Subprofile aware diversification of recommendations

dc.check.embargoformatEmbargo not applicable (If you have not submitted an e-thesis or do not want to request an embargo)en
dc.check.infoNot applicableen
dc.check.opt-outNot applicableen
dc.check.reasonNot applicableen
dc.check.typeNo Embargo Required
dc.contributor.advisorBridge, Derek G.en
dc.contributor.advisorBrown, Kenneth N.en
dc.contributor.authorKaya, Mesut
dc.contributor.funderScience Foundation Irelanden
dc.description.abstractA user of a recommender system is more likely to be satisfied by one or more of the recommendations if each individual recommendation is relevant to her but additionally if the set of recommendations is diverse. The most common approach to recommendation diversification uses re-ranking: the recommender system scores a set of candidate items for relevance to the user; it then re-ranks the candidates so that the subset that it will recommend achieves a balance between relevance and diversity. Ordinarily, we expect a trade-off between relevance and diversity: the diversity of the set of recommendations increases by including items that have lower relevance scores but which are different from the items already in the set. In early work, the diversity of a set of recommendations was given by an aggregate of their distances from one another, according to some semantic distance metric defined on item features such as movie genres. More recent intent-aware diversification methods formulate diversity in terms of coverage and relevance of aspects. The aspects are most commonly defined in terms of item features. By trying to ensure that the aspects of a set of recommended items cover the aspects of the items in the user’s profile, the level of diversity is more personalized. In offline experiments on pre-collected datasets, intent-aware diversification using item features as aspects sometimes defies the relevance/diversity trade-off: there are configurations in which the recommendations exhibits increases in both relevance and diversity. In this thesis, we present a new form of intent-aware diversification, which we call SPAD (Subprofile-Aware Diversification). In SPAD and its variants, the aspects are not item features; they are subprofiles of the user’s profile. We present a number of different ways to extract subprofiles from a user’s profile. None of them is defined in terms of item features. Therefore, SPAD and its variants are useful even in domains where item features are not available or are of low quality. On several pre-collected datasets from different domains (movies, music, books, social network), we compare SPAD and its variants to intent-aware methods in which aspects are item features. We also compare them to calibrated recommendations, which are related to intent-aware recommendations. We find on these datasets that SPAD and its variants suffer even less from the relevance/diversity trade-off: across all datasets, they increase both relevance and diversity for even more configurations than other approaches. Moreover, we apply SPAD to the task of automatic playlist continuation (APC), in which relevance is the main goal, not diversity. We find that, even when applied to the task of APC, SPAD increases both relevance and diversity.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Version
dc.identifier.citationKaya, M. 2019. Subprofile aware diversification of recommendations. PhD Thesis, University College Cork.en
dc.publisherUniversity College Corken
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.rights© 2019, Mesut Kaya.en
dc.subjectRecommender systemsen
dc.subjectIntent-aware diversificationen
dc.titleSubprofile aware diversification of recommendationsen
dc.typeDoctoral thesisen
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
1.42 MB
Adobe Portable Document Format
Full Text E-thesis
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
5.62 KB
Item-specific license agreed upon to submission