基于地理偏好排序的兴趣点混合推荐模型

Hybrid point-of-interest recommendation model based on geographic preference ranking

随着基于位置的社交网络(LBSN)迅速发展,作为缓解信息过载的有效手段,兴趣点(POI)推荐备受关注。由于用户签到数据是隐式反馈数据,且十分稀疏,为了有效地从用户签到数据中捕获用户POI偏好,提出了一个基于地理偏好排序的POI混合推荐模型。首先,考虑用户签到数据的隐式反馈特性及用户活动的空间约束,利用传统贝叶斯个性化排序(BPR)模型计算POI距离对POI排序的影响,提出加权BPR(GWBPR)模型;然后,针对用户签到数据的稀疏性,融合GWBPR模型和逻辑矩阵分解(LMF)模型,提出混合模型GWBPR-LMF。在两个真实数据集Foursquare和Gowalla上的实验结果表明,GWBPR-LMF模型的性能优于BPR、LMF、SAE-NAD(Self-AttentiveEncoderand Neighbor-Aware Decoder)等对比模型。与较优的对比模型SAE-NAD相比,GWBPR-LMF模型的POI推荐的精确率、召回率、F1值、平均精度均值(mAP)、归一化折损累积增益(NDCG)在数据集Foursquare上分别平均提升了44.9%、57.1%、78.4%、55.3%和40.0%,在数据集Gowalla上分别平均提升了3.0%、6.4%、4.6%、11.7%和4.2%。

With the development of Location-Based Social Network(LBSN) Point-Of-Interest(POI) recommendation,an effective way to alleviate information overload,has attracted much attention.As user check-in data are implicit feedback data and very sparse,a hybrid POI recommendation model based on geographic preference ranking was proposed to effectively capture the user preference for POIs from check-in data.First,considering the implicit feedback characteristics of check-in data and the spatial constraint of user activities,by calculating the influence of POI distances on POI ranking based on the traditional Bayesian personalized Ranking(BPR) model,a weighted BPR model named GWBPR(Geo-Weighted Bayesian Personalized Ranking) was proposed.Then,aiming at the sparsity of user check-in data,by further integrating Logistic Matrix Factorization(LMF) model with GWBPR model,a hybrid model GWBPR-LMF(GWBPR with LMF) was proposed.Experimental results on two real datasets,Foursquare and Gowalla,show that GWBPR-LMF model outperforms the comparison models like BPR,LMF and SAE-NAD(Self-Attentive Encoder and Neighbor-Aware Decoder).Compared with the relatively good-performance model SAE-NAD,GWBPR-LMF model improves the precision,recall,F1 score,mean Average Precision(mAP) and Normalized Discounted Cumulative Gain(NDCG) by 44.9%,57.1%,78.4%,55.3%,and 40.0% averagely and respectively on Foursquare dataset,and 3.0%,6.4%,4.6%,11.7%,and 4.2% averagely and respectively on Gowalla dataset.