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

doi:10.11772/j.issn.1001-9081.2022071029

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (8): 2448-2455.DOI: 10.11772/j.issn.1001-9081.2022071029

• Data science and technology • Previous Articles

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

Shijie PENG, Hongmei CHEN, Lizhen WANG, Qing XIAO

School of Information Science and Engineering，Yunnan University，Kunming Yunnan 650500，China

Received:2022-07-14 Revised:2022-11-18 Accepted:2022-11-30 Online:2023-01-15 Published:2023-08-10
Contact: Hongmei CHEN
About author:PENG Shijie， born in 1998， M. S. candidate. His research interests include spatial data mining.
WANG Lizhen， born in 1962， Ph. D.， professor. Her research interests include spatial data mining.
XIAO Qing， born in 1975， M. S.， associate professor. Her research interests include spatial data mining.
Supported by:
National Natural Science Foundation of China(62266050);Program for Young and Middle-aged Academic and Technical Reserve Leaders of Yunnan Province(202205AC160033);Yunnan Provincial Major Science and Technology Special Plan Project(202202AD080003);Yunnan Fundamental Research Project(202201AS070015)

基于地理偏好排序的兴趣点混合推荐模型

彭诗杰, 陈红梅, 王丽珍, 肖清

云南大学信息学院，昆明 650500

通讯作者: 陈红梅
作者简介:彭诗杰（1998—），男，江西萍乡人，硕士研究生，主要研究方向：空间数据挖掘
王丽珍（1962—），女，山东博兴人，教授，博士，CCF高级会员，主要研究方向：空间数据挖掘
肖清（1975—），女，江西吉水人，副教授，硕士，CCF会员，主要研究方向：空间数据挖掘。
基金资助:
国家自然科学基金资助项目(62266050);云南省中青年学术和技术带头人后备人才项目(202205AC160033);云南省重大科技专项(202202AD080003);云南省基础研究计划重点项目(202201AS070015)

Abstract

Abstract:

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.

Key words: Location-Based Social Network (LBSN), Point-Of-Interest (POI) recommendation, implicit feedback, POI ranking, weighted Bayesian Personalized Ranking (BPR)

摘要：

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-Attentive Encoder and 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%。

关键词: 基于位置的社交网络, 兴趣点推荐, 隐式反馈, 兴趣点排序, 加权贝叶斯个性化排序

CLC Number:

TP391.3

Shijie PENG, Hongmei CHEN, Lizhen WANG, Qing XIAO. Hybrid point-of-interest recommendation model based on geographic preference ranking[J]. Journal of Computer Applications, 2023, 43(8): 2448-2455.

彭诗杰, 陈红梅, 王丽珍, 肖清. 基于地理偏好排序的兴趣点混合推荐模型[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2448-2455.

Figures/Tables 8

Tab. 1 Symbols used in this paper and their descriptions

符号	描述
$U 、 I$	用户集合、POI集合
$u 、 i$	用户 $u ∈ U$ 、POI $i ∈ I$
$R$	用户-POI签到矩阵
$L u +$ 、 $L u -$	用户 $u$ 访问过的POI集、用户 $u$ 未访问的POI集
$M u$	用户 $u$ 的中心点集合
$l o c i$	POI $i$ 的位置坐标
$y ̂ u, i$	用户 $u$ 对POI $i$ 的偏好程度
$U 、 V$	BPR和GWBPR模型中的用户特征矩阵、POI特征矩阵
$k$	GWBPR模型中矩阵维度
$b i$	GWBPR模型中POI i的偏置项
$P 、 Q$	LMF模型中的用户表示矩阵、POI表示矩阵
$d$	LMF模型中矩阵维度
$β u$ 、 $β i$	LMF模型中用户 $u$ 的偏置项、POI $i$ 的偏置项

