Zipf’s law and goffman’s transition point in the automatic indexing
To identify keywords with high semantic value in the thematic content of a scientific paper the Goffman’s transition Point is applied. A total of 1,644 different words were identified in the text. These words were arranged in descending order of frequency to explore four possibilities. In the first...
| Autores: | , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2011 |
| País: | México |
| Recursos: | UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO |
| Repositorio: | Investigación Bibliotecológica: Archivonomía, Bibliotecología e Información |
| Idioma: | español |
| OAI Identifier: | oai:ojs.pkp.sfu.ca:article/27482 |
| Acesso em linha: | http://rev-ib.unam.mx/ib/index.php/ib/article/view/27482 |
| Access Level: | acceso abierto |
| Palavra-chave: | Ley de Zipf Punto de Transición de Goffman Bibliometría Cienciometría Infometría Zipf’s law Goffman’s Transition Point Bibliometrics Scientometrics Infometrics |
| Resumo: | To identify keywords with high semantic value in the thematic content of a scientific paper the Goffman’s transition Point is applied. A total of 1,644 different words were identified in the text. These words were arranged in descending order of frequency to explore four possibilities. In the first examination both, functional words and words with high semantic value were taken into account. In the second examination, the functional words were removed; and in the third examination both functional words as well as words with high semantic content, were lemmatized. In the fourth examination only functional word were eliminated. The result shows the identification of specific keywords. |
|---|