Andrea L. Houston

Internet browsing and searching: user evaluations of category map and concept space techniques

The Internet provides an exceptional testbed for developing algorithms that can improve browsing and searching large information spaces. Browsing and searching tasks are susceptible to problems of information overload and vocabulary differences. Much of the current research is aimed at the development and refinement of algorithms to improve browsing and searching by addressing these problems. Our research was focused on discovering whether two of the algorithms our research group has developed, a Kohonen algorithm category map for browsing, and an automatically generated concept space algorithm for searching, can help improve browsing and/or searching the Internet. Our results indicate that a Kohonen self-organizing map (SOM)-based algorithm can successfully categorize a large and eclectic Internet information space (the Entertainment subcategory of Yahool) into manageable sub-spaces that users can successfully navigate to locate a homepage of interest to them. The SOM algorithm worked best with browsing tasks that were very broad, and in which subjects skipped around between categories. Subjects especially liked the visual and graphical aspects of the map. Subjects who tried to do a directed search, and those that wanted to use the more familiar mental models (alphabetic or hierarchical organization) for browsing, found that the map did not work well. The results from the concept space experiment were especially encouraging. There were no significant differences among the precision measures for the set of documents identified by subject-suggested terms, thesaurus-suggested terms, and the combination of subject- and thesaurus-suggested terms. The recall measures indicated that the combination of subject- and thesaurus-suggested terms exhibited significantly better recall than subject-suggested terms alone. Furthermore, analysis of the homepages indicated that there was limited overlap between the homepages retrieved by the subject-suggested and thesaurus-suggested terms. Since the retrieved homepages for the most part were different, this suggests that a user can enhance a keyword-based search by using an automatically generated concept space. Subjects especially liked the level of control that they could exert over the search, and the fact that the terms suggested by the thesaurus were real (i.e., originating in the homepages) and therefore guaranteed to have retrieval success.

Toward intelligent meeting agents

Groupware has produced measurable productivity gains for major corporations in recent years. Agent software enhances productivity even more by helping groupware perform convergent tasks, thus freeing users for more creative work. An experiment with an Al-based software agent shows that it can help users organize and consolidate ideas from electronic brainstorming. The agent recalled concepts as effectively as experienced human meeting facilitators and in a fifth of the time.

Medical Data Mining on the Internet: Research on a Cancer Information System

This paper discusses several data mining algorithms and techniques thatwe have developed at the University of Arizona Artificial Intelligence Lab.We have implemented these algorithms and techniques into severalprototypes, one of which focuses on medical information developed incooperation with the National Cancer Institute (NCI) and the University ofIllinois at Urbana-Champaign. We propose an architecture for medicalknowledge information systems that will permit data mining across severalmedical information sources and discuss a suite of data mining tools that weare developing to assist NCI in improving public access to and use of theirexisting vast cancer information collections.

Exploring the use of concept spaces to improve medical information retrieval

This research investigated the application of techniques successfully used in previous information retrieval research, to the more challenging area of medical informatics. It was performed on a biomedical document collection testbed, . CANCERLIT, provided by the National Cancer Institute NCI , which contains information on all types of cancer therapy. The quality or usefulness of terms suggested by three different thesauri, one based on MeSH terms, one based solely on . terms from the document collection, and one based on the Unified Medical Language System UMLS Metathesaurus, was explored with the ultimate goal of improving CANCERLIT information search and retrieval. Researchers affiliated with the University of Arizona Cancer Center evaluated lists of related terms suggested by different thesauri for 12 different directed searches in the CANCERLIT testbed. The preliminary results indicated that among the thesauri, there were no statistically significant differences in either term recall or precision. Surprisingly, there was almost no overlap of relevant terms suggested by the different thesauri for a given search. This suggests that recall could be significantly improved by using a combined thesaurus approach. q 2000 Elsevier Science B.V. All rights reserved.