Tab. 1 Symbols used in this paper and their descriptions

符号	描述
$U 、 I$	用户集合、POI集合
$u 、 i$	用户 $u ∈ U$ 、POI $i ∈ I$
$R$	用户-POI签到矩阵
$L u +$ 、 $L u -$	用户 $u$ 访问过的POI集、用户 $u$ 未访问的POI集
$M u$	用户 $u$ 的中心点集合
$l o c i$	POI $i$ 的位置坐标
$y ̂ u, i$	用户 $u$ 对POI $i$ 的偏好程度
$U 、 V$	BPR和GWBPR模型中的用户特征矩阵、POI特征矩阵
$k$	GWBPR模型中矩阵维度
$b i$	GWBPR模型中POI i的偏置项
$P 、 Q$	LMF模型中的用户表示矩阵、POI表示矩阵
$d$	LMF模型中矩阵维度
$β u$ 、 $β i$	LMF模型中用户 $u$ 的偏置项、POI $i$ 的偏置项

Tab. 2 Statistics of datasets

数据集	用户数	POI数	签到数	矩阵稀疏程度/%	用户平均签到数
Foursquare	7 642	28 483	512 532	99.87	67.06
Gowalla	5 628	31 803	620 683	99.78	110.28

Tab. 3 Experimental results on Foursquare dataset

指标	PMF	MGM	LGLMF	FGCRec	BPR	LMF	SAE-NAD	GWBPR⁃LMF
Precision@5	0.002 6	0.018 2	0.031 8	0.033 3	0.029 3	0.039 4	0.039 5	0.056 9
Precision@10	0.002 5	0.016 6	0.026 4	0.027 8	0.022 0	0.031 6	0.030 5	0.044 2
Precision@15	0.002 3	0.016 6	0.023 3	0.024 4	0.019 0	0.027 5	0.026 1	0.037 7
Precision@20	0.002 0	0.016 1	0.021 3	0.022 7	0.016 9	0.025 0	0.022 8	0.033 4
Recall@5	0.001 9	0.015 7	0.025 7	0.026 6	0.019 7	0.028 8	0.027 1	0.042 3
Recall@10	0.003 5	0.028 2	0.042 5	0.044 1	0.030 0	0.046 8	0.042 0	0.065 7
Recall@15	0.004 8	0.042 3	0.056 3	0.057 5	0.039 3	0.061 3	0.053 6	0.083 9
Recall@20	0.005 8	0.054 1	0.067 5	0.071 0	0.046 8	0.073 7	0.062 1	0.099 0
F1@5	0.002 1	0.016 8	0.028 4	0.029 5	0.023 5	0.033 2	0.039 5	0.048 5
F1@10	0.002 9	0.020 8	0.032 5	0.034 1	0.025 3	0.037 7	0.030 5	0.052 8
F1@15	0.003 1	0.023 8	0.032 9	0.034 2	0.025 6	0.037 9	0.026 1	0.052 0
F1@20	0.002 9	0.024 8	0.032 3	0.034 4	0.024 8	0.037 3	0.022 8	0.049 9
NDCG@5	0.001 7	0.021 2	0.032 4	0.036 0	0.028 9	0.036 6	0.041 4	0.057 8
NDCG@10	0.001 5	0.019 6	0.028 5	0.031 3	0.024 3	0.031 9	0.034 6	0.048 6
NDCG@15	0.001 3	0.018 8	0.026 1	0.028 4	0.021 7	0.028 7	0.031 0	0.043 3
NDCG@20	0.001 3	0.018 2	0.024 4	0.026 7	0.019 9	0.026 7	0.028 3	0.039 7
mAP@5	0.000 5	0.008 9	0.014 1	0.015 7	0.010 0	0.014 4	0.015 4	0.023 7
mAP@10	0.000 6	0.011 2	0.016 9	0.018 6	0.011 7	0.017 1	0.017 8	0.027 7
mAP@15	0.000 6	0.012 6	0.018 5	0.020 0	0.012 6	0.018 3	0.019 1	0.029 7
mAP@20	0.000 7	0.013 6	0.019 4	0.021 1	0.013 2	0.019 3	0.019 9	0.031 1

