Journals | Cart | Stumble | Community

citation analysis > supervised learning approach


Select: All \| None \| Toggle Preview: Open All \| Close All
2004
			Han, H.	Two supervised learning approaches for name disambiguation in author citations read more Abstract: Due to name abbreviations, identical names, name misspellings, and pseudonyms in publications or bibliographies (citations), an author may have multiple names and multiple authors may share the same name. Such name ambiguity affects the performance of document retrieval, Web search, database integration, and may cause improper attribution to authors. We investigate two supervised learning approaches to disambiguate authors in the citations. One approach uses the naive Bayes probability model, a generative model; the other uses support vector machines (SVMs) [V. Vapnik (1995)] and the vector space representation of citations, a discriminative model. Both approaches utilize three types of citation attributes: coauthor names, the title of the paper, and the title of the journal or proceeding. We illustrate these two approaches on two types of data, one collected from the Web, mainly publication lists from homepages, the other collected from the DBLP citation databases. Information retrieval; internet; data integrity; citation analysis; Probability; Bayes methods; bibliographic systems; learning (artificial intelligence); search engines; support vector machines; DBLP citation databases; Web publication lists; Web search; author citations; bibliographies; citation vector space representation; coauthor names; database integration; discriminative model; document retrieval; homepages; identical names; journal title; naive Bayes probability model; name ambiguity; name disambiguation; name misspellings; publication pseudonyms; supervised learning approach; Checkout More Details \| Available Online	2004

Results: 1

1

Results per page: [25]

;

Select Another SubTopic

scientific literature (1);

name disambiguation (1);

research trend mining method (1);

Information Visualization (1);

citation vector space representation (1);

structural pattern extraction (1);

name misspellings (1);

Bayes methods (1);

Data mining (1);

coauthor names (1);

Knowledge Representation (1);

publication pseudonyms (1);

bibliographic systems (1);

Information retrieval (1);

database integration (1);

SOM (1);

supervised learning approach (1);

learning (artificial intelligence) (1);

internet (1);

discriminative model (1);

author-topic model (1);

search engines (1);

data visualisation (1);

document retrieval (1);

probablistic approach (1);

support vector machines (1);

INFORMATION technology (1);

Probability (1);

DBLP citation databases (1);

data integrity (1);

identical names (1);

self-organizing maps (1);

Web publication lists (1);

3D knowledge landscape (1);

journal title (1);

bibliographic networks (1);

Web search (1);

author co-citation analysis (1);

naive Bayes probability model (1);

self-organising feature maps (1);

author citations (1);

knowledge domain intellectual structure visualization (1);

name ambiguity (1);

research area mapping system (1);

bibliographies (1);

Feedback | About Memento