The (gradually) changing face of state IT jobs

Working for the state once meant long hours, low pay, and lots of red tape. That picture has certainly changed in recent years, as state governments plan to compete with the private sector for top IT talent.

Work Commitments of Baby Boomers and Gen-Xers in the it Profession: Generational Differences or Myth?

The study presented in this paper examines generational (age-cohort) differences in the work commitments of Baby Boomer (born between 1946 and 1962) and Gen-X (born between 1963 and 1981) information technology (IT) professionals. Data were obtained from 382 IT workers in 23 state agencies and universities. The work commitments examined include work involvement, job involvement, work group attachment, organizational commitment and professional commitment. Contrary to profiles of these two generations common in the popular and business press, results suggest that the work commitments of these generations of IT professionals are more homogeneous than different. Implications for research and for IT management are offered.

Semantic indexing and searching using a Hopfield net

This paper presents a neural network approach to document semantic indexing. A Hopfield net algorithm was used to simulate human associative memory for concept exploration in the domain of computer science and engineering. INSPEC, a collection of more than 320,000 document abstracts from leading journals, was used as the document testbed. Benchmark tests confirmed that three parameters (maximum number of activated nodes, ∊ - maximum allowable error, and maximum number of iterations) were useful in positively influencing network convergence behavior without negatively impacting central processing unit performance. Another series of benchmark tests was performed to determine the effectiveness of various filtering techniques in reducing the negative impact of noisy input terms. Preliminary user tests confirmed our expectation that the Hopfield net algorithm is potentially useful as an associative memory technique to improve document recall and precision by solving discrepancies between indexer vocabularies and end-user vocabularies.

Internet browsing and searching (poster): user evaluations of category map and concept space techniques

pages indicated that there was limited overlap between The Internet provides an exceptional testbed for develthe homepages retrieved by the subject-suggested and oping algorithms that can improve browsing and searchthesaurus-suggested terms. Since the retrieved homeing large information spaces. Browsing and searching pages for the most part were different, this suggests that tasks are susceptible to problems of information overa user can enhance a keyword-based search by using load and vocabulary differences. Much of the current an automatically generated concept space. Subjects esresearch is aimed at the development and refinement of pecially liked the level of control that they could exert algorithms to improve browsing and searching by adover the search, and the fact that the terms suggested dressing these problems. Our research was focused on by the thesaurus were ‘‘real’’ ( i.e., originating in the discovering whether two of the algorithms our research homepages) and therefore guaranteed to have retrieval group has developed, a Kohonen algorithm category success. map for browsing, and an automatically generated concept space algorithm for searching, can help improve browsing and/or searching the Internet. Our results indicate that a Kohonen self-organizing map (SOM)-based

Digital Libraries: Social Issues and Technological Advances

Abstract The location and provision of information services has dramatically changed over the last ten years. There is no need to leave the home or office to locate and access information now readily available on-line via digital gateways furnished by a wide variety of information providers, (e.g. libraries, electronic publishers, businesses, organizations, individuals). Information access is no longer restricted to what is physically available in the nearest library. It is electronically accessible from a wide variety of globally distributed information repositories—“digital libraries”. In this chapter we will focus on digital libraries, starting with a discussion of the historical visionaries, definitions, driving forces and enabling technologies and some key research issues. We will discuss some of the US and international digital library projects and research initiatives. We will then describe some of the emerging techniques for building large-scale digital libraries, including a discussion of semantic interoperability, the “Grand Challenge” of digital library research. Finally, we offer our conclusions and a discussion of some future directions for digital libraries.

Using an AI-based tool to categorize digitized textual forms of organizational memory

Digitized textual information is an increasingly common repository for organizational memory. This paper describes an AI-based tool that was developed at the University of Arizona which can be used to organize, categorize and extract digitized textual information from a group support system (GSS) called GroupSystems V. The first sections describe two experiments which measured the tools ability to categorize ideas and compared its performance with human facilitators. Later sections describe two field studies that used the tool with real organizations.