The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last ten years, due to the increased availability of documents in digital form and the ensuing need to organize them. In the research community the dominant approach to this problem is based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristics of the categories. The advantages of this approach over the knowledge engineering approach (consisting in the manual definition of a classifier by domain experts) are a very good effectiveness, considerable savings in terms of expert labor power, and straightforward portability to different domains. This survey discusses the main approaches to text categorization that fall within the machine learning paradigm. We will discuss in detail issues pertaining to three different problems, namely document representation, classifier construction, and classifier evaluation.

The naive Bayes classifier, currently experiencing a renaissance in machine learning, has long been a core technique in information retrieval. We review some of the variations of naive Bayes models used for text retrieval and classification, focusing on the distributional assump- tions made about word occurrences in documents.

Modem large retrieval environments tend to overwhelm their users by their large output. Since all documents are not of equal relevance to their users, highly relevant documents should be identified and ranked first for presentation to the users. In order to develop IR techniques to this direction, it is necessary to develop evaluation approaches and methods that credit IR methods for their ability to retrieve highly relevant documents. This can be done by extending traditional evaluation methods, i.e., recall and precision based on binary relevance assessments, to graded relevance assessments. Alternatively, novel measures based on graded relevance assessments may be developed. This paper proposes three novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position. The first one accumulates the relevance scores of retrieved documents along the ranked result list. The second one is similar but applies a discount factor on the relevance scores in order to devaluate late-retrieved documents. The third one computes the relative-tothe -ideal performance of IR techniques, based on the cumulative gain they are able to yield. The novel measures are defined and discussed and then their use is demonstrated in a case study using TREC data - sample system run results for 20 queries in TREC-7. As relevance base we used novel graded relevance assessments on a four-point scale. The test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences. The graphs based on the measures also provide insight into the performance IR techniques and allow interpretation, e.g., from the user point of ...

In a peer-to-peer (P2P) system, nodes typically connect to a small set of random nodes (their neighbors), and queries are propagated along these connections. Such query flooding tends to be very expensive. We propose that node connections be influenced by content, so that for example, nodes having many "Jazz" files will connect to other similar nodes. Thus, semantically related nodes form a Semantic Overlay Network (SON). Queries are routed to the appropriate SONs, increasing the chances that matching files will be found quickly, and reducing the search load on nodes that have unrelated content. We have evaluated SONs by using an actual snapshot of music-sharing clients. Our results show that SONs can significantly improve query performance while at the same time allowing users to decide what content to put in their computers and to whom to connect.

Semantic similarity measures play an important role in information retrieval and information integration. Traditional approaches to modeling semantic similarity compute the semantic distance between definitions within a single ontology. This single ontology is either a domain-independent ontology or the result of the integration of existing ontologies. We present an approach to computing semantic similarity that relaxes the requirement of a single ontology and accounts for differences in the levels of explicitness and formalization of the different ontology specifications. A similarity function determines similar entity classes by using a matching process over synonym sets, semantic neighborhoods, and distinguishing features that are classified into parts, functions, and attributes. Experimental results with different ontologies indicate that the model gives good results when ontologies have complete and detailed representations of entity classes. While the combination of word matching and semantic neighborhood matching is adequate for detecting equivalent entity classes, feature matching allows us to discriminate among similar, but not necessarily equivalent, entity classes.

RDF-based P2P networks have a number of advantages compared with simpler P2P networks such as Napster, Gnutella or with approaches based on distributed indices such as CAN and CHORD. RDF-based P2P networks allow complex and extendable descriptions of resources instead of fixed and limited ones, and they provide complex query facilities against these metadata instead of simple keyword-based searches.

Ranked queries are used to locate relevant documents in text databases. In a ranked query a list of terms is specified, then the documents that most closely match the query are returned---in decreasing order of similarity---as answers. Crucial to the efficacy of ranked querying is the use of a similarity heuristic, a mechanism that assigns a numeric score indicating how closely a document and the query match. In this note we explore and categorise a range of similarity heuristics described in the literature. We have implemented all of these measures in a structured way, and have carried out retrieval experiments with a substantial subset of these measures. Our purpose with this work is threefold: first, in enumerating the various measures in an orthogonal framework we make it straightforward for other researchers to describe and discuss similarity measures; second, by experimenting with a wide range of the measures, we hope to observe which features yield good retrieval behaviour in a variety of retrieval environments; and third, by describing our results so far, to gather feedback on the issues we have uncovered. We demonstrate that it is surprisingly difficult to identify which techniques work best, and comment on the experimental methodology required to support any claims as to the superiority of one method over another.

Research on Web searching is at an incipient stage. This aspect provides a unique opportunity to review the current state of research in the field, identify common trends, develop a methodological framework, and define terminology for future Web searching studies. In this article, the results from published studies of Web searching are reviewed in order to present the current state of research. The analysis of the limited Web searching studies available indicates that research methods and terminology are already diverging. A framework is proposed for future studies that will facilitate comparison of results. The advantages of such a framework are presented, and the implications for the design of Web information retrieval systems studies are discussed. Additionally, the searching characteristics of Web users are compared and contrasted with users of traditional information retrieval and online public access systems to discover if there is a need for more studies that focus predominantly or exclusively on Web searching. The comparison indicates that Web searching differs from searching in other environments.

In this paper we review studies of the growth of the Internet and technologies that are useful for information search and retrieval on the Web. We present data on the Internet from several different sources, e.g., current as well as projected number of users, hosts, and Web sites. Although numerical figures vary, overall trends cited

We describe an image retrieval system we built based on a Zoomable User Interface (ZUI). We also discuss the design, results and analysis of a controlled experiment we performed on the browsing aspects of the system. The experiment resulted in a statistically significant difference in the interaction between number of images (25, 75, 225) and style of browser (2D, ZUI, 3D). The 2D and ZUI browser systems performed equally, and both performed better than the 3D systems. The image browsers tested during the experiment include Cerious Software's Thumbs Plus, TriVista Technology's Simple LandScape and Photo GoRound, and our Zoomable Image Browser based on Pad++. Keywords Evaluation, controlled experiment, image browsers, retrieval systems, real-time computer graphics, Zoomable User Interfaces (ZUIs), multiscale interfaces, Pad++. INTRODUCTION In the past two decades, with the emergence of faster computers, the declining cost of memory, the popularity of digital cameras, online archives...