluster hypothesis: Scatter/gather on retrieval results. Proceedings of the 19th Annual International ACM SIGIR Conference on research and development in information retrieval. (Zurich). 76-84.
http://ils.unc.edu/~march/hcir_seminar/p76-hearst.pdf
Optional
Jorgensen C. & Jorgensen, P. (2005). Image querying by image professionals. JASIST, 56(12), 1346-1359.
Week 11 April 3. Facets and Categories
Clustering
Faceted classification
Read for next meeting
White, R., Jose, J., & Ruthven, I. (2005). Using top-ranking sentences to facilitate effective information access. JASIST, 56(10), 1113-1125.
Week 12 April 10. Designing for Interaction: Context and Other values
Discuss reading
Week 13 April 17 last day
Week 14 April 24 (CHI conference)