Tab. 4 Experimental results on Gowalla dataset

指标	PMF	MGM	LGLMF	FGCRec	BPR	LMF	SAE-NAD	GWBPR⁃LMF
Precision@5	0.002 2	0.023 8	0.040 2	0.043 3	0.031 1	0.046 6	0.062 7	0.066 1
Precision@10	0.002 4	0.022 9	0.035 7	0.037 7	0.025 2	0.038 9	0.052 9	0.054 5
Precision@15	0.002 8	0.021 5	0.032 8	0.033 5	0.021 4	0.035 4	0.047 0	0.048 3
Precision@20	0.002 8	0.020 9	0.030 5	0.031 1	0.018 8	0.032 9	0.043 1	0.043 5
Recall@5	0.000 5	0.012 7	0.020 5	0.022 6	0.013 9	0.024 1	0.030 6	0.033 6
Recall@10	0.001 9	0.024 2	0.035 1	0.039 1	0.022 4	0.039 5	0.051 0	0.053 9
Recall@15	0.003 3	0.033 3	0.048 1	0.051 6	0.028 6	0.052 9	0.066 9	0.071 1
Recall@20	0.004 6	0.042 5	0.058 5	0.063 2	0.033 2	0.064 4	0.080 9	0.084 1
F1@5	0.000 8	0.016 5	0.027 1	0.029 6	0.019 2	0.031 7	0.041 1	0.044 5
F1@10	0.002 1	0.023 5	0.035 3	0.038 3	0.023 7	0.039 1	0.051 9	0.054 1
F1@15	0.003 0	0.026 1	0.039 0	0.040 6	0.024 4	0.042 4	0.055 2	0.057 5
F1@20	0.003 4	0.028 0	0.040 0	0.041 6	0.024 0	0.043 5	0.056 2	0.057 3
NDCG@5	0.001 7	0.026 3	0.040 9	0.046 6	0.031 3	0.048 7	0.063 4	0.068 0
NDCG@10	0.001 7	0.025 2	0.037 6	0.041 1	0.027 3	0.042 6	0.057 2	0.059 5
NDCG@15	0.001 6	0.024 5	0.035 4	0.037 6	0.024 4	0.039 3	0.052 5	0.054 4
NDCG@20	0.001 6	0.023 7	0.033 5	0.035 4	0.022 2	0.036 8	0.049 3	0.050 4
mAP@5	0.000 2	0.008 0	0.011 5	0.013 6	0.007 3	0.013 6	0.017 1	0.019 9
mAP@10	0.000 3	0.010 5	0.014 5	0.016 7	0.008 9	0.016 2	0.021 5	0.024 0
mAP@15	0.000 4	0.012 1	0.016 3	0.018 3	0.009 5	0.017 9	0.023 9	0.026 4
mAP@20	0.000 4	0.013 4	0.017 5	0.019 5	0.010 0	0.018 9	0.025 6	0.027 8

