LDA Algorithm for the Identification of Topics: A Case of Study in the Most Influential Twitter Accounts in Ecuador
Abstract:
In the last years, the environment in which we develop has had various changes, most of them due to major technological changes, and the constant development of Information and Communication Technologies (ICTs). As a result of the advances in ICTs, today it is common to interact through social networks and make constant use of them. For this reason, this paper presents an analysis of the 10 most influential Twitter accounts in Ecuador; the objective of this analysis is to detect what the topics or topics addressed in these accounts are. The Latent Dirichlet Allocation (LDA) algorithm using bag of words (BoW) model and also the Term Frequency–Inverse Document Frequency (TF-IDF) model were used for the analysis, finally finding, if the topics provided by both models are similar.
Año de publicación:
2022
Keywords:
- Lda
- Machine learning
- ICTs
- SOCIAL NETWORKS
- Data Mining
Fuente:
google
scopusTipo de documento:
Conference Object
Estado:
Acceso restringido
Áreas de conocimiento:
- Aprendizaje automático
- Redes sociales
- Comunicación
Áreas temáticas:
- Métodos informáticos especiales
- Programación informática, programas, datos, seguridad
- Interacción social
