Presents an interpolation theorem for an extended Boolean information retrieval model. Results show that whenever two or more documents are similarly ranked at any two points for a query containing exactly two terms, then they are similarly ranked at all points in between; and that results can fail for queries with more than two terms. (Author/LRW)

Investigates the modeling of changes in user interest in information filtering systems and develops a new technique for tracking user interest shifts based on a Bayesian approach. Presents an analytical study to establish the rate of convergence for a profile learning module with and without the user interest tracking component. (Author/LRW)

Discusses latent semantic indexing (LSI) that would allow search engines to reduce the dimension of the document space by mapping it into a space spanned by conceptual indices. Topics include vector space models; singular value decomposition (SVD); unitary operators; the Haar transform; and new algorithms. (Author/LRW)

Explores aspects of data fusion (DF) for information retrieval (IR) using a set of data from the Fifth International Conference on Text Retrieval (TREC5). Derives an equation for effective DF based on a geometric model and shows that the performance of a pair of IR schemes may be approximated by a quadratic polynomial. (Author/LRW)

Discussion of information retrieval focuses on an Interaction Information Retrieval model in which documents are interconnected; queries and documents are treated in the same way; and retrieval is the result of the interconnection between query and documents. A theoretical mathematical formulation of this type of retrieval is given. (Contains 31…

Presents a unified mathematical definition for the classical models of information retrieval and identifies a mathematical structure behind relevance feedback. Highlights include vector information retrieval; probabilistic information retrieval; and similarity information retrieval. (Contains 118 references.) (Author/LRW)

Presents a new model for combining multiple sources of evidence in database merging based on logistic regression, and occurring only when ranks are available as a key to be used to merge different ranked lists obtained by various retrieval schemes. Results indicate better retrieval effectiveness than other approaches. (LRW)

Explains the use of a topological structure to examine the closeness between documents in retrieval systems and analyzes the topological structure of a vector-space model, a fuzzy-set model, an extended Boolean model, a probabilistic model, and a TIRS (Topological Information Retrieval System) model. Proofs for the results are appended. (17…

Discussion of models for information retrieval focuses on an application of linear algebra to text clustering, namely, a metric for measuring cluster quality based on the theory that cluster quality is proportional to the number of terms that are disjoint across the clusters. Explains term-document matrices and clustering algorithms. (Author/LRW)

Proposes a fuzzy-image database model and a concept of fuzzy space; describes fuzzy-query processing in fuzzy space and fuzzy indexing on complete fuzzy vectors; and uses an example image database, the computer-aided facial-image inference and retrieval system (CAFIIR), for explanation throughout. (Author/LRW)

Discussion of the failure of individual keywords to identify conceptual content of documents in retrieval systems highlights Metric Similarity Modeling, a method for creating vector space representation of documents based on modeling target interdocument similarity values. Semantic relatedness, latent semantic indexing, an indexing and retrieval…

Discussion of local area networks and multiple file servers for concurrent information retrievals provides a rationale for workload and data allocation and presents an analytical model which will attain effective allocation policies. Nonlinear integer programming is discussed, and computational results show the effectiveness of the heuristic.…

Proposes that document space and query space have different structures in information retrieval and discusses similarity measures, term independence, and linear structure. Examples are given using the retrieval functions of dot-product, the cosine measure, the coefficient of Jaccard, and the overlap function. (Contains 28 references.) (LRW)

Presents a visualization tool for information retrieval that can display two different similarity measures, angle and distance, in the same space. Discusses the visual display of information-retrieval evaluation models and develops a new retrieval means based on the visual retrieval tool, the controlling bar. (Author/LRW)

Proposes a fuzzy multiset model for information clustering with application to information retrieval on the World Wide Web. Highlights include search engines; term clustering; document clustering; algorithms for calculating cluster centers; theoretical properties concerning clustering algorithms; and examples to show how the algorithms work.…