A graph based method for constructing popular routes with check-ins
World Wide Web(2017)
摘要
Location-based social networks allow people to share their experience of trips by check-in or other ways. Check-in records normally contain two aspects of information, one is semantic information (in the form of text) and the other is location information (in the form of coordinate). In this paper, we present a popular route construction method named GRID based on collective knowledge. Firstly, we mine the check-in records which contain the route’s attributes to divide the whole space into regions and find the POIs of each region. Secondly, we use the location trajectory information of check-ins to infer the connection of POIs in the same region and the connection between regions. Finally, according to user-specified query locations a visiting sequence is determined by calculating the probability of each query location. Experimental results on two real datasets show our approach outperforms a state-of-the-art method in terms of effectiveness and efficiency.
更多查看译文
关键词
Popular route, Social media, Collective knowledge, Route mining
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络