
handle: 10486/662313
La formación de comunidades es un tema apasionante que puede ser enfocado desde múltiples ámbitos (formación, agrupamiento, cohesión, …) En este caso se van a detectar comunidades científicas, grupos de trabajo de investigadores. Esto permitirá entre otras cosas poder identificar autores importantes de una determinada materia, o por el contrario, fraude científico (autores con fama pero sin especial relevancia). Para ello se ha desarrollado una herramienta que permite extraer esa información de una fuente de datos online (Google Scholar), interpretarla y generar un grafo para su posterior análisis. El grafo generado se puede visualizar con cualquier herramienta de visualización de grafos como Gephi. Una vez que se tienen los grafo, se han probado algunos algoritmos de detección de comunidades sobre ellos. Además se ha realizado un breve estudio sobre la detección de cadenas de caracteres con ligeras diferencias entre ellas que refieren al mismo elemento (record linkage), ya que es un problema que aparece a la hora de analizar el trabajo de los autores en base a su firma de artículos.
The formation of communities is an amazing subject that can be approached in several fields (creation, development, clustering, nodes cohesion,...) Scientific communities (working groups of researchers) will be detected in this project. This will permit, among other things, to identify distinguished authors in a certain subject or, on the contrary, detect scientific fraud (famous authors with limited relevance). To do so, it has been developed a tool which permit to extract information from an online database (Google Scholar), structure it and generate a graph to analise it later. The generated graph can be visualised with any tool of graph visualisation, such as Gephi or Cytoscape. Some community detection algorithms, like Chinese Whispers, has been tested over those graphs. Furthermore a brief research about string comparison and record linkages were carried out, since this is a problem that appears when it comes to analise the work of the authors based on their articles signatures.
Informática, Grafos, Teoría de, Investigación científica, Minería de datos
Informática, Grafos, Teoría de, Investigación científica, Minería de datos
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