Fig. 1 Influence of parameter k on recommendation results

Fig. 2 Influence of parameter d on recommendation results

Fig. 3 Influence of parameter γ on recommendation results

Tab. 5 Results of ablation experiments on Foursquare dataset and Gowalla dataset

指标	Foursquare数据集					Gowalla数据集
指标	BPR	LMF	GWBPR	BPR-LMF	GWBPR-LMF	BPR	LMF	GWBPR	BPR-LMF	GWBPR-LMF
Precision@5	0.029 3	0.039 4	0.050 7	0.048 0	0.0569	0.031 1	0.046 6	0.051 6	0.060 3	0.066 1
Precision@10	0.022 0	0.031 6	0.038 5	0.037 1	0.0442	0.025 2	0.038 9	0.040 4	0.052 9	0.054 5
Precision@15	0.019 0	0.027 5	0.032 6	0.032 0	0.0377	0.021 4	0.035 4	0.036 2	0.047 0	0.048 3
Precision@20	0.016 9	0.025 0	0.029 2	0.028 5	0.0334	0.018 8	0.032 9	0.033 0	0.043 4	0.043 5
Recall@5	0.019 7	0.028 8	0.036 6	0.035 2	0.0423	0.013 9	0.024 1	0.024 4	0.030 5	0.033 6
Recall@10	0.030 0	0.046 8	0.055 0	0.054 3	0.0657	0.022 4	0.039 5	0.038 2	0.048 1	0.053 9
Recall@15	0.039 3	0.061 3	0.070 1	0.070 4	0.0839	0.028 6	0.052 9	0.050 2	0.061 1	0.071 1
Recall@20	0.046 8	0.073 7	0.083 0	0.082 7	0.0990	0.033 2	0.064 4	0.060 8	0.072 9	0.084 1
F1@5	0.023 5	0.033 2	0.042 5	0.040 6	0.0485	0.019 2	0.031 7	0.033 1	0.040 5	0.044 5
F1@10	0.025 3	0.037 7	0.045 2	0.044 0	0.0528	0.023 7	0.039 1	0.039 2	0.050 3	0.054 1
F1@15	0.025 6	0.037 9	0.044 5	0.044 0	0.0520	0.024 4	0.042 4	0.042 0	0.053 1	0.057 5
F1@20	0.024 8	0.037 3	0.043 2	0.042 9	0.0499	0.024 0	0.043 5	0.042 7	0.054 4	0.057 3
NDCG@5	0.028 9	0.036 6	0.054 0	0.049 5	0.0578	0.031 3	0.048 7	0.055 3	0.058 3	0.068 0
NDCG@10	0.024 3	0.031 9	0.045 0	0.042 1	0.0486	0.027 3	0.042 6	0.046 4	0.050 2	0.059 5
NDCG@15	0.021 7	0.028 7	0.039 8	0.038 0	0.0433	0.024 4	0.039 3	0.042 0	0.045 6	0.054 4
NDCG@20	0.019 9	0.026 7	0.036 6	0.034 8	0.0397	0.022 2	0.036 8	0.038 9	0.042 6	0.050 4
mAP@5	0.010 0	0.014 4	0.021 0	0.019 1	0.0237	0.007 3	0.013 6	0.014 8	0.016 8	0.019 9
mAP@10	0.011 7	0.017 1	0.024 6	0.022 5	0.0277	0.008 9	0.016 2	0.017 1	0.019 8	0.024 0
mAP@15	0.012 6	0.018 3	0.026 3	0.024 3	0.0297	0.009 5	0.017 9	0.018 5	0.021 4	0.026 4
mAP@20	0.013 2	0.019 3	0.027 5	0.025 4	0.0311	0.010 0	0.018 9	0.019 6	0.022 6	0.027 8

