AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
LORE weighs the effect of each visited location on a new location based on the gravity model that effectively integrates the spatiotemporal, social and popularity influences to determine the attractive force between the visited location and the new location

Spatiotemporal Sequential Influence Modeling for Location Recommendations: A Gravity-based Approach

ACM Transactions on Intelligent Systems and Technology, no. 1 (2015)

被引用50|浏览10
EI
下载 PDF 全文
引用
微博一下

摘要

Recommending to users personalized locations is an important feature of Location-Based Social Networks (LBSNs), which benefits users who wish to explore new places and businesses to discover potential customers. In LBSNs, social and geographical influences have been intensively used in location recommendations. However, human movement als...更多

代码

数据

0
简介
  • With the rapid advancement of mobile devices and location acquisition technologies, location-based social networks (LBSNs), such as Foursquare, Gowalla and Brightkite, ACM Transactions on Intelligent Systems and Technology, Vol V, No N, Article A, Publication date: January YYYY.
  • Zhang and C.-Y.
  • Chow Users Social Links Check-ins.
  • Points-ofInterest in Map Bar Stadium Museum Restaurant
重点内容
  • With the rapid advancement of mobile devices and location acquisition technologies, location-based social networks (LBSNs), such as Foursquare, Gowalla and Brightkite, ACM Transactions on Intelligent Systems and Technology, Vol V, No N, Article A, Publication date: January YYYY
  • — In this study, we extend the additive Markov chain developed in our previous work [Zhang et al 2014b] through a gravity model in order to exploit the spatiotemporal higher-order sequential influence
  • We focus on the relative accuracy of our LORE compared to the state-of-the-art location recommendation techniques and expect LORE can improve recommendation accuracy as more check-in activities are recorded
  • LORE exploits the higher-order sequential influence based on the nthorder additive Markov chain that considers all visited locations in the check-in history of a user to find out her probability of visiting new locations
  • LORE weighs the effect of each visited location on a new location based on the gravity model that effectively integrates the spatiotemporal, social and popularity influences to determine the attractive force between the visited location and the new location
  • Experimental results on three real-world data sets show that LORE achieves significantly better recommendation performance than the state-of-the-art location recommendation techniques
方法
  • The authors evaluate the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets.

    5.1.
  • The authors evaluate the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets.
  • The authors use three publicly available large-scale real check-in data sets that were crawled from Foursquare [Gao et al 2012], Gowalla and Brightkite [Cho et al 2011], in which the locations are distributed all over the world.
结果
  • Experimental Results and Discussion

    Here the authors analyze and discuss the experimental results.

    5.5.1.
  • This method [Yuan et al 2013] utilizes the spatiotemporal influences through modeling the spatial influence as a power-law distribution and inferring the temporal influence at each time slot separately which suffers from time information loss and may not correlate temporal influences at different time slots due to time discretization.
  • STI does not perform well in comparison to other recommendation methods
结论
  • The authors discuss the general trends and important findings as follows. Effect of the sparsity of data.
  • It is worth emphasizing that the accuracy of location recommendation techniques for LBSNs is usually not very high, because the density of a user-POI check-in matrix is pretty low.
  • LORE exploits the higher-order sequential influence based on the nthorder additive Markov chain that considers all visited locations in the check-in history of a user to find out her probability of visiting new locations.
  • The authors plan to extend LORE to recommend a trip of POIs for users, investigate the sequential patterns between location categories at the coarse level of.
  • Experimental results on three real-world data sets show that LORE achieves significantly better recommendation performance than the state-of-the-art location recommendation techniques.
总结
  • Introduction:

    With the rapid advancement of mobile devices and location acquisition technologies, location-based social networks (LBSNs), such as Foursquare, Gowalla and Brightkite, ACM Transactions on Intelligent Systems and Technology, Vol V, No N, Article A, Publication date: January YYYY.
  • Zhang and C.-Y.
  • Chow Users Social Links Check-ins.
  • Points-ofInterest in Map Bar Stadium Museum Restaurant
  • Methods:

    The authors evaluate the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets.

