Exploiting Geographical Neighborhood Characteristics for Location Recommendation

By Yong Liu, Wei Wei, Aixin Sun, Chunyan Miao. International Conference on Information and Knowledge Management, 2014

355 citations recorded by the source corpus.

Geographical characteristics derived from the historical check-in data have been reported effective in improving location recommendation accuracy. However, previous studies mainly exploit geographical characteristics from a user's perspective, via modeling the geographical distribution of each individual user's check-ins. In this paper, we are interested in exploiting geographical characteristics from a location perspective, by modeling the geographical neighborhood of a location. The neighborhood is modeled at two levels: the instance-level neighborhood defined by a few nearest neighbors of the location, and the region-level neighborhood for the geographical region where the location exists. We propose a novel recommendation approach, namely Instance-Region Neighborhood Matrix Factorization (IRenMF), which exploits two levels of geographical neighborhood characteristics: a) instance-level characteristics, i.e., nearest neighboring locations tend to share more similar user preferences; and b) region-level characteristics, i.e., locations in the same geographical region may share similar user preferences. In IRenMF, the two levels of geographical characteristics are naturally incorporated into the learning of latent features of users and locations, so that IRenMF predicts users' preferences on locations more accurately. Extensive experiments on the real data collected from Gowalla, a popular LBSN, demonstrate the effectiveness and advantages of our approach.

Subfields: Information Systems, Transportation, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ec8977e127c1bd1ffce46bc0f2532f420e69e97f

How researchers see this paper

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

In Information Systems

1. Qiang Liu
2. Yingtao Luo
3. Zhaocheng Liu
4. Liang Wang
5. Carl Yang
6. Tien-Ping Tan
7. Quan Yuan
8. Jiawei Han

In Transportation

1. Liang Wang
2. Tien-Ping Tan
3. Quan Yuan
4. Jiawei Han
5. Qiang Liu
6. Shu Wu

In Signal Processing

1. Liang Wang
2. Tien-Ping Tan
3. Quan Yuan
4. Jiawei Han
5. Qiang Liu
6. Shu Wu
7. Yu Zheng
8. Charu C. Aggarwal

Citations in the corpus

• Bridging Collaborative Filtering and Semi-Supervised Learning: A Neural Approach for POI Recommendation (2017, methodology): “We compare PACE with the following POI recommendation algorithms: • IRenMF [28]: it models geographical inƒuence by incorporating neighboring characteristics into weighted MF.”
• Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts (2016, background): “Recently, some work considers users’ interest to the neighborhood of the destination location (Liu et al. 2014; Li et al. 2015).”
• GeoSoCa: Exploiting Geographical, Social and Categorical Correlations for Point-of-Interest Recommendations (2015, neutral): “Another way is to apply the geographical latent factor or topic models to derive latent features of regions or POIs [7, 8, 12, 16, 25, 26].”
• STAN: Spatio-Temporal Attention Network for Next Location Recommendation (2021, background): “Meanwhile, such a system can also provide users with the convenience to decide where to go and how to plan the day, based on previous visits as well as current status [5, 7, 9, 23, 41].”