Similarity measures, author cocitation analysis, and information theory

Leydesdorff, Loet

doi:10.1002/asi.20130

Cited by 106 publications

(61 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The perfect rank-order correlation (r ϭ 1.00; p Ͻ .01) between the cosine matrix derived from the asymmetrical citation matrix, and the Jaccard index based on this same Leydesdorff (2005) discussed the advantages of using information measures for the precise calculation of distances using the same co-occurrence data. Information theory also is based on probability calculus (cf.…”

Section: Resultsmentioning

confidence: 99%

“…This led to discussions in previous issues of this journal about the pros and cons of using the Pearson correlation or other measures (Ahlgren, Jarneving, & Rousseau, 2004;Bensman, 2004;Leydesdorff, 2005;White, 2003White, , 2004. Leydesdorff and Vaughan (2006) used the same dataset to show why one should use the (asymmetrical) citation instead of the (symmetrical) co-citation matrix as the basis for the normalization.…”

Section: Introductionmentioning

confidence: 99%

“…The two groups are thus completely separated in terms of the Pearson correlation coefficients; however, there are relations between individual authors in the two groups. An optimal representation should reflect both this complete separation in terms of correlations at the level of the set and the weak overlap generated by individual relations (Leydesdorff, 2005(Leydesdorff, , 2007Waltman & van Eck, 2007). (A visualization of the co-citation matrix TABLE 1.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the normalization and visualization of author co‐citation data: Salton's Cosine versus the Jaccard index

Leydesdorff

2007

J. Am. Soc. Inf. Sci.

Self Cite

190

130

View full text Add to dashboard Cite

The debate about which similarity measure one should use for the normalization in the case of Author Co-citation Analysis (ACA) is further complicated when one distinguishes between the symmetrical co-citation-or, more generally, co-occurrence-matrix and the underlying asymmetrical citation-occurrence-matrix. In the Web environment, the approach of retrieving original citation data is often not feasible. In that case, one should use the Jaccard index, but preferentially after adding the number of total citations (i.e., occurrences) on the main diagonal. Unlike Salton's cosine and the Pearson correlation, the Jaccard index abstracts from the shape of the distributions and focuses only on the intersection and the sum of the two sets. Since the correlations in the co-occurrence matrix may be spurious, this property of the Jaccard index can be considered as an advantage in this case.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the normalization and visualization of author co‐citation data: Salton's Cosine versus the Jaccard index

Leydesdorff

2007

J. Am. Soc. Inf. Sci.

Self Cite

190

130

View full text Add to dashboard Cite

show abstract

“…Following the debate over the use of various similarity measures (Ahlgren et al, 2003(Ahlgren et al, , 2004White, 2003;Leydesdorff & Vaughan, 2006;Leydesdorff, 2008) and other techniques (Leydesdorff, 2005), we begin by testing Blondel et al's algorithm on the often-used case of 12 highly-cited authors working in the information retrieval field and 12 from the field of scientometrics or bibliometrics. Fig.…”

Section: Resultsmentioning

confidence: 99%

A new approach for detecting scientific specialties from raw cocitation networks

Wallace

Gingras

Duhon

2008

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

We use a technique recently developed by Blondel et al. (2008) in order to detect scientific specialties from author cocitation networks. This algorithm has distinct advantages over most of the previous methods used to obtain cocitation "clusters", since it avoids the use of similarity measures, relies entirely on the topology of the weighted network and can be applied to relatively large networks. Most importantly, it requires no subjective interpretation of the cocitation data or of the communities found. Using two examples, we show that the resulting specialties are the smallest coherent "group" of researchers (within a hierarchy of cluster sizes) and can thus be identified unambiguously. Furthermore, we confirm that these communities are indeed representative of what we know about the structure of a given scientific discipline and that, as specialties, they can be accurately characterized by a few keywords (from the publication titles). We argue that this robust and efficient algorithm is particularly well-suited to cocitation networks, and that the results generated can be of great use to researchers studying various facets of the structure and evolution of science.

show abstract

“…where This particular similarity measure is frequently used in text-classification applications, including, for example, the e-rater application, because it is known to be relatively insensitive to zero-frequency word classes (Leydesdorff, 2005). That is, the absence of a particular word class (e.g., bacteria|germ) does not indicate dissimilarity as strongly as the presence of a matching word class indicates similarity.…”

Section: Content Featuresmentioning

confidence: 99%

Inside Sourcefinder: Predicting the Acceptability Status of Candidate Reading-Comprehension Source Documents

Sheehan

Kostin

Futagi

et al. 2006

ETS Research Report Series

View full text Add to dashboard Cite

This paper describes the development, implementation, and evaluation of an automated system for predicting the acceptability status of candidate reading-comprehension stimuli extracted from a database of journal and magazine articles. The system uses a combination of classification and regression techniques to predict the probability that a given document will be deemed acceptable for use in completing a specified passage-creation assignment by at least one test developer. The text features that form the basis of the estimated models are automatically extracted by natural language processing techniques. Model performance is evaluated by comparing the proportion of acceptable documents located with the screening capability turned on to the proportion of acceptable documents located with the screening capability turned off. The evaluation suggests that the estimated models have succeeded in capturing useful information about the characteristics of texts that affect test developers' ratings of source acceptability and that they can help test developers find a greater number of high-quality sources in less time.

show abstract

Similarity measures, author cocitation analysis, and information theory

Cited by 106 publications

References 17 publications

On the normalization and visualization of author co‐citation data: Salton's Cosine versus the Jaccard index

On the normalization and visualization of author co‐citation data: Salton's Cosine versus the Jaccard index

A new approach for detecting scientific specialties from raw cocitation networks

Inside Sourcefinder: Predicting the Acceptability Status of Candidate Reading-Comprehension Source Documents

Contact Info

Product

Resources

About