Collaborative Filtering Meets Mobile Recommendation: A User-Centered Approach
By Vincent Wenchen Zheng, Bin Cao, Yu Zheng, Xing Xie, Qiang Yang. AAAI Conference on Artificial Intelligence, 2010
383 citations recorded by the source corpus.
With the increasing popularity of location tracking services such as GPS, more and more mobile data are being accumulated. Based on such data, a potentially useful service is to make timely and targeted recommendations for users on places where they might be interested to go and activities that they are likely to conduct. For example, a user arriving in Beijing might wonder where to visit and what she can do around the Forbidden City. A key challenge for such recommendation problems is that the data we have on each individual user might be very limited, while to make useful and accurate recommendations, we need extensive annotated location and activity information from user trace data. In this paper, we present a new approach, known as user-centered collaborative location and activity filtering (UCLAF), to pull many users’ data together and apply collaborative filtering to find like-minded users and like-patterned activities at different locations. We model the userlocation- activity relations with a tensor representation, and propose a regularized tensor and matrix decomposition solution which can better address the sparse data problem in mobile information retrieval. We empirically evaluate UCLAF using a real-world GPS dataset collected from 164 users over 2.5 years, and showed that our system can outperform several state-of-the-art solutions to the problem.
Subfields: Computer Networks and Communications, Information Systems, Transportation
View Paper: https://www.semanticscholar.org/paper/5751765095b4ba4a675ca9fb111c94fd87782871
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
In Information Systems
In Transportation
Citations in the corpus
- Ieee Transactions on Knowledge and Data Engineering 1 towards Bayesian Deep Learning: a Framework and Some Existing Methods (neutral): “…example, to achieve high accuracy in recommender systems (RS) [1], [39], [40], [50], [67], we need to fully understand the content of the items (e.g., documents and movies) [46], analyze the profile and preferences of users [70], [73], and evaluate the similarity among the users [3], [11], [29].”
- Urban Computing: Concepts, Methodologies, and Applications (2014, methodology): “Y. Zheng, Y. Chen, X. Xie, and W. Y. Ma. 2009a. GeoLife2.”
- Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts (2016, methodology): “As another popular method, Tensor Factorization (TF) has been successfully applied for time-aware recommendation (Xiong et al. 2010) as well as modeling spatial temporal information (Zheng et al. 2010a; Bahadori, Yu, and Liu 2014).”
- Trajectory Data Mining (2015, methodology): “[139][137] extend the generic location-activity research [138] into a personalized one, by adding a user dimension into the original location-activity matrix.”
- User Conditional Hashtag Prediction for Images (2015, background): “Many works have incorporated user modeling into machine learning methods for various applications, for example by considering tensor factorisations for recommendation using music tags [13], web pages [10], using age and gender [4], location [21] and time [19].”
- Fused Matrix Factorization with Geographical and Social Influence in Location-Based Social Networks (2012, methodology): “One line of research is to solve POI recommendation based on the extracted stay points from GPS trajectory logs of several hundred monitored users (Zheng et al. 2009; 2010a; 2010b; Leung, Lee, and Lee 2011; Zheng and Xie 2011; Cao, Cong, and Jensen 2010).”
- Diagnosing New York city's noises with ubiquitous data (2014, methodology): “[21][23][28][29] used a context-aware tensor decomposition incorporating additional information, such as the activityactivity correlation and geographical features of a location, to conduct different kinds of recommendations.”
- iBAT: detecting anomalous taxi trajectories from GPS traces (2011, background): “Gathering and analyzing the large-scale GPS traces have provided us a great opportunity to reveal the hidden “facts” about the city dynamics and human behaviors, enabling diverse innovative applications [22, 13, 18, 30, 26, 21, 23, 28, 24].”
- Exploiting geographical influence for collaborative point-of-interest recommendation (2011, methodology): “In LBSNs, a POI recommendation service, aiming at recommending new POIs to users in order to help them explore new places and know their cities better, is an essential function that has received a lot of research momentum recently [25, 26].”
- All-at-once Optimization for Coupled Matrix and Tensor Factorizations (2011, methodology): “Similarly, coupled analysis of matrices and tensors has been a topic of interest in the areas of community detection [22], collaborative filtering [36], and chemometrics [30].”
- Rank-GeoFM: A Ranking based Geographical Factorization Method for Point of Interest Recommendation (2015, methodology): “• UCLAF: UCLAF is a PARAFAC-based tensor decomposition model, originally proposed to recommend locations and activities with user-location-activity tensor data [27], where Laplician regularization terms are imposed on decompositions to incorporate extra information.”
- A Survey on Bayesian Deep Learning (2016, background): “A highly accurate recommender system requires (1) thorough understanding of item content (e.g., content in documents and movies) [85], (2) careful analysis of users’ profiles/preferences [126, 130, 134], and (3) proper evaluation of similarity among users [3, 12, 46, 109].”
- GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory (2010, background): “[5] Wenchen Zheng, Bin Cao, Yu Zheng, Xing Xie, Qiang Yang.”