Brief papersReal-time event embedding for POI recommendation
Introduction
In recent years, social networking is widespread growing throughout the world. According to the statistics revealed on Statista,1 more and more people tend to share their daily life with friends and family, which has become a city phenomenon. Several famous location-based social networks (LBSNs), such as Facebook and Twitter, provide geo-tagging (check-in) services, in which users can share their activities and locations (Fig. 1). For the fast grown-up of LBSNs, point-of-interest (POI) recommendation has become a hot issue to help users discover interesting locations by mining users’ preference from a large number of check-in behaviors. However, POI recommendation is challenging as the number of POIs is often so large compared to the number of POIs visited by an individual, resulting in a very sparse user-POI matrix. Many researchers focus on studying sequential check-in to learn users’ preference [30], [4], [31], while ignoring the POI information. Recent works show integrating textual information on POI can improve the performance of POI recommendation. For instance, Liu et al. [13] recommended POIs by mining their textual information to topics with Latent Dirichlet allocation (LDA). [26] mined latent features of POIs with CNN. While those works mostly focus on embedding intrinsic information of POI, two major factors are being ignored. One is the factor of time. In a scenario that given the user and the current time, we want to recommend a POI which is most suitable for him/her at that time. The other one is the factor of event. We assume that event will directly affect users’ desire to visit one place even though they are not supposed to visit based on their preference.
For example, a Coldplay fan who seldom has sports checks-in at a stadium because of the Coldplay concert. However, most works on POI recommender that exploit temporal characteristics do not consider the factor of event. Therefore, we are going to develop a real-time POI embedding metric that consider both intrinsic and time-aware information of POI and employ it to improve POI recommendation.
We assume that instead of eye-catching POI, users would prefer a place with an event which they are interested in. To observe the importance of discovering events, an empirical data analysis is applied to answer the following two questions: (1) how is the population of POIs behaving whether events happened or not? (2) How the posts on POIs perform with events happened? We analyze a specific POI with its geo-tagged posts in sequential days, as shown in Fig. 2. We divide days into hours and observed the (check-ins) records as well as the contents of posts. We also analyze the high occurrence of keywords from tweets which were posted on an event day, as shown in Fig. 3. We sum up with two obvious phenomena, (1) the number of check-ins apparently increase when events happened; meanwhile (2) from the content of related posts, we find that abnormal vocabs would be mentioned more frequently, hence the words with high frequency could well describe the event.
It is clear that geo-tagged posts provide immediate and direct information of events. For the above-mentioned reasons, this study proposes a real-time POI recommendation system with event detection to analyze textual information on social media. Specifically, our POI recommender consists of two major characteristics:
- 1)
Time-aware POI Information which capturing both intrinsic and time-aware information on POIs.
- 2)
Real-time Event Tracking on social media for extracting latest and highly attentive information on POIs.
For the intrinsic representation of POIs, we develop a CNN metric in mining textual description or reviews to capture intrinsic features for POIs, inspiring by [26]. Whereas for the real-time process, we construct a multimodal embedding of keyword, location and time to explore instant semantic representation of geo-tagged posts given the POI, so as to keep track of whether there are events occurring. Our recommendation system combines real-time embedding to matrix factorization.
The thesis is organized as follows: Section 2 reviews the related works; Section 3 describes the details of the proposed model. Section 4 describes the experiment to evaluate the performance of our model, and finally, Section 5 closes the thesis with conclusions and suggestions for future work.
Section snippets
Related work
In this section, we will first give a brief introduction of the current development on POI recommendation which gives us inspiration. Secondly, we will summarize current works on recommendation with temporal information to describe the importance of the temporal factor. Finally, we will describe the work we referenced in event detection.