    5.1.
  • The authors evaluate the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets.
  • The authors use three publicly available large-scale real check-in data sets that were crawled from Foursquare [Gao et al 2012], Gowalla and Brightkite [Cho et al 2011], in which the locations are distributed all over the world.
  • Results:

    Experimental Results and Discussion

    Here the authors analyze and discuss the experimental results.

    5.5.1.
  • This method [Yuan et al 2013] utilizes the spatiotemporal influences through modeling the spatial influence as a power-law distribution and inferring the temporal influence at each time slot separately which suffers from time information loss and may not correlate temporal influences at different time slots due to time discretization.
  • STI does not perform well in comparison to other recommendation methods
  • Conclusion:

    The authors discuss the general trends and important findings as follows. Effect of the sparsity of data.
  • It is worth emphasizing that the accuracy of location recommendation techniques for LBSNs is usually not very high, because the density of a user-POI check-in matrix is pretty low.
  • LORE exploits the higher-order sequential influence based on the nthorder additive Markov chain that considers all visited locations in the check-in history of a user to find out her probability of visiting new locations.
  • The authors plan to extend LORE to recommend a trip of POIs for users, investigate the sequential patterns between location categories at the coarse level of.
  • Experimental results on three real-world data sets show that LORE achieves significantly better recommendation performance than the state-of-the-art location recommendation techniques.
表格
  • Table1: Key Notations in the Paper
  • Table2: Statistics of the Three Real Data Sets
Download tables as Excel
相关工作
  • In general, there are six main categories for existing location recommendation approaches in LBSNs. Note that some works belong to more than one category, since they combine different recommendation methods with different input data.

    Collaborative filtering. Most studies provide POI recommendations using the memory or model based collaborative filtering techniques on users’ check-in data [Bao et al 2012; Levandoski et al 2012; Lian et al 2015; Liu and Xiong 2013; Lu et al 2012], GPS trajectories [Leung et al 2011; Zheng et al 2011; Zheng et al 2012], or geotagged photos [Shi et al 2013]. These studies usually concentrate on measuring the similarities among users or locations, for instance, the study [Zheng et al 2011] takes into account three factors: (a) the sequence property of people’s outdoor movements, (b) the visited popularity of a geographic region, and (c) the hierarchical property of geographic spaces. Specifically, Levandoski et al [2012] applied the item-based collaborative filtering method, Bao et al [2012], Lian et al [2015], Lu et al [2012] and Zheng et al [2011] employed the user-based collaborative filtering methods, Liu and Xiong [2013], Zheng et al [2012] and Shi et al [2013] utilized the matrix factorization methods, and Leung et al [2011] designed a new similarity-based approach and co-clustering technique. These classical collaborative filtering techniques have been extensively extended to integrate with other information such as social links between users, geographical coordinates and textual contents of POIs, as discussed below.
基金
  • This work was supported by Guangdong Natural Science Foundation of China under Grant S2013010012363
研究对象与分析
real-world data sets: 3
Experimental results show that LORE achieves significantly superior location recommendations compared to other state-of-the-art location recommendation techniques. This section evaluates the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets.

5.1
. Three Real Data Sets

We use three publicly available large-scale real check-in data sets that were crawled from Foursquare [Gao et al 2012], Gowalla and Brightkite [Cho et al 2011], in which the locations are distributed all over the world

large-scale real-world data sets: 3
The gravity model effectively integrates the spatiotemporal, social, and popularity influences by estimating a power-law distribution based on (1) the spatial distance and temporal difference between two consecutive check-in locations of the same user, (2) the check-in frequency of social friends, and (3) the popularity of locations from all users, respectively. Finally, we conduct a comprehensive performance evaluation for LORE using three large-scale real-world data sets collected from Foursquare, Gowalla, and Brightkite. Experimental results show that LORE achieves significantly superior location recommendations compared to other state-of-the-art location recommendation techniques

