Collaborative location and activity recommendations with GPS history data

By Vincent Wenchen Zheng, Yu Zheng, Xing Xie, Qiang Yang. The Web Conference, 2010

730 citations recorded by the source corpus.

Subfields: Geography, Planning and Development, Transportation, Signal Processing

View Paper: https://www.semanticscholar.org/paper/7d38e6dfcfaf7a408f3d04f3c33d49381b7345c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Geography, Planning and Development

1. Yu Zheng
2. Xing Xie
3. Mohamed F. Mokbel
4. Jie Bao
5. Vincent Wenchen Zheng
6. Qiang Yang
7. Hui Xiong
8. Wei-Ying Ma

In Transportation

1. Yu Zheng
2. Xing Xie
3. Jie Bao
4. Mohamed F. Mokbel
5. Irwin King
6. Ouri Wolfson
7. Michael R. Lyu
8. Licia Capra

In Signal Processing

1. Yu Zheng
2. Xing Xie
3. Jie Bao
4. Mohamed F. Mokbel
5. Qiang Yang
6. Ouri Wolfson
7. Licia Capra
8. David Wilkie

Citations in the corpus

• Explaining Recommendations: Design and Evaluation (2015, background): “Ongoing research has been studying the impact of recommendations based on people’s relationships in online social networks [51, 58, 85], and geographic information [7, 64, 89], in addition to more classical recommendation algorithms.”
• Learning travel recommendations from user-generated GPS traces (2011, neutral): “…real-world location histories, some recommender systems, such as Geowhiz [Horozov et al. 2006], CityVoyager [Takeuchi and Sugimoto 2006], and GeoLife [Zheng et al. 2009a; Li et al. 2008; Zheng et al. 2010b], have been designed to recommend geographic locations like shops or restaurants to users.”
• LARS: A Location-Aware Recommender System (2012, background): “The spatial activity recommendation system [29] mines GPS trajectory data with embedded user-provided tags in order t o detect interesting activities located in a city (e.”
• Understanding urban human activity and mobility patterns using large-scale location-based data from online social media (2013, background): “formation provided by the location-based data which has already enabled many novel applications such as recommendation system for physical locations (or activity) [1, 2] or recommending potential customers or friend [3, 4]; and determining popular travel routes in a city [5].”
• Trajectory Data Mining (2015, methodology): “[138] proposed a coupled matrix factorization method to enable locationactivity recommendation, using activity-tagged GPS trajectories.”
• Event labeling combining ensemble detectors and background knowledge (2014, methodology): “In the next phase we compute the weight of the event by a method similar to [56] where search results count is used as a criterion for extraction the correlation between two terms (e.”
• GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory (2010, background): “Refer to papers [5, 6] for details.”
• Where You Like to Go Next: Successive Point-of-Interest Recommendation (2013, positive): “Many collaborative filter-ing algorithms, e.g., collective matrix factorization [Zheng et al. , 2010a], tensor factorization [Zheng et al. , 2010b], memory-based collaborative location model (CLM) [Leung et al. , 2011], etc., have been proposed to solve it and deemed the locations as items in…”
• Recommender Systems (2012, background): “3 Accurate recommendation asks for both the high predictability of human movements [49,50] and quantitative way to define similarities between locations and people [51,52].”
• Measuring Large-Scale Social Networks with High Resolution (2014, methodology): “From the raw location data we can extract stop locations as groups of locations clustered within distance D and time T [162–165].”
• Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts (2016, methodology): “2010a) and collective matrix factorization (Zheng et al. 2010b).”
• Location-based and preference-aware recommendation using sparse geo-social networking data (2012, methodology): “Though [15, 24] applied Single Value Decomposition to a user-location matrix so as to reduce the data sparseness problem to some extent, this method does not work well when there is no overlap between users’ location histories.”
• A Survey on Ambient-Assisted Living Tools for Older Adults (2013, background): “tive learning [93], and transfer learning [94], [95] have also been applied to the sparsely labeled human activity data.”
• Friendship and mobility: user movement in location-based social networks (2011, background): “Knowledge o f users’ locations can help improve large scale systems, such as clou d omputing, content-based delivery networks [21], and locatio n-based recommendations [13, 32, 33].”
• Activity-Based Human Mobility Patterns Inferred from Mobile Phone Data: A Case Study of Singapore (2017, background): “CDRs are not as structured as traditional travel survey data which contains location and time information for meaningful activity destinations, or as precise as GPS data which provides higher frequency and accuracy [18].”
• Recommendations in location-based social networks: a survey (2015, methodology): “12 Collaborative location-activity leaning model [127]”