An indirect method of information retrieval

doi:10.1016/0020-0271(68)90030-2

Information Storage and Retrieval

Volume 4, Issue 4, December 1968, Pages 361-373

https://doi.org/10.1016/0020-0271(68)90030-2 Get rights and content

Abstract

The information retrieval process, treated strictly as a matching procedure, has the defects that the whole file must be probed for each query, and that it overlooks the fact that the relevance of the information from one document depends upon what is already known about the subject, and in turn affects the relevance of other documents subsequently examined. A mathematical model of a search technique in which the defects of the direct method are taken into account is demonstrated by an experiment in which a given paper is treated as an enquiry and the references cited in the paper are treated as relevant answers. The results in two tests show much better results than those achieved by the direct method. No spurious material was retrieved by either method.

References (5)

W. Goffman
A searching procedure for information retrieval
Inf Stor. & Retr.
(1964)
W. Goffman
On relevance as a measure
Inf. Star. & Retr.
(1964)

There are more references available in the full text version of this article.

Cited by (36)

Probabilistic co-relevance for query-sensitive similarity measurement in information retrieval
2013, Information Processing and Management
Interdocument similarities are the fundamental information source required in cluster-based retrieval, which is an advanced retrieval approach that significantly improves performance during information retrieval (IR). An effective similarity metric is query-sensitive similarity, which was introduced by Tombros and Rijsbergen as method to more directly satisfy the cluster hypothesis that forms the basis of cluster-based retrieval. Although this method is reported to be effective, existing applications of query-specific similarity are still limited to vector space models wherein there is no connection to probabilistic approaches. We suggest a probabilistic framework that defines query-sensitive similarity based on probabilistic co-relevance, where the similarity between two documents is proportional to the probability that they are both co-relevant to a specific given query. We further simplify the proposed co-relevance-based similarity by decomposing it into two separate relevance models. We then formulate all the requisite components for the proposed similarity metric in terms of scoring functions used by language modeling methods. Experimental results obtained using standard TREC test collections consistently showed that the proposed query-sensitive similarity measure performs better than term-based similarity and existing query-sensitive similarity in the context of Voorhees’ nearest neighbor test (NNT).
Estimating the diffusion models of crisis information in micro blog
2012, Journal of Informetrics
Citation Excerpt :
In the field of informetrics, Goffman and Price did pioneering research in measuring information growth. Goffman applied an epidemic model to study the diffusion of ideas and the growth of scientific specialties (Goffman, 1966, 1968, 1971; Goffman & Newill, 1967). Price studied the number growth patterns of scientists, scientific journals and papers, finding an exponential growth rate of 5% for the scientific literatures over the past two centuries, corresponding to a doubling time of 15 years (Price, 1963, 1975).
The study tries to construct the diffusion models of crisis information in micro blog. We propose three information release patterns in micro blog according to the duration of crisis information released, namely concentrated release, continuous release, and pulse release. Based on Logistic function, three respective diffusion models are constructed. We choose three crisis events to test the diffusion models using the variables of the number of micro blogs with the crisis information (NMCI) and the increment of NMCI. The estimate results show that the diffusion of crisis information in micro blogs can be described by Logistic function, and the growth curve of NMCI is S-shaped.
Remembering William Goffman: Mathematical information science pioneer
2008, Information Processing and Management
This paper reviews the career and legacy of William (Bill) Goffman, who served as a researcher, Professor, Dean and Emeritus at Case Western Reserve University, Cleveland, Ohio, from 1959 to 2000. Goffman pioneered mathematical information science broadly and in several key areas. First, he applied disease epidemiology concepts to model accurately the spread of knowledge and the formation of knowledge systems and their ecologies, including the dynamics of scientific discovery. Second, he proposed significant improvements in information retrieval through the deployment of multi-valued logic, appropriate file ordering, effective and efficient retrieval measures, and simplified retrieval approaches, including early work in citation-based searching. Third, Goffman applied Bradford-like distributions to model effective core research literature collection development and usage. Fourth, he developed original epidemiology models, and was an early contributor in biomedical informatics. His mathematical contributions have stood the test of time and will continue to be applicable indefinitely.
'Citation profiles' to improve relevance in a two-stage retrieval system: A proposal
1993, Information Processing and Management
Individual differences in relevance judgements are not entirely erratic, and it is productive to consider citation profiles as a simple, convenient, and automatic method of reflecting the knowledge structure/past experience/viewpoints of the authors of papers. A citation profile is nothing but the list of citations appended to the paper. The list of references normally reflects a good sample of the complete or partial survey of that literature considered relevant by the author. Therefore, the source paper, together with its list of references, are to be kept together to provide a more complete picture of the ‘content’ and ‘structure’ of the document. The citation profile is believed to reflect the ‘state of knowing’ of the author, and higher commonality between the citation profile and the mental profile of a user would help improve a relevance decision. A mental profile is the state of knowing of the user, in terms of a set of documents known to the user as relevant. A step in the direction of designing and developing interactive, user-oriented, user-driven systems would be a two-stage information retrieval system where, in the first stage, a topical set of document representations would be produced by a Boolean search, and in the second stage, the citation profile of each document would be provided to the user, either in addition to or in lieu of abstracts.
A Probabilistic Retrieval Scheme for Cluster-based Adaptive Information Retrieval
1991, Proceedings of the 8th International Workshop on Machine Learning, ICML 1991
This paper discusses a retrieval scheme for an Information Retrieval system in which the feedback from a number of users of the system, about its performance (global feedback), is stored in the form of document clusters called user-oriented clusters. These clusters are utilized in answering a query in conjunction with feedback obtained about the system's performance after a partial retrieval for that query (local feedback).
Set-oriented retrieval
1989, Information Processing and Management
The broad way in which we look at how an IRS functions influences the types of questions we ask about it and the ways we try to improve performance. In the recent past, retrieval methodologies have been based on retrieving documents one at a time. In this paper we are introducing a set-oriented view. We observe that this view is quite consistent with the single-document or sequential methods, and define a precise model to capture the set-oriented approach. We then examine a number of consequences of the model, such as the limitations implied by a finite index vocabulary. Finally, we discuss various ways in which the set orientation can influence our thinking about IR.

View all citing articles on Scopus

^☆: Research Supported by AFOSR Grant 403-66.

View full text

An indirect method of information retrieval☆

Abstract

Inf Stor. & Retr.

Inf. Star. & Retr.