Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912057614> ?p ?o ?g. }
- W2912057614 endingPage "23" @default.
- W2912057614 startingPage "1" @default.
- W2912057614 abstract "User interactions can be considered to constitute different feedback channels, for example, view, click, like or follow, that provide implicit information on users’ preferences. Each implicit feedback channel typically carries a unary, positive-only signal that can be exploited by collaborative filtering models to generate lists of personalized recommendations. This article investigates how a learning-to-rank recommender system can best take advantage of implicit feedback signals from multiple channels. We focus on Factorization Machines (FMs) with Bayesian Personalized Ranking (BPR), a pairwise learning-to-rank method, that allows us to experiment with different forms of exploitation. We perform extensive experiments on three datasets with multiple types of feedback to arrive at a series of insights. We compare conventional, direct integration of feedback types with our proposed method, which exploits multiple feedback channels during the sampling process of training. We refer to our method as multi-channel sampling. Our results show that multi-channel sampling outperforms conventional integration, and that sampling with the relative “level” of feedback is always superior to a level-blind sampling approach. We evaluate our method experimentally on three datasets in different domains and observe that with our multi-channel sampler the accuracy of recommendations can be improved considerably compared to the state-of-the-art models. Further experiments reveal that the appropriate sampling method depends on particular properties of datasets such as popularity skewness." @default.
- W2912057614 created "2019-02-21" @default.
- W2912057614 creator A5037486611 @default.
- W2912057614 creator A5056272341 @default.
- W2912057614 creator A5068226863 @default.
- W2912057614 creator A5086566231 @default.
- W2912057614 date "2019-02-13" @default.
- W2912057614 modified "2023-09-24" @default.
- W2912057614 title "Top-N Recommendation with Multi-Channel Positive Feedback using Factorization Machines" @default.
- W2912057614 cites W1412447802 @default.
- W2912057614 cites W163868085 @default.
- W2912057614 cites W1866019567 @default.
- W2912057614 cites W1969147614 @default.
- W2912057614 cites W1973616272 @default.
- W2912057614 cites W1976999215 @default.
- W2912057614 cites W1981844236 @default.
- W2912057614 cites W1992665562 @default.
- W2912057614 cites W1994389483 @default.
- W2912057614 cites W2002834872 @default.
- W2912057614 cites W2008886893 @default.
- W2912057614 cites W2031485704 @default.
- W2912057614 cites W2054470031 @default.
- W2912057614 cites W2074290495 @default.
- W2912057614 cites W2094286023 @default.
- W2912057614 cites W2101409192 @default.
- W2912057614 cites W2102937240 @default.
- W2912057614 cites W2116838569 @default.
- W2912057614 cites W2164166952 @default.
- W2912057614 cites W2295739661 @default.
- W2912057614 cites W2415326922 @default.
- W2912057614 cites W2509235963 @default.
- W2912057614 cites W2517217469 @default.
- W2912057614 cites W2517388038 @default.
- W2912057614 doi "https://doi.org/10.1145/3291756" @default.
- W2912057614 hasPublicationYear "2019" @default.
- W2912057614 type Work @default.
- W2912057614 sameAs 2912057614 @default.
- W2912057614 citedByCount "15" @default.
- W2912057614 countsByYear W29120576142019 @default.
- W2912057614 countsByYear W29120576142020 @default.
- W2912057614 countsByYear W29120576142021 @default.
- W2912057614 countsByYear W29120576142023 @default.
- W2912057614 crossrefType "journal-article" @default.
- W2912057614 hasAuthorship W2912057614A5037486611 @default.
- W2912057614 hasAuthorship W2912057614A5056272341 @default.
- W2912057614 hasAuthorship W2912057614A5068226863 @default.
- W2912057614 hasAuthorship W2912057614A5086566231 @default.
- W2912057614 hasConcept C107673813 @default.
- W2912057614 hasConcept C111919701 @default.
- W2912057614 hasConcept C114614502 @default.
- W2912057614 hasConcept C119857082 @default.
- W2912057614 hasConcept C124101348 @default.
- W2912057614 hasConcept C127162648 @default.
- W2912057614 hasConcept C140779682 @default.
- W2912057614 hasConcept C154945302 @default.
- W2912057614 hasConcept C164226766 @default.
- W2912057614 hasConcept C189430467 @default.
- W2912057614 hasConcept C21569690 @default.
- W2912057614 hasConcept C31258907 @default.
- W2912057614 hasConcept C33923547 @default.
- W2912057614 hasConcept C41008148 @default.
- W2912057614 hasConcept C557471498 @default.
- W2912057614 hasConcept C73602740 @default.
- W2912057614 hasConcept C76155785 @default.
- W2912057614 hasConcept C86037889 @default.
- W2912057614 hasConcept C94915269 @default.
- W2912057614 hasConcept C98045186 @default.
- W2912057614 hasConceptScore W2912057614C107673813 @default.
- W2912057614 hasConceptScore W2912057614C111919701 @default.
- W2912057614 hasConceptScore W2912057614C114614502 @default.
- W2912057614 hasConceptScore W2912057614C119857082 @default.
- W2912057614 hasConceptScore W2912057614C124101348 @default.
- W2912057614 hasConceptScore W2912057614C127162648 @default.
- W2912057614 hasConceptScore W2912057614C140779682 @default.
- W2912057614 hasConceptScore W2912057614C154945302 @default.
- W2912057614 hasConceptScore W2912057614C164226766 @default.
- W2912057614 hasConceptScore W2912057614C189430467 @default.
- W2912057614 hasConceptScore W2912057614C21569690 @default.
- W2912057614 hasConceptScore W2912057614C31258907 @default.
- W2912057614 hasConceptScore W2912057614C33923547 @default.
- W2912057614 hasConceptScore W2912057614C41008148 @default.
- W2912057614 hasConceptScore W2912057614C557471498 @default.
- W2912057614 hasConceptScore W2912057614C73602740 @default.
- W2912057614 hasConceptScore W2912057614C76155785 @default.
- W2912057614 hasConceptScore W2912057614C86037889 @default.
- W2912057614 hasConceptScore W2912057614C94915269 @default.
- W2912057614 hasConceptScore W2912057614C98045186 @default.
- W2912057614 hasIssue "2" @default.
- W2912057614 hasLocation W29120576141 @default.
- W2912057614 hasOpenAccess W2912057614 @default.
- W2912057614 hasPrimaryLocation W29120576141 @default.
- W2912057614 hasRelatedWork W1786507113 @default.
- W2912057614 hasRelatedWork W1991055526 @default.
- W2912057614 hasRelatedWork W2104465941 @default.
- W2912057614 hasRelatedWork W2293317945 @default.
- W2912057614 hasRelatedWork W2364400397 @default.
- W2912057614 hasRelatedWork W2807848202 @default.
- W2912057614 hasRelatedWork W2957250813 @default.