publicly available real data sets: 3
The sequential patterns may associate with the time of a day (e.g., people usually visit museums or libraries at daytime, go to restaurants for dinner in the evening, and then relax in cinemas or bars at night), the geographical proximity of POIs (e.g., tourists often orderly visit London Eye, Big Ben, Downing Street, Horse Guards, and Trafalgar Square [Yin et al 2011]), the place nature and human preference (e.g., checking in stadiums first and then restaurants is better than the reverse way because it is not healthy to exercise right after a meal [Hsieh et al 2014]). To observe the sequential patterns in depth, we conduct analysis on three publicly available real data sets collected from popular LBSNs: Foursquare [Gao et al 2012], Gowalla and Brightkite [Cho et al 2011]. As an example, here we focus on the twogram sequential patterns

large-scale real-world data sets: 3
Temporal difference between two time instants The spatial Haversine distance between two locations Popularity of location l Social check-in frequency by user u’s friends to location l study to investigate the spatiotemporal higher-order sequential influence for location recommendations. (Section 3) — We propose a new gravity model that effectively integrates the spatiotemporal, social and popularity influences to find the personalized attractive force between a visited location of a user and a new location for the user as the weight of the visited location affecting the new location. Moreover, the spatiotemporal, social, and popularity influences are modeled as a distribution from the historical check-in data, respectively. (Section 4) — We conduct extensive experiments to evaluate the performance of LORE using three large-scale real-world data sets collected from Foursquare, Gowalla, and Brightkite. Experimental results show that LORE outperforms other state-of-the-art location recommendation techniques in terms of recommendation accuracy. (Section 5)

publicly available real data sets: 3
FT em and FSpa are deduced from the distributions of temporal difference and spatial distance that are learned from the check-in data. We assume that the temporal difference or spatial distance between consecutive check-ins of users follows a power-law distribution; this assumption has been validated in three publicly available real data sets collected from popular LBSNs: Foursquare [Gao et al 2012], Gowalla and Brightkite [Cho et al 2011]. 4.2.1

real-world data sets: 3
ln(x + 1). Figure 6 shows that the temporal differences (i.e., the dots) in the three real-world data sets fit a certain power-law distribution (i.e., the line) quite well that is estimated through Equations (8) and (9). Thus, modeling the temporal difference as a power-law distribution is reasonable and effective

real-world data sets: 3
ln(y + 1). Figure 7 also shows that the probability density of the spatial distances (i.e., the dots) in the three real-world data sets approximately follows an estimated power-law distribution (i.e., the line) based on Equations (12) and (13). Thus, the assumption made here is reasonable and feasible as well

real-world data sets: 3
is the popularity of location l′. Figure shows the probability density of popularity (i.e., the dots) in the three real-world data sets matches the power-law distribution (i.e., the line) very well, estimated by Equations (19) and (20). Thus, these results have validated the assumption of the power-law distribution

real-world data sets: 3
of user u′ on location l′. Figure 9 presents the probability density of social check-in frequency (i.e., the dots) in the three real-world data sets that approaches to the power-law distribution (i.e., the line) estimated based on Equations (22) and (23). Hence, the assumption of the power-law distribution has been validated

real-world data sets: 3
In terms of her current location and visited history on POIs, LORE suggests the user to visit the Times Square, Museum of Modern Art, Plaza Hotel, Central Park and Metropolitan Museum of Art that are around her current location and satisfy her personal preference derived from ALGORITHM 1. This section evaluates the recommendation accuracy of LORE compared to the stateof-the-art location recommendation techniques on three real-world data sets. 5.1

real data sets: 3
Comparison of Recommendation Accuracy. Figures 11 and 12 compare the recommendation accuracy of the state-of-the-art location recommendation techniques regarding the number of recommended POIs for users (top-k) and the number of visited POIs of users in the training set (given-n), respectively, on the three real data sets. STI

data sets: 3
In Figure 11, we examine the recommendation quality respecting the recommended number k of POIs; note that recommending too many POIs is not helpful for users. As expected with the increase of k, the recall gradually gets higher but the precision steadily becomes lower on the three data sets. The explanation is pretty straightforward: in general, by returning more POIs for users, it is always able to discover more POIs that users would like to visit

real-world data sets: 3
Further, LORE weighs the effect of each visited location on a new location based on the gravity model that effectively integrates the spatiotemporal, social and popularity influences to determine the attractive force between the visited location and the new location. Finally, experimental results on three real-world data sets show that LORE achieves significantly better recommendation performance than the state-of-the-art location recommendation techniques. In the future, we plan to extend LORE to recommend a trip of POIs for users, investigate the sequential patterns between location categories at the coarse level of

