This paper has not been submitted elsewhere in identical or similar form, nor will it be during the first three months after its submission to UMUAI. As the number of Internet users and the number of accessible Web pages grows, it is becoming increasingly difficult for users to find documents that are relevant to their particular needs. Users must either browse through a large hierarchy of concepts to find the information for which they are looking or submit a query to a publicly available search engine and wade through hundreds of results, most of them irrelevant. The core of the problem is that whether the user is browsing or searching, whether they are an eighth grade student or a Nobel prize winner, the identical information is selected and it is presented the same way. In this paper, we report on research that adapts information navigation based on a user profile structured as a weighted concept hierarchy. A user may create his or her own concept hierarchy and use them for browsing Web sites. Or, the user profile may be created from a reference ontology by ‘watching over the user’s shoulder’ while they browse. We show that these automatically created profiles reflect the user’s interests quite well and they are able to produce moderate improvements when applied to search results. Current work is investigating the interaction between the user profiles and conceptual search wherein documents are indexed by their concepts in addition to their keywords.

As the number of Internet users and the number of accessible Web pages grows, it is becoming increasingly difficult for users to find documents that are relevant to their particular needs. Users must either browse through a large hierarchy of con cepts to find the information for which they are looking or submit a query to a publicly available search engine and wade through hundreds of results, most of them irrelevant. The core of the problem is that whether the user is browsing or searching, whet her they are an eighth grade student or a Nobel prize winner, the identical information is selected and it is presented the same way. In this paper, we report on research that adapts information navigation based on a user profile structured as a weighted concept hierarchy. A user may create his or her own concept hierarchy and use them for browsing Web sites. Or, the user profile may be created from a reference ontology by `watching over the user's shoulder' while they browse. We show that these automati cally created profiles reflect the user's interests quite well and they are able to produce moderate improvements when applied to search results. Current work is investigating the interaction between the user profiles and conceptual search wherein documents are indexed by their concepts in addition to their keywords. Keywords: ontologies, personalization, browsing, Web navigation, conceptual search 2 1.

As the number of available Web pages grows, users experience increasing difficulty finding documents relevant to their interests. One of the underlying reasons for this is that most search engines find matches based on keywords, regardless of their meanings. To provide the user with more useful information, we need a system that disambiguates queries by including information about the user's conceptual framework. This is the goal of KeyConcept, a conceptual search engine. During indexing, KeyConcept classifies documents into concepts selected from a manuallyconstructed concept hierarchy. During retrieval, KeyConcept ranks documents based on a combination of keyword and conceptual similarity. This paper describes the system architecture and discusses the results of experiments that evaluate the effect of exploiting the hierarchical relationships between concepts during retrieval. Our results confirm that conceptual match significantly improves the precision of the search results over keyword match alone. In addition, the use of the concept hierarchy to prune irrelevant search results also significantly increases precision. Finally, we show that the two used together, conceptual search and pruning, significantly outperforms either used alone.

Abstract not found

The promise of intelligent agents acting on behalf of users' personalized knowledge sharing needs may be hampered by the insistence that these agents begin with a predefined, common ontology instead of personalized, diverse ontologies. Only until recently have researchers diverged from the last decade's "common ontology" paradigm to a paradigm involving agents that can share knowledge using diverse ontologies. This paper describes how we address this agent knowledge sharing problem of how agents deal with diverse ontologies by introducing a methodology and algorithras for multi-agent knowledge sharing and learning. We demonstrate how this approach will enable multi-agent systems to assist groups of people in locating, translating, and sharing knowledge using our Distributed Ontology Gathering Group Integration Environment (DOGGIE) and describe our proof-of-concept experiments. DOGGIE synthesizes agent communication, machine learning, and reasoning for information sharing in the Web domain.

Recommendation and personalization attempt to reduce information overload and retain customers. While research in both recommender systems and personalization grew mainly out of information retrieval, both areas have emerged from nascent levels to veritable and challenging research areas in their own right. Whereas no technical or sophisticated methodologies exist by which to build such systems, the field also lacks a comprehensive, yet manageable survey by which to study recommenda-tion systems and personalization facilities. In this paper, we attempt to fill that gap by presenting a thematic approach toward studying recommendation and personalization. Specifically, we present three major representative personalization themes: rec-ommendation; induction, exploration, and exploitation of social networks; and personalization of information access. We unify the presentation of the three themes which we have extracted from the rich landscape of recommender system and personal-ization research via a functional metaphor, where inputs and output to a function are identified in each theme and instantiated through a number of systems and projects visited. In addition, we examine how a number of systems implement the function through various operators and techniques. Finally, we cover several broadening aspects, such as targeting, privacy and trust,

Abstract—Search engines have significantly improved the efficiency of bio-medical literature searching. These search engines, however, could return many irrelevant results to the intention of the user’s query. To improve precision and recall, various query expansion strategies are widely used. In this paper, we explore the three widely used query expansion strategies-local analysis, global analysis, and ontology-based term reweighting across various search engines. Through experiments, we show that ontology-based term re-weighting works best. Term re-weighting reformulates queries with selection of key original query terms and re-weights these terms and their associated synonyms from UMLS. The results of experiments show that with LUCENE and LEMUR, the average precision is enhanced by up to 20.3 % and 12.1%, respectively, compared to the baseline runs. We believe the principles of this term re-weighting strategy may be extended and utilized in other bio-medical domains. Index Terms—query expansion strategy, term re-weighting, UMLS, ontology I.

. In acknowledging the importance of ontologies in conceptual modeling, database integration and business process modeling, this paper introduces a set of principles for building ontologies. Starting from Guarino's meta-properties of ontological terms, the paper describes the denotational semantics of the meta-properties and derives from them some engineering rules and checks for constructing domain specific conceptual models, based on the overarching requirement to assign meanings to concepts using tags and labels. Parallel research by the authors into the use of contextual references and roles to restrict such meanings will be published elsewhere. 1

The Internet presents a vast resource of information that continues to grow exponentially. Most of the present day search engines aid in locating relevant documents based on keyword matches. However, to provide the user with more relevant information, we need a system that also incorporates the conceptual framework of the queries. This is the goal of KeyConcept, a search engine that retrieves documents based on a combination of keyword and conceptual matching. An automatic classifier is used to determine the concepts to which new documents belong. Currently, the classifier is trained by selecting documents randomly from each concept’s training set and it also ignores the hierarchical structure of the concept tree. In this thesis, we present a novel approach to select these training documents by using document clustering within the concepts. We also exploit hierarchical structure in which the concepts themselves are arranged. Combining these approaches to text classification, we achieve an improvement of 67 % in accuracy over the existing system. 2

This work presents a model in which concepts in ontologies are extended with organizational information to explicitly express the situation in which they were learned and used. It is discussed how autonomous agents are allowed to reason about concept usage and privacy in terms of organizational constructs, paving the way to reason about social roles in open Web communities. A peer-to-peer application following the model is described. We depart from a specific organization model, MOISE , briefly presented here.