Search results

A major problem in using current best‐match methods in a filtering task is that of setting appropriate thresholds, which are required in order to force a binary decision on notifying a user of a document. We discuss methods for setting such thresholds and adapting them as a result of feedback information on the performance of the profile. These methods fit within the probabilistic approach to retrieval, and are applied to a probabilistic system. Some experiments, within the framework of the TREC‐7 adaptive filtering track, are described.

The term‐weighting function known as IDF was proposed in 1972, and has since been extremely widely used, usually as part of a TF*IDF function. It is often described as a heuristic, and many papers have been written (some based on Shannon's Information Theory) seeking to establish some theoretical basis for it. Some of these attempts are reviewed, and it is shown that the Information Theory approaches are problematic, but that there are good theoretical justifications of both IDF and TF*IDF in the traditional probabilistic model of information retrieval.

Robertson comments on the theoretical status of IDF term weighting. Its history illustrates how ideas develop in a specific research context, in theory/experiment interaction, and in operational practice.

This paper describes the development of a genetic algorithm (GA) for the assignment of weights to query terms in a ranked‐output document retrieval system. The GA involves a fitness function that is based on full relevance information, and the rankings resulting from the use of these weights are compared with the Robertson‐Sparck Jones F4 retrospective relevance weight. Extended experiments with seven document test collections show that the ga can often find weights that are slightly superior to those produced by the deterministic weighting scheme. That said, there are many cases where the two approaches give the same results, and a few cases where the F4 weights are superior to the ga weights. Since the ga has been designed to identify weights yielding the best possible level of retrospective performance, these results indicate that the F4 weights provide an excellent and practicable alternative. Evidence is presented to suggest that negative weights may play an important role in retrospective relevance weighting.

Sir, We write to record our debt, and that of our colleagues, to one of the founding fathers of information retrieval, Gerard (Gerry) Salton, who died on 28th August 1995 in Ithaca, ny at the age of 68. Information retrieval was established as a new academic discipline by a small number of pioneers, Gerry among them, who recognised the need for, and the research challenges presented by, the automated indexing, storage and retrieval of text documents. He brought academic rigour and scholarship to establishing the foundations of this discipline, and we acknowledge his influential contributions to the theory, experimental methods, and practice of information retrieval.

The decision by the European Court of Justice in Luxembourg in the case involving the Belgian footballer Jean‐Marc Bosnian presents the most serious challenge yet to the influence football clubs hold over their players. The court decided that it is a breach of European law for clubs to demand a transfer fee in respect of a player at the end of his contract, as this is a restriction of the free movement of labour as set out in Article 48 of the Treaty of Rome. This paper considers the implications of this decision for professional football clubs in the UK, several of whom record the services provided by their players as assets on their balance sheet. The paper considers various possible accounting treatments and concludes that in the short term at least, given the uncertainties surrounding the industry post Bosman, recording the cost of players' registrations at their historical cost is the most appropriate policy for clubs to adopt. The paper also considers the implications of the case for clubs' fund‐raising capabilities, through interviews with clubs' bankers, finding that banks are more concerned about the quality of income stream rather than the existence of security in the form of transferring players' registrations. ‘If someone regards players as a merchandise with a monetary value, whose value may in some cases even be included in the balance sheet, he does so at his own risk.’

Aslib is interested in developing modular simulation models of aspects of library systems in order to investigate the use of such models as aids to systems design and operation. The conceptual model of library procedures, developed during the OSTI‐supportcd project on the use of bibliographic records in libraries, offered a suitable basis for a pilot study. The pilot study was aimed at investigating the practicality of developing and using simulation models of library operations, and gaining experience in the application of simulation techniques to problems in the library and information field. The simulation language used was GPSS, in accordance with the 1968 edition of the IBM GPSS/360 User's Manual, H20–0326–2.

Investigates the differences in protocols between arbitral tribunals and courts, with particular emphasis on US, Greek and English law. Gives examples of each country and its way of using the law in specific circumstances, and shows the variations therein. Sums up that arbitration is much the better way to gok as it avoids delays and expenses, plus the vexation/frustration of normal litigation. Concludes that the US and Greek constitutions and common law tradition in England appear to allow involved parties to choose their own judge, who can thus be an arbitrator. Discusses e‐commerce and speculates on this for the future.

The purpose of this article is to present an overview of the history and development of transaction log analysis (TLA) in library and information science research. Organizing a literature review of the first twenty‐five years of TLA poses some challenges and requires some decisions. The primary organizing principle could be a strict chronology of the published research, the research questions addressed, the automated information retrieval (IR) systems that generated the data, the results gained, or even the researchers themselves. The group of active transaction log analyzers remains fairly small in number, and researchers who use transaction logs tend to use this method more than once, so tracing the development and refinement of individuals' uses of the methodology could provide insight into the progress of the method as a whole. For example, if we examine how researchers like W. David Penniman, John Tolle, Christine Borgman, Ray Larson, and Micheline Hancock‐Beaulieu have modified their own understandings and applications of the method over time, we may get an accurate sense of the development of all applications.