引用论文
  • Jie Bao, Yu Zheng, and Mohamed F. Mokbel. 2012. Location-based and preference-aware recommendation using sparse geo-social networking data. In Proceedings of the 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Redondo Beach, CA, 199–208.
    Google ScholarLocate open access versionFindings
  • Zaiben Chen, Heng Tao Shen, and Xiaofang Zhou. 2011. Discovering popular routes from trajectories. In Proceedings of the 27th IEEE International Conference on Data Engineering. Hannover, Germany, 900– 911.
    Google ScholarLocate open access versionFindings
  • An-Jung Cheng, Yan-Ying Chen, Yen-Ta Huang, Winston H. Hsu, and Hong-Yuan Mark Liao. 2011. Personalized travel recommendation by mining people attributes from community-contributed photos. In Proceedings of the 19th ACM International Conference on Multimedia. Scottsdale, AZ, 83–92.
    Google ScholarLocate open access versionFindings
  • Chen Cheng, Haiqin Yang, Irwin King, and Michael R. Lyu. 2012. Fused matrix factorization with geographical and social influence in location-based social networks. In Proceedings of the 26th National Conference on Artificial Intelligence. Toronto, Canada, 17–23.
    Google ScholarLocate open access versionFindings
  • Chen Cheng, Haiqin Yang, Michael R. Lyu, and Irwin King. 2013. Where you like to go next: Successive point-of-interest recommendation. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence. Beijing, China, 2605–2611.
    Google ScholarLocate open access versionFindings
  • Eunjoon Cho, Seth A. Myers, and Jure Leskovec. 2011. Friendship and mobility: User movement in locationbased social networks. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, CA, 1082–1090.
    Google ScholarLocate open access versionFindings
  • Gregory Ference, Mao Ye, and Wang-Chien Lee. 2013. Location recommendation for out-of-town users in location-based social networks. In Proceedings of the 22nd ACM Conference on Information and Knowledge Management. San Francisco, CA, 721–726.
    Google ScholarLocate open access versionFindings
  • Huiji Gao, Jiliang Tang, Xia Hu, and Huan Liu. 2013. Exploring temporal effects for location recommendation on location-based social networks. In Proceedings of the 7th ACM Conference on Recommender Systems. Hong Kong, China, 93–100.
    Google ScholarLocate open access versionFindings
  • Huiji Gao, Jiliang Tang, Xia Hu, and Huan Liu. 2015. Content-aware point of interest recommendation on location-based social networks. In Proceedings of the 29th National Conference on Artificial Intelligence. Austin, TX, 1721–1727.
    Google ScholarLocate open access versionFindings
  • Huiji Gao, Jiliang Tang, and Huan Liu. 2012. gSCorr: Modeling geo-social correlations for new check-ins on location-based social networks. In Proceedings of the 21st ACM Conference on Information and Knowledge Management. Maui, HI, 1582–1586.
    Google ScholarLocate open access versionFindings
  • Marta C. Gonzalez, Cesar A. Hidalgo, and Albert-Laszlo Barabasi. 2008. Understanding individual human mobility patterns. Nature 453, 7196 (2008), 779–782.
    Google ScholarLocate open access versionFindings
  • Hsun-Ping Hsieh, Cheng-Te Li, and Shou-De Lin. 2014. Measuring and recommending time-sensitive routes from location-based data. ACM Transactions on Intelligent Systems and Technology 5, 3 (2014), 45:1– 45:27.
    Google ScholarLocate open access versionFindings
  • Bo Hu and Martin Ester. 20Spatial topic modeling in online social media for location recommendation. In Proceedings of the 7th ACM Conference on Recommender Systems. Hong Kong, China, 25–32.
    Google ScholarLocate open access versionFindings
  • Bo Hu, M. Jamali, and M. Ester. 2013. Spatio-temporal topic modeling in mobile social media for location recommendation. In Proceedings of the 13th IEEE International Conference on Data Mining. Dallas, TX, 1073–1078.
