Describes a system based on a probabilistic inference network retrieval model that was used to study the retrieval effectiveness benefits of combining types of document and query information that are found in typical commercial databases and information services. Multiple document representations, multiple index representations, and multiple query…

Discusses the PRECALL, PRR (probability of relevance given retrieval), and EP (expected precision) approaches for dealing with the problem of weak ordering in information retrieval systems. Findings of two experiments comparing evaluation results obtained by PRR and EP are reported. Several mathematical formulas and proofs are included. (20…

Describes an information retrieval methodology based on relevance weighting of search terms in pairs of documents. The vector space model of information retrieval is reviewed, the Bayesian model of text retrieval is discussed, and an automatic implementation of weight estimation using the Medline database is described. (16 references) (LRW)

Presents a logical analysis of the characteristics of indexing and their effects on retrieval. The foundational questions of performance evaluation and the basic quantitative performance measures for binary noninteractive retrieval systems are established. The effects of indexing devices, indexing exhaustivity, specificity, correctness, and…

Explores the theory of psychological relevance and its relationship to information retrieval, and provides an extended example. Topics discussed include information need, the search process, the nature of information, topical relevance, relevance judgments and retrieval testing, information retrieval and bibliometrics, and suggestions for further…

Discussion of the role of Boolean logic in the information retrieval process focuses on a study that investigated the optimization of search logic for the MEDLINE database. Measures of retrieval effectiveness are discussed, the relationship of weighting schema and the logical schema is considered, and further investigations are suggested. (17…

Compares two methods of information retrieval--one that rates documents according to a query and another that uses relevant documents to find further relevant documents (i.e., neighboring documents). Highlights include experiments at the National Library of Medicine; feedback; vector cosine retrieval; and a measure of retrieval effectiveness…

Explores similarities or dissimilarities between citation-semantic and analytic indexing based on a study of records in the Science Citation Index and MEDLINE databases on antibiotic resistance in pneumonia. Concludes that disparate indexing terms may be an advantage for better recall and precision in information retrieval. (Contains 42…

Content-based image retrieval is based on the idea of extracting visual features from images and using them to index images in a database. Proposes similarity measures and an indexing algorithm based on information theory that permits an image to be represented as a single number. When used in conjunction with vectors, this method displays…

Describes the design of an information retrieval system that permits the personalization of a search by developing a user profile in order to reduce noise and increase the number of relevant items retrieved. The preorientation system is explained and an example using full-text natural language processing tools is presented. (Author/LRW)

Discusses methods to be used in an adaptive filtering task, in which incoming documents are routed to users according to stored profiles. Highlights include decision thresholds to help in the retrieval decision; probability of relevance; calibration and logistic regression; feedback; and examples in the Okapi text retrieval system. (LRW)

Investigates the combination of terms and document weighting functions in information retrieval. Describes weighting functions based on how information is used within documents and collections and uses them in two types of experiments: one based on combination of evidence for ad hoc retrieval, and one within a relevance feedback situation.…

This dissertation studies information extraction (IE), the problem of extracting structured information from unstructured data. Example IE tasks include extracting person names from news articles, product information from e-commerce Web pages, street addresses from emails, and names of emerging music bands from blogs. IE is all increasingly…

The amount of online information has grown exponentially over the past few decades, and users become more and more dependent on ranking and recommendation systems to address their information seeking needs. The advance in information technologies has enabled users to provide feedback on the utilities of the underlying ranking and recommendation…

The monitoring and support of university freshmen is considered very important at many educational institutions. In this paper we describe the results of the educational data mining case study aimed at predicting the Electrical Engineering (EE) students drop out after the first semester of their studies or even before they enter the study program…