文章基本信息

标题：E-Mail Processing with Fuzzy SOMs and Association Rules
本地全文：下载
作者：L. Lanzarini ; A. Villa Monte ; C. Estrebou 等
期刊名称：Journal of Computer Science and Technology
印刷版ISSN：1666-6046
电子版ISSN：1666-6038
出版年度：2011
卷号：11
期号：1
出版社：Iberoamerican Science & Technology Education Consortium
摘要：E-mail texts are hard to process due to their short length.In this article, the use of a diffuse neural network thatis capable of identifying the most relevant terms in a setof e-mails is proposed. The associations between theseterms will be measured through association rules built withthe terms identified by the network. The metrics support,confidence and interest of the rules will be used to qualifythe corresponding terms. The method proposed has been usedto process e-mails of the PACENI Project (Support Projectfor Improving First-Year Teaching in Courses of Studies inExact and Natural Sciences, Economic Science and ComputerScience). With this type of analysis, the most common topicsof student questions have been identified. Even though thisnew information can have various applications, they allinvolve, as a first instance, an improvement in student service
关键词：Information Retrieval; Data Mining; Text Mining;E-mails Analysis; FSOM; Association Rules