    Google ScholarLocate open access versionFindings
  • Yehuda Koren. 2010. Collaborative filtering with temporal dynamics. Commun. ACM 53, 4 (2010), 89–97.
    Google ScholarLocate open access versionFindings
  • Takeshi Kurashima, Tomoharu Iwata, Takahide Hoshide, Noriko Takaya, and Ko Fujimura. 2013. Geo topic model: Joint modeling of user’s activity area and interests for location recommendation. In Proceedings of the 6th ACM International Conference on Web Search and Data Mining. Rome, Italy, 375–384.
    Google ScholarLocate open access versionFindings
  • Takeshi Kurashima, Tomoharu Iwata, Go Irie, and Ko Fujimura. 2010. Travel route recommendation using geotags in photo sharing sites. In Proceedings of the 19th ACM Conference on Information and Knowledge Management. Toronto, Canada, 579–588.
    Google ScholarLocate open access versionFindings
  • Kenneth Wai-Ting Leung, Dik Lun Lee, and Wang-Chien Lee. 2011. CLR: A collaborative location recommendation framework based on co-clustering. In Proceeding of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. Beijing, China, 305–314.
    Google ScholarLocate open access versionFindings
  • Justin J. Levandoski, Mohamed Sarwat, Ahmed Eldawy, and Mohamed F. Mokbel. 2012. LARS: A locationaware recommender system. In Proceedings of the 28th IEEE International Conference on Data Engineering. Washington, DC, 450–461.
    Google ScholarLocate open access versionFindings
  • Defu Lian, Xing Xie, Vincent W. Zheng, Nicholas Yuan, Fuzheng Zhang, and Enhong Chen. 2015. CEPR: A collaborative exploration and periodically returning model for location prediction. ACM Transactions on Intelligent Systems and Technology, accepted to appear (2015).
    Google ScholarLocate open access versionFindings
  • Defu Lian, Cong Zhao, Xing Xie, Guangzhong Sun, Enhong Chen, and Yong Rui. 2014. GeoMF: Joint geographical modeling and matrix factorization for point-of-interest recommendation. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York City, NY, 831–840.
    Google ScholarLocate open access versionFindings
  • Bin Liu, Yanjie Fu, Zijun Yao, and Hui Xiong. 2013a. Learning geographical preferences for point-of-interest recommendation. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago, IL, 1043–1051.
    Google ScholarLocate open access versionFindings
  • Bin Liu and Hui Xiong. 2013. Point-of-interest recommendation in location based social networks with topic and location awareness. In Proceedings of the SIAM International Conference on Data Mining. Austin, TX, 396–404.
    Google ScholarLocate open access versionFindings
  • Bin Liu, Hui Xiong, Spiros Papadimitriou, Yanjie Fu, and Zijun Yao. 2014c. A general geographical probabilistic factor model for point of interest recommendation. IEEE Transactions on Knowledge and Data Engineering, accepted to appear (2014).
    Google ScholarLocate open access versionFindings
  • Xin Liu, Yong Liu, Karl Aberer, and Chunyan Miao. 2013b. Personalized point-of-interest recommendation by mining users’ preference transition (short paper). In Proceedings of the 22nd ACM Conference on Information and Knowledge Management. San Francisco, CA, 733–738.
    Google ScholarLocate open access versionFindings
  • Yu Liu, Zhengwei Sui, Chaogui Kang, and Yong Gao. 2014a. Uncovering patterns of inter-urban trip and spatial interaction from social media check-in data. PLoS ONE 9, 1 (2014), e86026.
    Google ScholarLocate open access versionFindings
  • Yong Liu, Wei Wei, Aixin Sun, and Chunyan Miao. 2014b. Exploiting geographical neighborhood characteristics for location recommendation. In Proceedings of the 23rd ACM Conference on Information and Knowledge Management. Shanghai, China, 739–748.
    Google ScholarLocate open access versionFindings
