带有时间标签的流行社交位置发现

Discovering Popular Social Location with Time Label

流行社交位置是指大多数人日常生活中经常访问的位置,其广泛应用于推荐系统、定向广告应用等领域。随着基于位置的社交网络(Location-Based Social Network,LBSN)的迅速发展,流行社交位置的挖掘成为时空数据挖掘中的一个研究热点。然而,现有的研究主要是从LBSN中挖掘流行社交位置,忽略了流行社交位置的时间因素,因此,文中提出了带有时间标签的流行社交位置发现算法。该算法首先量化LBSN数据集中的时间信息,得到个体用户带有时间标签的频繁社交位置集合;然后计算这些带时间标签的位置在群体用户中的流行度;最后识别出符合要求的带时间标签的流行社交位置。文中采用约10个月的Foursquare东京用户签到数据对该算法的效率和正确性进行验证,结果表明,该算法能够较为准确地发现带有时间标签的流行社交位置。

The popular social location means the places that most people visit frequently in daily life,which is widely used in recommendation systems,targeted advertisement applications,and other fields.With the rapid development of location-based social networks(LBSN),the identification of popular social locations has become an important hot research point in spatio-temporal data mining.However,the existing research mainly focuses on mining popular social locations from LBSN,but ignores the time factor of popular social locations.Therefore,this paper proposed a new algorithm for mining popular locations with time label.The proposed algorithm first quantifies the time information in the LBSN dataset to obtain a set of frequent social locations with respect to individual users,then calculates the popularity of these locations with respect to group of users,and then identifies popular social locations that meet the requirements.This paper validated the efficiency and correctness of the algorithm by using the Foursquare Tokyo user check-in data for about 10 months.The results show that the proposed algorithm can find the popular social location with time label more accurately.