References 29

1	RENDLE S， FREUDENTHALER C， GANTNER Z， et al. BPR： Bayesian personalized ranking from implicit feedback［C］// Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. Arlington， VA： AUAI Press， 2015： 452-461. 10.1609/aaai.v30i1.9973
2	LI X T， CONG G， LI X L， et al. Rank-GeoFM： a ranking based geographical factorization method for point of interest recommendation［C］// Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2015： 433-442. 10.1145/2766462.2767722
3	CHENG C， YANG H Q， KING I， et al. A unified point-of-interest recommendation framework in location-based social networks［J］. ACM Transactions on Intelligent Systems and Technology， 2017， 8（1）： No.10. 10.1145/2901299
4	张松慧，熊汉江. 融合神经网络和泊松分解的兴趣点推荐算法［J］. 计算机工程与应用， 2020， 56（21）：176-186.
	ZHANG S H， XIONG H J. Point-of-interest recommendation algorithm based on Poisson factorization and neural network［J］. Computer Engineering and Applications， 2020， 56（21）： 176-186.
5	KARATZOGLOU A， BALTRUNAS L， SHI Y. Learning to rank for recommender systems［C］// Proceedings of the 7th ACM Conference on Recommender Systems. New York： ACM， 2013： 493-494. 10.1145/2507157.2508063
6	CHENG C， YANG H Q， KING I， et al. Fused matrix factorization with geographical and social influence in location-based social networks［C］// Proceedings of the 26th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2012： 17-23.
7	YE M， YIN P F， LEE W C， et al. Exploiting geographical influence for collaborative point-of-interest recommendation［C］// Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2011： 325-334. 10.1145/2009916.2009962
8	ZHANG J D， CHOW C Y. iGSLR： personalized geo-social location recommendation： a kernel density estimation approach［C］// Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York： ACM， 2013： 334-343. 10.1145/2525314.2525339
9	LIAN D F， ZHAO C， XIE X， et al. GeoMF： joint geographical modeling and matrix factorization for point-of-interest recommendation［C］// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2014： 831-840. 10.1145/2623330.2623638
10	WANG X L， SUN G H， FANG X， et al. Modeling spatio-temporal neighbourhood for personalized point-of-interest recommendation［C］// Proceedings of the 31st International Joint Conference on Artificial Intelligence. California： ijcai.org， 2022： 3530-3536. 10.24963/ijcai.2022/490
11	安敬民，李冠宇，蒋伟，等. 基于用户活动轨迹和个性化区域划分的兴趣点推荐［J］. 计算机学报， 2022， 45（6）：1176-1194. 10.11897/SP.J.1016.2022.01176
	AN J M， LI G Y， JIANG W， et al. A point-of-interest recommendation method based on activity tracks and personalized-area partitions of users［J］. Chinese Journal of Computers， 2022， 45（6）： 1176-1194. 10.11897/SP.J.1016.2022.01176
12	YUAN Q， CONG G， MA Z Y， et al. Time-aware point-of-interest recommendation［C］// Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2013： 363-372. 10.1145/2484028.2484030
13	RAHMANI H A， ALIANNEJADI M， BARATCHI M， et al. Joint geographical and temporal modeling based on matrix factorization for point-of-interest recommendation［C］// Proceedings of the 2020 European Conference on Information Retrieval， LNCS 12035. Cham： Springer， 2020： 205-219.
14	李寒露，解庆，唐伶俐，等. 融合时空信息和兴趣点重要性的POI推荐算法［J］. 计算机应用， 2020， 40（9）：2600-2605.
	LI H L， XIE Q， TANG L L， et al. POI recommendation algorithm combining spatiotemporal information and POI importance［J］. Journal of Computer Applications， 2020， 40（9）： 2600-2605.
15	王营丽，姜聪聪，冯小年，等. 时间感知的兴趣点推荐方法［J］. 计算机科学， 2021， 48（9）：43-49. 10.11896/jsjkx.210400130
	WANG Y L， JIANG C C， FENG X N， et al. Time aware point-of-interest recommendation［J］. Computer Science， 2021， 48（9）： 43-49. 10.11896/jsjkx.210400130
16	ZHANG J D， CHOW C Y. GeoSoCa： exploiting geographical， social and categorical correlations for point-of-interest recommendations［C］// Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2015： 443-452. 10.1145/2766462.2767711
17	RAHMANI H A， ALIANNEJADI M， MIRZAEI ZADEH R， et al. Category-aware location embedding for point-of-interest recommendation［C］// Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval. New York： ACM， 2019： 173-176. 10.1145/3341981.3344240
18	董婵娟，李胜，何熊熊，等. 融合地理信息、种类信息与隐式社交关系的兴趣点推荐算法［J］. 模式识别与人工智能， 2021， 34（2）：106-116.
	DONG C J， LI S， HE X X， et al. Point of interest recommendation algorithm integrating geo-category information and implicit social relationship［J］. Pattern Recognition and Artificial Intelligence， 2021， 34（2）： 106-116.
19	GUO L， JIANG H R， WANG X H， et al. Learning to recommend point-of-interest with the weighted Bayesian personalized ranking method in LBSNs［J］. Information， 2017， 8（1）： No.20. 10.3390/info8010020
20	YUAN F J， JOSE J M， GUO G B， et al. Joint geo-spatial preference and pairwise ranking for point-of-interest recommendation［C］// Proceedings of the IEEE 28th International Conference on Tools with Artificial Intelligence. Piscataway： IEEE， 2016： 46-53. 10.1109/ictai.2016.0018
21	LIU B P， SU Y J， ZHA D R， et al. CARec： content-aware point-of-interest recommendation via adaptive Bayesian personalized ranking［J］. Australian Journal of Intelligent Information Processing Systems， 2019， 15（3）： 61-68.
22	MANOTUMRUKSA J， MACDONALD C， OUNIS I. A personalised ranking framework with multiple sampling criteria for venue recommendation［C］// Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York： ACM， 2017： 1469-1478. 10.1145/3132847.3132985
23	JOHNSON C C. Logistic matrix factorization for implicit feedback data［EB/OL］. ［2022-03-20］..
24	LIU Y D， PHAM T A N， CONG G， et al. An experimental evaluation of point-of-interest recommendation in location-based social networks［J］. Proceedings of the VLDB Endowment， 2017， 10（10）： 1010-1021. 10.14778/3115404.3115407
25	GAO R， LI J， DU B， et al. Exploiting geo-social correlations to improve pairwise ranking for point-of-interest recommendation［J］. China Communications， 2018， 15（7）： 180-201. 10.1109/cc.2018.8424613
26	SALAKHUTDINOV R， MNIH A. Probabilistic matrix factorization［C］// Proceedings of the 20th International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2007： 1257-1264. 10.1145/1390156.1390267
27	RAHMANI H A， ALIANNEJADI M， AHMADIAN S， et al. LGLMF： local geographical based logistic matrix factorization model for POI recommendation［C］// Proceedings of the 2019 Asia Information Retrieval Symposium， LNCS 12004. Cham： Springer， 2020： 66-78.
28	SU Y J， LI X， LIU B P， et al. FGCRec： fine-grained geographical characteristics modeling for point-of-interest recommendation［C］// Proceedings of the 2020 IEEE International Conference on Communications. Piscataway： IEEE， 2020： 1-6. 10.1109/icc40277.2020.9148797
29	MA C， ZHANG Y X， WANG Q L， et al. Point-of-interest recommendation： exploiting self-attentive autoencoders with neighbor-aware influence［C］// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York： ACM， 2018： 697-706. 10.1145/3269206.3271733

