Incorporating Spatial, Temporal, and Social Context in Recommendations for Location-Based Social Networks
Citations
1 citations
1 citations
Cites background or methods from "Incorporating Spatial, Temporal, an..."
...Some cQA research [3,16,18] leveraged the subtasks of the SemEval...
[...]
...[18], most of neural network-based models exploited supervised data....
[...]
...The analysis of users’ behavior indicates that geographical information has a higher impact on users’ preference than other contextual information [6,18,22]....
[...]
...Several methods have been applied to helpfulness prediction task including support vector regression [9,26,29], probabilistic matrix factorization [23], linear regression [13], extended tensor factorization models [16], HMM-LDA based model [18] and multi-layer neural networks [11]....
[...]
...– LMFT [18]: A method that considers a user’s recent activities as more important than their past activities and multiple visits to a location, as indicates of a stronger preference for that location....
[...]
References
9,873 citations
"Incorporating Spatial, Temporal, an..." refers background in this paper
...Given a set of users U and a set of items I , a recommender system attempts to find the subset of items that are the most relevant to each user (U j ) [20]....
[...]
5,686 citations
4,842 citations
2,946 citations
"Incorporating Spatial, Temporal, an..." refers methods in this paper
...To give credit to a larger set of coratings, we scale (1) by the Jaccard similarity index [23]...
[...]
2,922 citations