Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788893025> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2788893025 abstract "Although latent factor models (e.g., matrix factorization) achieve good accuracy in rating prediction, they suffer from several problems including cold-start, non-transparency, and suboptimal recommendation for local users or items. In this paper, we employ textual review information with ratings to tackle these limitations. Firstly, we apply a proposed aspect-aware topic model (ATM) on the review text to model user preferences and item features from different aspects, and estimate the aspect importance of a user towards an item. The aspect importance is then integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings. In particular, ALFM introduces a weighted matrix to associate those latent factors with the same set of aspects discovered by ATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, an aspect rating is weighted by an aspect importance, which is dependent on the targeted user's preferences and targeted item's features. Therefore, it is expected that the proposed method can model a user's preferences on an item more accurately for each user-item pair locally. Comprehensive experimental studies have been conducted on 19 datasets from Amazon and Yelp 2017 Challenge dataset. Results show that our method achieves significant improvement compared with strong baseline methods, especially for users with only few ratings. Moreover, our model could interpret the recommendation results in depth." @default.
- W2788893025 created "2018-03-06" @default.
- W2788893025 creator A5016415049 @default.
- W2788893025 creator A5057820981 @default.
- W2788893025 creator A5068843001 @default.
- W2788893025 creator A5072424476 @default.
- W2788893025 date "2018-01-01" @default.
- W2788893025 modified "2023-10-17" @default.
- W2788893025 title "Aspect-Aware Latent Factor Model" @default.
- W2788893025 cites W193333623 @default.
- W2788893025 cites W2001082470 @default.
- W2788893025 cites W2028988057 @default.
- W2788893025 cites W2030385985 @default.
- W2788893025 cites W2054141820 @default.
- W2788893025 cites W2061212083 @default.
- W2788893025 cites W2061873838 @default.
- W2788893025 cites W2116959421 @default.
- W2788893025 cites W2124065797 @default.
- W2788893025 cites W2132481658 @default.
- W2788893025 cites W2142972908 @default.
- W2788893025 cites W2144487656 @default.
- W2788893025 cites W2336920772 @default.
- W2788893025 cites W2481439837 @default.
- W2788893025 cites W2511264801 @default.
- W2788893025 cites W2512971201 @default.
- W2788893025 cites W2514530580 @default.
- W2788893025 cites W2605350416 @default.
- W2788893025 cites W2606749808 @default.
- W2788893025 cites W2740276176 @default.
- W2788893025 cites W2767724106 @default.
- W2788893025 cites W2788730650 @default.
- W2788893025 cites W2963655167 @default.
- W2788893025 cites W39762900 @default.
- W2788893025 cites W4301312111 @default.
- W2788893025 doi "https://doi.org/10.1145/3178876.3186145" @default.
- W2788893025 hasPublicationYear "2018" @default.
- W2788893025 type Work @default.
- W2788893025 sameAs 2788893025 @default.
- W2788893025 citedByCount "181" @default.
- W2788893025 countsByYear W27888930252018 @default.
- W2788893025 countsByYear W27888930252019 @default.
- W2788893025 countsByYear W27888930252020 @default.
- W2788893025 countsByYear W27888930252021 @default.
- W2788893025 countsByYear W27888930252022 @default.
- W2788893025 countsByYear W27888930252023 @default.
- W2788893025 crossrefType "proceedings-article" @default.
- W2788893025 hasAuthorship W2788893025A5016415049 @default.
- W2788893025 hasAuthorship W2788893025A5057820981 @default.
- W2788893025 hasAuthorship W2788893025A5068843001 @default.
- W2788893025 hasAuthorship W2788893025A5072424476 @default.
- W2788893025 hasBestOaLocation W27888930251 @default.
- W2788893025 hasConcept C10879293 @default.
- W2788893025 hasConcept C119857082 @default.
- W2788893025 hasConcept C121332964 @default.
- W2788893025 hasConcept C124101348 @default.
- W2788893025 hasConcept C154945302 @default.
- W2788893025 hasConcept C158693339 @default.
- W2788893025 hasConcept C177264268 @default.
- W2788893025 hasConcept C199360897 @default.
- W2788893025 hasConcept C23123220 @default.
- W2788893025 hasConcept C2781039887 @default.
- W2788893025 hasConcept C2781067378 @default.
- W2788893025 hasConcept C41008148 @default.
- W2788893025 hasConcept C42355184 @default.
- W2788893025 hasConcept C62520636 @default.
- W2788893025 hasConceptScore W2788893025C10879293 @default.
- W2788893025 hasConceptScore W2788893025C119857082 @default.
- W2788893025 hasConceptScore W2788893025C121332964 @default.
- W2788893025 hasConceptScore W2788893025C124101348 @default.
- W2788893025 hasConceptScore W2788893025C154945302 @default.
- W2788893025 hasConceptScore W2788893025C158693339 @default.
- W2788893025 hasConceptScore W2788893025C177264268 @default.
- W2788893025 hasConceptScore W2788893025C199360897 @default.
- W2788893025 hasConceptScore W2788893025C23123220 @default.
- W2788893025 hasConceptScore W2788893025C2781039887 @default.
- W2788893025 hasConceptScore W2788893025C2781067378 @default.
- W2788893025 hasConceptScore W2788893025C41008148 @default.
- W2788893025 hasConceptScore W2788893025C42355184 @default.
- W2788893025 hasConceptScore W2788893025C62520636 @default.
- W2788893025 hasLocation W27888930251 @default.
- W2788893025 hasLocation W27888930252 @default.
- W2788893025 hasOpenAccess W2788893025 @default.
- W2788893025 hasPrimaryLocation W27888930251 @default.
- W2788893025 hasRelatedWork W2605281151 @default.
- W2788893025 hasRelatedWork W3006943036 @default.
- W2788893025 hasRelatedWork W3012234327 @default.
- W2788893025 hasRelatedWork W3119715496 @default.
- W2788893025 hasRelatedWork W3191046242 @default.
- W2788893025 hasRelatedWork W3203961807 @default.
- W2788893025 hasRelatedWork W4205364923 @default.
- W2788893025 hasRelatedWork W4206534706 @default.
- W2788893025 hasRelatedWork W4229079080 @default.
- W2788893025 hasRelatedWork W4294031299 @default.
- W2788893025 isParatext "false" @default.
- W2788893025 isRetracted "false" @default.
- W2788893025 magId "2788893025" @default.
- W2788893025 workType "article" @default.