位置社交网络中基于评论文本的兴趣点推荐

发布时间：2018-06-19 22:49

本文选题：用户兴趣点推荐 + 社交网络　；参考：《计算机科学》2017年12期

【摘要】：随着位置社交网络(Location-Based Social Networks,LBSN)的快速发展,兴趣点(Point-Of-Interest,POI)推荐对于用户和商家愈发重要。目前基于社交网络的兴趣点推荐算法主要利用用户的历史签到数据和社交网络数据来提升推荐质量,但忽略了利用兴趣点的评论文本数据;并且LBSN中的数据经常会存在部分信息缺失的情况,对兴趣点推荐算法而言如何保证鲁棒性是一个巨大的挑战。为此,提出了一种新的用户兴趣点推荐模型,称其为SoGeoCom模型。该模型融合了用户社交网络数据、地理位置数据以及兴趣点的评论文本数据这3个因素来进行兴趣点推荐。基于来自Yelp的真实数据集的实验结果表明,与其他主流的兴趣点推荐算法相比,SoGeoCom模型能够提高准确率和召回率,并且具有良好的鲁棒性,获得了更好的推荐效果。
[Abstract]:With the rapid development of Location-Based Social Networks (LBSN), Point-Of-InterestPoI recommendations are becoming increasingly important to users and businesses. At present, social network-based point of interest recommendation algorithm mainly uses user's history check in data and social network data to improve the quality of recommendation, but neglects to use the comment text data of interest point; And the data in LBSN often have some missing information, so how to ensure robustness is a great challenge to point of interest recommendation algorithm. Therefore, a new user point of interest recommendation model is proposed, which is called SoGeoCom model. The model combines user social network data, geographical location data and comment text data of points of interest to make point of interest recommendation. The experimental results based on the real data set from Yelp show that the SoGeoCom model can improve the accuracy and recall rate compared with other popular point of interest recommendation algorithm and has good robustness and better recommendation effect.
【作者单位】：武汉理工大学计算机科学与技术学院;
【基金】：国家自然科学基金(61303029) 科技部国家科技支撑计划基金项目(2012BAH89F01)资助
【分类号】：TP391.3

【相似文献】