Modeling of topics applied to the analysis of the paper of automatic learning in systemic revisions

The objective of the research was to analyze the role of machine data learning in systematic literature reviews. The Natural Language Processing technique called topic modeling was applied to a set of titles and abstracts collected from the Scopus database. Specifically, the Latent Dirichlet Assignment (LDA) technique was used, from which it was possible to discover and understand the underlying themes in the collection of documents. The results showed the usefulness of the technique used in the exploratory literature review, by allowing the results to be grouped by theme. Likewise, it was possible to identify the specific areas and activities where machine learning has been applied the most, in relation to literature reviews. It is concluded that the LDA technique is an easy-to-use strategy and whose results allow a wide collection of documents to be approached in a systematic and coherent manner, notably reducing the review time.

• Tipo de recurso: http://purl.org/coar/resource_type/c_6718
• Fecha de publicación: 2022
• Institución: Universidad Pedagógica y Tecnológica de Colombia
• Repositorio: RiUPTC: Repositorio Institucional UPTC
• Idioma: spa
• OAI Identifier: oai:repositorio.uptc.edu.co:001/10398
• Acceso en línea: https://revistas.uptc.edu.co/index.php/investigacion_duitama/article/view/15271; https://repositorio.uptc.edu.co/handle/001/10398
• Palabra clave: topic modeling; machine learning; systematic reviews; Latent Dirichlet Allocation; modelado de tópicos; aprendizaje automático; revisiones sistemáticas; Asignación Latente de Dirichlet
• License: Derechos de autor 2022 Revista de Investigación, Desarrollo e Innovación