期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2015
卷号：28
期号：1
页码：17-20
DOI：10.14445/22312803/IJCTT-V28P105
出版社：Seventh Sense Research Group
摘要：Microblogging services such as twitter, Weibo, and Tumblr create shorttext messages like tweets which are shared at an unprecedented rate. These messages in their raw form while being informative also contains enormous amount of noise and redundancies. Mining these microblogging services can be very useful for business growth and opportunities. This project work proposes a mechanism for using shorttext messages such as tweets to enhance user purchase model. It combines the benefits of Stream clustering module, Highlevel summarization module to model user profile based purchase system. The purchase portal will have two options such as; General Purchase and Profile Based Purchase where items are displayed base on user’s interest. Using a case study approach, the range, frequency, timing, and content of tweets in a corporate account was analyzed.
关键词：Twitter; purchase; tweets; big data; data mining.
