Enhancing Online Discussion Forums with Topic-Driven Content Search and Assisted Posting

• Autores: Distante, Damiano; Fernández, Alejandro; Cerulo, Luigi; Visaggio, Aaron
• Año de publicación: 2014
• Idioma: inglés
• Tipo de recurso: documento de conferencia
• Materia: Informática; Online discussion forums; information search; Information extraction; text mining; Topic modeling; navigability; searchability; assisted posting; E-learning; Learning management systems; Moodle
• Institución: Universidad Nacional de La Plata

Online forums represent nowadays one of the most popular and rich repository of user generated information over the Internet. Searching information of interest in an online forum may be substantially improved by a proper organization of the forum content. With this aim, in this paper we propose an approach that enhances an existing forum by introducing a navigation structure that enables searching and navigating the forum content by topics of discussion. Topics and hierarchical relations between them are semi-automatically extracted from the forum content by applying Information Retrieval techniques, specifically Topic Models and Formal Concept Analysis. Then, forum posts and discussion threads are associated to discussion topics on a similarity score basis. Moreover, to support automatic moderation in websites that host several forums, we propose a strategy to assist a user writing a new post in choosing the most appropriate forum into which it should be added. An implementation of the topic-driven content search and navigation and assisted posting forum enhancement approaches for the Moodle learning management system is also presented in the paper, opening to the application of these approaches to several real distance learning contexts. Finally, we also report on two case studies that we have conducted to validate the two approaches and evaluate their benefits.
Laboratorio de Investigación y Formación en Informática Avanzada