期刊名称：International Journal of Computer Science and Engineering Communications
电子版ISSN：2347-8586
出版年度：2015
期号：3910
页码：1177-1183
出版社：Scientist Link Group of Publications
摘要：Exponential growth of information generated by online social networks demand effective recommender systems to give useful results. Traditional and Existing system approaches become unqualified because they consider only social relation and network structure but social contextual information has not been fully considered .In this paper we investigate the problem based on social contextual factors. we conduct experiments on Twitter style unidirectional social network datasets. We investigate the real-time interaction of events such as tsunami, earthquakes, cyclone in Online Chat Application and propose an algorithm to monitor chats and to detect a target event. To probe such interactions, device a classifier using Support Vector Machine (SVM) of tweets based on keywords in a tweet, the number of words, and their context. It regards each user as a sensor, and analyzes a spatial and temporal pattern of an event and applies particle filtering which used for location estimation. Also developing an earthquake reporting system detects earthquakes and notification is delivered to nearest users and rescue team. This system detects earthquakes and notification is delivered faster than JMA broadcast announcements.
