Two supervised learning approaches for name disambiguation in author citations

• Published in: Proceedings of the 4th ACM/IEEE-CS Joint Conference on Digital Libraries pp. 296 - 305
• Main Authors: Han, Hui, Giles, Lee, Zha, Hongyuan, Li, Cheng, Tsioutsiouliklis, Kostas
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 07.06.2004; IEEE; ACM Press
• Series: ACM Conferences
• Subjects: Applied sciences; Artificial intelligence; Bibliographies; Computer science; Computer science; control theory; systems; Exact sciences and technology; Information retrieval; Information systems > Information retrieval; Information systems. Data bases; Memory organisation. Data processing; Permission; Public healthcare; Software; Software libraries; Statistics; Supervised learning; Web search; naive bayes; name disambiguation; support vector machine; Abbreviation; Bayes estimation; Data type; Information integration; Statistical analysis; Disambiguation; Probabilistic approach; Electronic document; Information retrieval; Modeling; Document retrieval; Discrimination; Vector space; Supervised learning; World wide web; Database; Vector support machine; Internet; Electronic library; Bibliography; Ambiguity
• ISBN: 1581138326; 9781581138320
• DOI: 10.1145/996350.996419

Due to name abbreviations, identical names, name misspellings, and pseudonyms inpublications 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. This paper investigates 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) and the vector space representation of citations, a discriminative model. Both approaches utilize three types of citation attributes: co-author 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 DBLPcitation databases.