Selección de artículos de investigación relevantes y no relevantes con base en resultados de Scopus y visualización por grupos de documentos.

This paper presents a web application that seeks to facilitate the selection of research articles that are relevant or not to a topic. The process starts when a researcher writes a search string, which is sent to the Scopus API. With the results obtained, a grouping process is carried out to generate a visualization by groups or topics instead of the traditional ordered lists of results, making it easier for users to discard groups of articles irrelevant to their query. The proposal uses five clustering algorithms, among which Spectral and K-means exhibited the best performance in classical information retrieval metrics on four state of the art datasets. The application was assessed in two rounds by researchers of Universidad del Cauca, who, in the final round, considered that 71.4% of the clusters had a good title, 92.9% of the clusters had a good document order, and 65.8% of the articles were well clustered. The implementation of overlapping in grouping stands out since it allows articles to belong to several topics. Finally, the results are promising, and the application constitutes a valuable contribution for researchers in developing their projects. However, the results are not generalizable, and the need to create better labeling algorithms to generate more descriptive titles is evident, along with the use of tools to assist the user in query construction. [ABSTRACT FROM AUTHOR]