  • Eric Hsueh-Chan Lu, Ching-Yu Chen, and Vincent S. Tseng. 2012. Personalized trip recommendation with multiple constraints by mining user check-in behaviors. In Proceedings of the 20th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Redondo Beach, CA, 209– 218.
    Google ScholarLocate open access versionFindings
  • Yue Shi, Pavel Serdyukov, Alan Hanjalic, and Martha Larson. 2013. Nontrivial landmark recommendation using geotagged photos. ACM Transactions on Intelligent Systems and Technology 4, 3 (2013), 47:1– 47:27.
    Google ScholarLocate open access versionFindings
  • Roger W. Sinnott. 1984. Virtues of the Haversine. Sky and Telescop 68, 2 (1984), 159–159.
    Google ScholarLocate open access versionFindings
  • Chaoming Song, Zehui Qu, Nicholas Blumm, and Albert-Laszlo Barabasi. 2010. Limits of predictability in human mobility. Science 327, 5968 (2010), 1018–1021.
    Google ScholarLocate open access versionFindings
  • Hao Wang, Manolis Terrovitis, and Nikos Mamoulis. 2013. Location recommendation in location-based social networks using user check-in data. In Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando, FL, 384–393.
    Google ScholarLocate open access versionFindings
  • Xiangyu Wang, Yi-Liang Zhao, Liqiang Nie, Yue Gao, Weizhi Nie, Zheng-Jun Zha, and Tat-Seng Chua. 2015. Semantic-based location recommendation with multimodal venue semantics. IEEE Transactions on Multimedia 17, 3 (2015), 409–419.
    Google ScholarLocate open access versionFindings
  • Dingqi Yang, Daqing Zhang, Zhiyong Yu, and Zhu Wang. 2013. A sentiment-enhanced personalized location recommendation system. In Proceedings of the 24th ACM Conference on Hypertext and Social Media. Paris, France, 119–128.
    Google ScholarLocate open access versionFindings
  • Zijun Yao, Bin Liu, Yanjie Fu, Hui Xiong, and Yong Ge. 2014. User preference learning with multiple information fusion for restaurant recommendation. In Proceedings of the SIAM International Conference on Data Mining. Philadelphia, PA, 470–478.
    Google ScholarLocate open access versionFindings
  • Mao Ye, Peifeng Yin, Wang-Chien Lee, and Dik-Lun Lee. 2011. Exploiting geographical influence for collaborative point-of-interest recommendation. In Proceeding of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. Beijing, China, 325–334.
    Google ScholarLocate open access versionFindings
  • Hongzhi Yin, Bin Cui, Yizhou Sun, Zhiting Hu, and Ling Chen. 2014. LCARS: A spatial item recommender system. ACM Transactions on Information Systems 32, 3 (2014), 11:1–11:37.
    Google ScholarLocate open access versionFindings
  • Hongzhi Yin, Yizhou Sun, Bin Cui, Zhiting Hu, and Ling Chen. 2013. LCARS: A location-content-aware recommender system. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago, IL, 221–229.
    Google ScholarLocate open access versionFindings
  • Zhijun Yin, Liangliang Cao, Jiawei Han, Jiebo Luo, and Thomas S. Huang. 2011. Diversified trajectory pattern ranking in geo-tagged social media. In Proceedings of the SIAM International Conference on Data Mining. Mesa, AZ, 980–991.
    Google ScholarLocate open access versionFindings
  • Josh Jia-Ching Ying, Wen-Ning Kuo, Vincent S. Tseng, and Eric Hsueh-Chan Lu. 2014. Mining user checkin behavior with a random walk for urban point-of-interest recommendations. ACM Transactions on Intelligent Systems and Technology 5, 3 (2014), 40:1–40:26.
    Google ScholarLocate open access versionFindings
  • Josh Jia-Ching Ying, Wang-Chien Lee, and Vincent S. Tseng. 2013. Mining geographic-temporal-semantic patterns in trajectories for location prediction. ACM Transactions on Intelligent Systems and Technology 5, 1 (2013), 2:1–2:33.
    Google ScholarLocate open access versionFindings
  • Josh Jia-Ching Ying, Eric Hsueh-Chan Lu, Wen-Ning Kuo, and Vincent S. Tseng. 2012. Urban point-ofinterest recommendation by mining user check-in behaviors. In Proceedings of the ACM SIGKDD International Workshop on Urban Computing. Beijing, China, 63–70.
