Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310344268> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4310344268 endingPage "103169" @default.
- W4310344268 startingPage "103169" @default.
- W4310344268 abstract "Point-of-interest (POI) recommendation helps users quickly filter out irrelevant POI by considering the spatio-temporal factor. In this paper, we address the problem of check-in preference modeling in POI recommendation, and propose a novel POI recommendation method that depicts user preference by constructing unique hypersphere interest model for each user. Different from existing works, we have done three innovative work. (1) We build a check-in graph and adopt DeepWalk algorithm to learn POI embedding, further aggregating them to obtain a hypersphere interest space with an interest center and interest radius. (2) We established a stacked neural network module by a bidirectional LSTM, a self-attention and a memory network, to grasp memory features contained in check-in histories. (3) We proposed a novel candidate POI filter method that updates ranking score by evaluating the Euclidean distance between the vectors of candidate POI and interest center. We evaluate the performance of our method on the four real-world check-in datasets constructed from Foursquare. The comparison between our method and six baselines demonstrates the outstanding performance on various measurements. Compared to the best baseline method, our method achieves about 50% performance improvement on NDCG. In terms of MRR, Precision and Recall, our method achieves about 37%, 21% and 9% performance improvement over the best baseline method. Further ablation experiments verified the importance and effectiveness of the hypersphere interest model, as removing this component caused significant performance degradation." @default.
- W4310344268 created "2022-12-09" @default.
- W4310344268 creator A5050020259 @default.
- W4310344268 creator A5060760048 @default.
- W4310344268 date "2023-03-01" @default.
- W4310344268 modified "2023-10-18" @default.
- W4310344268 title "Mapping user interest into hyper-spherical space: A novel POI recommendation method" @default.
- W4310344268 cites W2593485853 @default.
- W4310344268 cites W2607776459 @default.
- W4310344268 cites W2643577078 @default.
- W4310344268 cites W2765651856 @default.
- W4310344268 cites W2810223544 @default.
- W4310344268 cites W2888233556 @default.
- W4310344268 cites W2890552332 @default.
- W4310344268 cites W2921983621 @default.
- W4310344268 cites W2930456628 @default.
- W4310344268 cites W2936831540 @default.
- W4310344268 cites W2966699521 @default.
- W4310344268 cites W2969332039 @default.
- W4310344268 cites W3007094428 @default.
- W4310344268 cites W3023706892 @default.
- W4310344268 cites W3040377978 @default.
- W4310344268 cites W3044498809 @default.
- W4310344268 cites W3045111859 @default.
- W4310344268 cites W3089822892 @default.
- W4310344268 cites W3118661748 @default.
- W4310344268 cites W3127158617 @default.
- W4310344268 cites W3127961343 @default.
- W4310344268 cites W3129523363 @default.
- W4310344268 cites W3131806423 @default.
- W4310344268 cites W3133053751 @default.
- W4310344268 cites W3158111568 @default.
- W4310344268 cites W3161070260 @default.
- W4310344268 cites W3163426640 @default.
- W4310344268 cites W3175031862 @default.
- W4310344268 cites W3194847385 @default.
- W4310344268 cites W3205043674 @default.
- W4310344268 cites W4211195978 @default.
- W4310344268 cites W4211255280 @default.
- W4310344268 doi "https://doi.org/10.1016/j.ipm.2022.103169" @default.
- W4310344268 hasPublicationYear "2023" @default.
- W4310344268 type Work @default.
- W4310344268 citedByCount "5" @default.
- W4310344268 countsByYear W43103442682023 @default.
- W4310344268 crossrefType "journal-article" @default.
- W4310344268 hasAuthorship W4310344268A5050020259 @default.
- W4310344268 hasAuthorship W4310344268A5060760048 @default.
- W4310344268 hasConcept C119857082 @default.
- W4310344268 hasConcept C124101348 @default.
- W4310344268 hasConcept C150140777 @default.
- W4310344268 hasConcept C154945302 @default.
- W4310344268 hasConcept C189430467 @default.
- W4310344268 hasConcept C23123220 @default.
- W4310344268 hasConcept C2776562905 @default.
- W4310344268 hasConcept C41008148 @default.
- W4310344268 hasConceptScore W4310344268C119857082 @default.
- W4310344268 hasConceptScore W4310344268C124101348 @default.
- W4310344268 hasConceptScore W4310344268C150140777 @default.
- W4310344268 hasConceptScore W4310344268C154945302 @default.
- W4310344268 hasConceptScore W4310344268C189430467 @default.
- W4310344268 hasConceptScore W4310344268C23123220 @default.
- W4310344268 hasConceptScore W4310344268C2776562905 @default.
- W4310344268 hasConceptScore W4310344268C41008148 @default.
- W4310344268 hasFunder F4320321001 @default.
- W4310344268 hasIssue "2" @default.
- W4310344268 hasLocation W43103442681 @default.
- W4310344268 hasOpenAccess W4310344268 @default.
- W4310344268 hasPrimaryLocation W43103442681 @default.
- W4310344268 hasRelatedWork W1982912006 @default.
- W4310344268 hasRelatedWork W2089586275 @default.
- W4310344268 hasRelatedWork W2118564381 @default.
- W4310344268 hasRelatedWork W2138279922 @default.
- W4310344268 hasRelatedWork W2384888906 @default.
- W4310344268 hasRelatedWork W2905463021 @default.
- W4310344268 hasRelatedWork W2961085424 @default.
- W4310344268 hasRelatedWork W4295894805 @default.
- W4310344268 hasRelatedWork W4306674287 @default.
- W4310344268 hasRelatedWork W4224009465 @default.
- W4310344268 hasVolume "60" @default.
- W4310344268 isParatext "false" @default.
- W4310344268 isRetracted "false" @default.
- W4310344268 workType "article" @default.