E-mail processing with fuzzy soms and association rules
Material type:
ArticleDescription: 1 archivo (372,4 KB)Subject(s): Online resources: Summary: E-mail texts are hard to process due to their short length. In this article, the use of a diffuse neural network that is capable of identifying the most relevant terms in a set of e-mails is proposed. The associations between these terms will be measured through association rules built with the terms identified by the network. The metrics support, confidence and interest of the rules will be used to qualify the corresponding terms. The method proposed has been used to process e-mails of the PACENI Project (Support Project for Improving First-Year Teaching in Courses of Studies in Exact and Natural Sciences, Economic Science and Computer Science). With this type of analysis, the most common topics of student questions have been identified. Even though this new information can have various applications, they all involve, as a first instance, an improvement in student service.
| Item type | Home library | Collection | Call number | URL | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|---|---|
Capítulo de libro
|
Biblioteca de la Facultad de Informática | Biblioteca digital | A0427 (Browse shelf(Opens below)) | Link to resource | No corresponde |
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
E-mail texts are hard to process due to their short length. In this article, the use of a diffuse neural network that is capable of identifying the most relevant terms in a set of e-mails is proposed. The associations between these terms will be measured through association rules built with the terms identified by the network. The metrics support, confidence and interest of the rules will be used to qualify the corresponding terms. The method proposed has been used to process e-mails of the PACENI Project (Support Project for Improving First-Year Teaching in Courses of Studies in Exact and Natural Sciences, Economic Science and Computer Science). With this type of analysis, the most common topics of student questions have been identified. Even though this new information can have various applications, they all involve, as a first instance, an improvement in student service.
Journal of Computer Science & Technology, 11(1), pp. 41-46