    Google ScholarLocate open access versionFindings
  • Quan Yuan, Gao Cong, Zongyang Ma, Aixin Sun, and Nadia Magnenat-Thalmann. 2013. Time-aware pointof-interest recommendation. In Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. Dublin, Ireland, 363–372.
    Google ScholarLocate open access versionFindings
  • Quan Yuan, Gao Cong, and Aixin Sun. 2014. Graph-based point-of-interest recommendation with geographical and temporal influences. In Proceedings of the 23rd ACM Conference on Information and Knowledge Management. Shanghai, China, 659–668.
    Google ScholarLocate open access versionFindings
  • Quan Yuan, Gao Cong, Kaiqi Zhao, Zongyang Ma, and Aixin Sun. 2015.
    Google ScholarFindings
  • Who, where, when and what: A nonparametric Bayesian approach to context-aware recommendation and search for Twitter users. ACM Transactions on Information Systems, accept to appear (2015).
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang and Chi-Yin Chow. 2013. iGSLR: Personalized geo-social location recommendation - a kernel density estimation approach. In Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando, FL, 344–353.
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang and Chi-Yin Chow. 2015a. CoRe: Exploiting the personalized influence of two-dimensional geographic coordinates for location recommendations. Information Sciences 293 (2015), 163–181.
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang and Chi-Yin Chow. 2015b. GeoSoCa: Exploiting geographical, social and categorical correlations for point-of-interest recommendations. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, accepted to appear. Santiago, Chile.
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang and Chi-Yin Chow. 2015c. TICRec: A probabilistic framework to utilize temporal influence correlations for time-aware location recommendations. IEEE Transactions on Services Computing, accepted to appear (2015).
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang, Chi-Yin Chow, and Yanhua Li. 2014a. iGeoRec: A personalized and efficient geographical location recommendation framework. IEEE Transactions on Services Computing, accepted to appear (2014).
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang, Chi-Yin Chow, and Yanhua Li. 2014b. LORE: Exploiting sequential influence for location recommendations. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Dallas, TX, 103–112.
    Google ScholarLocate open access versionFindings
  • Jia-Dong Zhang, Gabriel Ghinita, and Chi-Yin Chow. 2014c. Differentially private location recommendations in geosocial networks. In Proceedings of the 15th IEEE International Conference on Mobile Data Management. Brisbane, Australia, 59–68.
    Google ScholarLocate open access versionFindings
  • Yi-Liang Zhao, Liqiang Nie, Xiangyu Wang, and Tat-Seng Chua. 2014. Personalized recommendations of locally interesting venues to tourists via cross-Region community matching. ACM Transactions on Intelligent Systems and Technology 5, 3 (2014), 50:1–50:26.
    Google ScholarLocate open access versionFindings
  • Vincent W. Zheng, Yu Zheng, Xing Xie, and Qiang Yang. 2012. Towards mobile intelligence: Learning from GPS history data for collaborative recommendation. Artificial Intelligence 184-185 (2012), 17–37.
    Google ScholarLocate open access versionFindings
  • Yu Zheng, Lizhu Zhang, Zhengxin Ma, Xing Xie, and Wei-Ying Ma. 2011. Recommending friends and locations based on individual location history. ACM Transactions on the Web 5, 1 (2011), 5:1–5:44.
    Google ScholarLocate open access versionFindings
  • Yan-Tao Zheng, Zheng-Jun Zha, and Tat-Seng Chua. 2012. Mining travel patterns from geotagged photos. ACM Transactions on Intelligent Systems and Technology 3, 3 (2012), 56:1–56:18.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科