[1]	Jinwei LUO, Dugang LIU, Weike PAN, Zhong MING. Unbiased recommendation model based on improved propensity score estimation [J]. Journal of Computer Applications, 2021, 41(12): 3508-3514.
[2]	Gai LI, Lei LI, Jiaqiang ZHANG. Social collaborative ranking recommendation algorithm by exploiting both explicit and implicit feedback [J]. Journal of Computer Applications, 2021, 41(12): 3515-3520.
[3]	ZHANG Wenlong, QIAN Fulan, CHEN Jie, ZHAO Shu, ZHANG Yanping. Collaborative filtering recommendation algorithm based on dual most relevant attention network [J]. Journal of Computer Applications, 2020, 40(12): 3445-3450.
[4]	SHAO Changcheng, CHEN Pinghua. Point-of-interest recommendation integrating social networks and image contents [J]. Journal of Computer Applications, 2019, 39(5): 1261-1268.
[5]	HU Min, CHEN Yuanhui, HUANG Hongcheng. Supernetwork link prediction method based on spatio-temporal relation in location-based social network [J]. Journal of Computer Applications, 2018, 38(6): 1682-1690.
[6]	GU Junhua, GUAN Lei, ZHANG Jian, GAO Xing, ZHANG Suqi. IPTV implicit scoring model based on Hadoop [J]. Journal of Computer Applications, 2017, 37(11): 3188-3193.
[7]	WANG Dong, CHEN Zhi, YUE Wenjing, GAO Xiang, WANG Feng. Probabilistic matrix factorization recommendation with explicit and implicit feedback [J]. Journal of Computer Applications, 2015, 35(9): 2574-2578.
[8]	LI Gai. Collaborative ranking algorithm by explicit and implicit feedback fusion [J]. Journal of Computer Applications, 2015, 35(5): 1328-1332.

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

基于地理偏好排序的兴趣点混合推荐模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 29

Related Articles 8

Recommended Articles

Metrics