Automatic Identification of Expertise Analyzing Curves in Lattes Format
Abstract
This paper presents a software system that automatically identifies expertise in personal curriculums, stored in the Lattes format. The identification is made through the extraction of textual information from XML structures used in the Lattes format. Text mining techniques are used to classify the texts according to themes defined in a domain ontology. This process allows identifying user's expertise, that is, competences and areas of interest. Since curriculums in Lattes format are structured by sections (publications, experience, projects, etc), it is possible to identify different areas in different fields of action.
References
CNPq, Conselho Nacional de Pesquisa e qualidade. Disponível pela URL: http://lattes.cnpq.br/
DAVENPORT, T. H. e PRUZAC, L. (1997) "Working knowledge - How organizations rnanage what they know", Harvard Business School Press, Harvard.
LEWIS, D. D. (1998) "Naive (bayes) at forty: the independence assumption in information Retrieval", in: Proc. European Conference on Machine Learning, Lecture Notes in Computer Science, v.1398, Springer, Berlin, p. 4-15.
LOH, S. ; WIVES, L. K.; OLIVEIR, J. P. M. (2000) "Concept-based knowledge discovery in texts extracted from the Web", ACM SIGKDD Explorations 2 (1), p. 29-39.
MCDONALD, D.W. e ACKERMAN, M.S. (2000) "Expertise recommender: a flexible recommendation system and architecture" in Proc. ACM Conf. on Computer Supported Cooperative Work, Philadelphia, p.231-240.
NOY N. F. e MCGUINESS, D. L. (2002) "Ontology Development 101: a guide to creating your first ontology". Disponivel em http://protege.stanford.edu/publications/.
ROCCHIO, J. J. (1966) "Document retrieval systems - optimization and evaluation", Ph. D. Thesis, Harvard Computation Laboratory, Harvard University, Report ISR-10 to National Science Foundation.
SOWA, J. F. (2002) "Building, sharing, and merging ontologies", AAAI Press / MIT press, pages 3-41.
YIMAM-SElD, Dawit; KOBSA, Alfred. Expert Finding Systems for Organizations: Problern and Domain Analysis and the DEMOIR Approach. Journal of Organizational Computing and Electronic Commerce, v. 13, n. 1,2003, p.1-24.
