Field Exam:Information Storage and Retrieval Questions Spring 2005 No. 1

From GSLISWiki

Jump to: navigation, search

Information Storage and Retrieval - Spring 2005

See Also:

[edit] Directions

Answer five out of the six questions below. In your responses to the questions posed, draw on the article itself, articles on your list for the field exam, and other relevant knowledge. The total length of the exam is not to exceed 7500 words, or approximately 1500 words per answer (for a total of about 25-30 double spaced pages of text).

[edit] Article

Yang, Meng; Marchionini, Gary. "Exploring users' video relevance criteria--a pilot study." ASIST '04 Proceedings http://www.open-video.org/papers/MengYang_ASIST040517.pdf

[edit] Question

One of the challenges of designing multimedia retrieval systems is understanding how to align system matching algorithms and user relevance criteria. The study described in this paper seeks to better understand users' video relevance criteria. Does their method lead to findings that can inform system design? Among other things, explore both the strengths and weaknesses of the methodology used in the paper. How does their approach compare to efforts to design other multimedia systems (images, music) to respond to user relevance criteria?

[edit] Article

Salton, Gerard. "The Smart environment for retrieval system evaluation-- advantages and problem areas." In: Information Retrieval Experiment, pp. 316-329, 1981.

[edit] Question

Salton's Smart system was a testbed for implementing and evaluating a large number of different automatic search and retrieval processes. How do the advantages and problem areas that Salton discusses in this article compare to later information retrieval experimental efforts such as TREC?

[edit] Article

Jansen, Bernard J.; Spink, Amanda; Pedersen, Jan. "A temporal comparison of AltaVista web searching." Journal of the American Society for Information Science and Technology 56(6): 559-570, April 2005.

[edit] Question

Transaction log analysis provides an unobtrusive tool for analyzing use of Web search engines. How does this study use these data to characterize use of the Web and implications for further development of Web search engines? How does this approach compare to insights gained from other studies of information search either on the web or using other systems and datasets?

[edit] Article

Bulterman, Dick C.A. "Is it time for a moratorium on metadata?" IEEE Multimedia, pp. 10-17, October-December 2004. http://www.computer.org/multimedia/mu2004/promo1.pdf

[edit] Question

With reference to the large body of content-based and metadata-based retrieval research in the areas of audio, images, video and music, discuss whether the author is correct in his assertion that the development and continued refinement of metadata systems is both unnecssary and unhelpful.

[edit] Article

Hearst, Marti A. "Untangling text data mining." Proceedings of ACL '99: the 37th Annual Meeting of the Association for Computational Linguistics. http://www.sims.berkeley.edu/~hearst/papers/acl99/acl99-tdm.html

[edit] Question

In this paper Marti Hearst concludes that "we do not need fully artificially intelligent text analysis; rather, a mixture of computationally-driven and user-guided analysis may open the door to exciting new results." How does she justify this conclusion in her paper? How does subsequent research in text mining support or refute her conclusion?

[edit] Article

Dunlop, Mark. "Reflections on Mira: Interactive evaluation in information retrieval." Journal of the American Society for Information Science 51(14):1269-1274, December 2000.

[edit] Question

Dunlop concludes his article on interactive evaluation with the observation that "Usability evaluation has approached the assessment of users and their interaction with computers from many different angles: ranging from laboratory experiments, through cooperative evaluation on simulated tasks to long-term workplace studies of systems in use. Adopting these techniques within IR, in parallel to the traditional test collection approaches, should lead to a wider range and style of evaluation work." How does he demonstrate the value of these expanded approaches to evaluation? How have subsequent studies by other investigators approached this challenge?

Retrieved from "http://www.gslis.org/wiki/Field_Exam:Information_Storage_and_Retrieval_Questions_Spring_2005_No._1"
Personal tools