Actas de congresos
Bipartite graph for topic extraction
Fecha
2015-07Registro en:
International Joint Conference on Artificial Intelligence, 24th, 2015, Buenos Aires.
9781577357384
Autor
Faleiros, Thiago de Paulo
Lopes, Alneu de Andrade
Institución
Resumen
This article presents a bipartite graph propagation method to be applied to different tasks in the machine learning unsupervised domain, such as topic extraction and clustering. We introduce the objectives and hypothesis that motivate the use of graph based method, and we give the intuition of the proposed Bipartite Graph Propagation Algorithm. The contribution of this study is the development of new method that allows the use of heuristic knowledge to discover topics in textual data easier than it is possible in the traditional mathematical formalism based on Latent Dirichlet Allocation (LDA). Initial experiments demonstrate that our Bipartite Graph Propagation algorithm return good results in a static context (offline algorithm). Now, our research is focusing on big amount of data and dynamic context (online algorithm).