A description of the catalog division project at the College of Physicians of Philadelphia Library.

This paper describes the procedures used at the Library of the College of Physicians of Philadelphia to divide its ninety-year-old dictionary card catalog. The division was necessitated by overcrowding, obsolete subject headings, and lack of a complete authority list which resulted in like materials being scattered throughout the catalog under several headings. Two catalogs were created: the historical-biographical catalog, representing all works published before 1950 and all works of historical or biographical nature; and the current catalog, containing all works published from 1950 on, excepting historical or biographical materials. The 1950- catalog was further divided into name and subject catalogs, and the subject section was revised according to MeSH. The project was completed in about two years. As a result, searching time has been much reduced, and the library is able to take advantage of the annual revisions of MeSH to update the subject catalog.     

A computer-generated catalog of audiovisuals.

A computer-generated catalog of nonprint media is described. Examples are given of four access points to the data base: (1) main entry, (2) title, (3) MeSH terms, and (4) broad subject categories. The data input procedure is summarized. The AV catalog as the basis for a union list is evaluated, and finally, the catalog in relation to certain local problems is discussed.     

Hierarchical clustering of a Finnish newspaper article collection with graded relevance assessments

Search facilitated with agglomerative hierarchical clustering methods was studied in a collection of Finnish newspaper articles (N = 53,893). To allow quick experiments, clustering was applied to a sample (N = 5,000) that was reduced with principal components analysis. The dendrograms were heuristically cut to find an optimal partition, whose clusters were compared with each of the 30 queries to retrieve the best-matching cluster. The four-level relevance assessment was collapsed into a binary one by (A) considering all the relevant and (B) only the highly relevant documents relevant, respectively. Single linkage (SL) was the worst method. It created many tiny clusters, and, consequently, searches enabled with it had high precision and low recall. The complete linkage (CL), average linkage (AL), and Ward's methods (WM) returned reasonably-sized clusters typically of 18–32 documents. Their recall (A: 27–52%, B: 50–82%) and precision (A: 83–90%, B: 18–21%) was higher than and comparable to those of the SL clusters, respectively. The AL and WM clustering had 1–8% better effectiveness than nearest neighbor searching (NN), and SL and CL were 1–9% less efficient that NN. However, the differences were statistically insignificant. When evaluated with the liberal assessment A, the results suggest that the AL and WM clustering offer better retrieval ability than NN. Assessment B renders the AL and WM clustering better than NN, when recall is considered more important than precision. The results imply that collections in the highly inflectional and agglutinative languages, such as Finnish, may be clustered as the collections in English, provided that documents are appropriately preprocessed.     

Can constrained relevance feedback and display strategies help users retrieve items on mobile devices?

Searching online information resources using mobile devices is affected by small screens which can display only a fraction of ranked search results. In this paper we investigate whether the search effort can be reduced by means of a simple user feedback: for a screenful of search results the user is encouraged to indicate a single most relevant document. In our approach we exploit the fact that, for small display sizes and limited user actions, we can construct a user decision tree representing all possible outcomes of the user interaction with the system. Examining the trees we can compute an upper limit on relevance feedback performance. In this study we consider three standard feedback algorithms: Rocchio, Robertson/Sparck-Jones (RSJ) and a Bayesian algorithm. We evaluate them in conjunction with two strategies for presenting search results: a document ranking that attempts to maximize information gain from the user’s choices and the top-D ranked documents. Experimental results indicate that for RSJ feedback which involves an explicit feature selection policy, the greedy top-D display is more appropriate. For the other two algorithms, the exploratory display that maximizes information gain produces better results. We conducted a user study to compare the performance of the relevance feedback methods with real users and compare the results with the findings from the tree analysis. This comparison between the simulations and real user behaviour indicates that the Bayesian algorithm, coupled with the sampled display, is the most effective. Extended version of “Evaluating Relevance Feedback Algorithms for Searching on Small Displays, ” Vishwa Vinay, Ingemar J. Cox, Natasa Milic-Frayling, Ken Wood published in the proceedings of ECIR 2005, David E. Losada, Juan M. Fernández-Luna (Eds.), Springer 2005, ISBN 3-540-25295-9     

Indianapolis I3: the third generation Integrated Advanced Information Management Systems.

In 2001, the Regenstrief Institute for Health Care and the Indiana University School of Medicine (IUSM) began an IAIMS planning effort to create a vision and a tactical plan for the first Integrated Advanced Information Management Systems (IAIMS) implementation to cross a large area and include unaffiliated institutions. A number of elements made this planning effort unique. Among these elements were the existence of a network infrastructure that supported the Indianapolis Network for Patient Care, the existence of a mature medical informatics program at the Regenstrief Institute, and the existence of a wide-area knowledge network fostered by the IUSM libraries. However, the leadership for a strong information technology role in the IUSM that could promote collaboration in support of education and research across the diverse Indianapolis hospital systems had been lacking. By bringing together various groups, each with a commitment to improve health care quality and public health across the Indianapolis metropolitan area, regardless of individual institutional affiliation, the strategic directions for I3-Indianapolis IAIMS Initiative have been defined and the foundations for a third generation IAIMS construct have been laid in Indianapolis, Indiana.     

Web usage mining at an academic health sciences library: an exploratory study.

OBJECTIVES: This paper explores the potential of multinomial logistic regression analysis to perform Web usage mining for an academic health sciences library Website. METHODS: Usage of database-driven resource gateway pages was logged for a six-month period, including information about users' network addresses, referring uniform resource locators (URLs), and types of resource accessed. RESULTS: It was found that referring URL did vary significantly by two factors: whether a user was on-campus and what type of resource was accessed. CONCLUSIONS: Although the data available for analysis are limited by the nature of the Web and concerns for privacy, this method demonstrates the potential for gaining insight into Web usage that supplements Web log analysis. It can be used to improve the design of static and dynamic Websites today and could be used in the design of more advanced Web systems in the future.