Real-time event embedding for POI recommendation
The purpose of this study is to develop a real-time POI recommendation which considers not only intrinsic information but also instant (real-time) information of each POI based on geo-tagged posts of social media. Our system exploits geo-tagged post in social media to capture properties of a real-time event and time-aware information. We use the auxiliary information to capture intrinsic properties of POI and combine both kinds of properties in order to learn real-time POI representation. After
Experiments and results
In our study, we use the geo-tagged tweets of New York City from August 2014 – October 2014 as in [32]. After data collection and data preprocessing, all of the tweets are geo-tagged around 2994 POIs of New York City from Foursquare.4 There are 506,750 check-ins (records) in the dataset. We separate the data into 8:1:1 ratio as training data, validation data and testing data respectively. We use Keras,5 a high-level neural
Conclusion and future work
In this research, we develop a real-time POI recommender system. We propose the real-time POI embedding model to capture intrinsic information as well as ad-hoc information from social media on different time periods. The proposed approach learns POI intrinsic characteristics by using reviews and description of those POIs in Foursquare. Besides, we develop a time-aware POI embedding metric with the multimodal embedding of different types of units, which keep tracking on social media and capture
Acknowledgment
This research work was supported in part by the Ministry of Science and Technology Research Grant MOST 108-2634-F-006-006-.
Pei-Yi Hao received the B.Sc. degree in mathematics from National Cheng Kung University, Tainan, Taiwan, ROC. in 1999, and the Ph.D. degree in computer science and information engineering from same university in 2003.
He is currently an Associate Professor in the Department of Information Management, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan, R.O.C. His research interests include neural networks, fuzzy theory, pattern recognition, support vector machines, and
References (33)
- et al.
A time-based approach to effective recommender systems using implicit feedback
Expert Syst. Appl.
(2008) - et al.
Role of matrix factorization model in collaborative filtering algorithm: a survey
International Journal of Advance Foundation and Research in Computer (IJAFRC)
(2014) - et al.
Collaborative and content-based filtering for item recommendation on social bookmarking websites
- et al.
Exploring millions of footprints in location sharing services
- et al.
Where you like to go next: successive point-of-interest recommendation
- et al.
Time weight collaborative filtering
- et al.
Exploring temporal effects for location recommendation on location-based social networks
- et al.
Geo-located Twitter as the proxy for global mobility patterns
Cartogr. Geogr. Inf. Sci.
(2013) Convolutional neural networks for sentence classification
- et al.
Convolutional matrix factorization for document context-aware recommendation
Collaborative filtering with temporal dynamics
GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation
Learning geographical preferences for point-of-interest recommendation
Exploiting geographical neighborhood characteristics for location recommendation
Incorporation of efficient second-order solvers into latent factor models for accurate prediction of missing QoS data
IEEE Trans. Cybern.
An inherently non-negative latent factor model for high-dimensional and sparse matrices from industrial applications
IEEE Trans. Ind. Inf.
Cited by (0)
Pei-Yi Hao received the B.Sc. degree in mathematics from National Cheng Kung University, Tainan, Taiwan, ROC. in 1999, and the Ph.D. degree in computer science and information engineering from same university in 2003.
He is currently an Associate Professor in the Department of Information Management, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan, R.O.C. His research interests include neural networks, fuzzy theory, pattern recognition, support vector machines, and modeling of bioinformatics problems.
Weng-Hang Cheang received the M.Sc. degree in computer science and information engineering from National Cheng Kung University, Tainan, Taiwan, ROC. in 2018.
Hers research interests include POI recommendation, matrix factorization, deep learning and convolutional neural networks.
Jung-Hsien Chiang (M’92–SM’05) received the B.Sc. degree in electrical engineering from the National Taiwan Institute of Technology, Taiwan, R.O.C., and the M.S. and Ph.D. degrees in computer engineering from the University of Missouri, Columbia, in 1991 and 1995, respectively.
He is currently a Professor in the Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C. Previously, he was a Researcher in the Computer and Communication Laboratory, Industrial Technology Research Institute, the largest information technology research institute in Taiwan. His current research interests include fuzzy modeling, neural networks, pattern clustering, and modeling of bioinformatics problems.