Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315706479> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4315706479 abstract "Music recommender systems are an integral part of our daily life. Recent research has seen a significant effort around black-box recommender based approaches such as Deep Reinforcement Learning (DRL). These advances have led, together with the increasing concerns around users' data collection and privacy, to a strong interest in building responsible recommender systems. A key element of a successful music recommender system is modelling how users interact with streamed content. By first understanding these interactions, insights can be drawn to enable the construction of more transparent and responsible systems. An example of these interactions is skipping behaviour, a signal that can measure users' satisfaction, dissatisfaction, or lack of interest. In this paper, we study the utility of users' historical data for the task of sequentially predicting users' skipping behaviour. To this end, we adapt DRL for this classification task, followed by a post-hoc explainability (SHAP) and ablation analysis of the input state representation. Experimental results from a real-world music streaming dataset (Spotify) demonstrate the effectiveness of our approach in this task by outperforming state-of-the-art models. A comprehensive analysis of our approach and of users' historical data reveals a temporal data leakage problem in the dataset. Our findings indicate that, overall, users' behaviour features are the most discriminative in how our proposed DRL model predicts music skips. Content and contextual features have a lesser effect. This suggests that a limited amount of user data should be collected and leveraged to predict skipping behaviour." @default.
- W4315706479 created "2023-01-12" @default.
- W4315706479 creator A5006194101 @default.
- W4315706479 creator A5044534211 @default.
- W4315706479 creator A5059100610 @default.
- W4315706479 creator A5066946791 @default.
- W4315706479 date "2023-03-19" @default.
- W4315706479 modified "2023-10-17" @default.
- W4315706479 title "Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning" @default.
- W4315706479 cites W2111621157 @default.
- W4315706479 cites W2131244036 @default.
- W4315706479 cites W2149527117 @default.
- W4315706479 cites W2606292639 @default.
- W4315706479 cites W2746553466 @default.
- W4315706479 cites W2765302304 @default.
- W4315706479 cites W2773640334 @default.
- W4315706479 cites W2787933113 @default.
- W4315706479 cites W2789399993 @default.
- W4315706479 cites W2799544270 @default.
- W4315706479 cites W2902760701 @default.
- W4315706479 cites W2911829170 @default.
- W4315706479 cites W2951274974 @default.
- W4315706479 cites W2964152520 @default.
- W4315706479 cites W2971364334 @default.
- W4315706479 cites W2972657244 @default.
- W4315706479 cites W2980951591 @default.
- W4315706479 cites W3004041021 @default.
- W4315706479 cites W3033630125 @default.
- W4315706479 cites W3044963235 @default.
- W4315706479 cites W3081484165 @default.
- W4315706479 cites W3088203142 @default.
- W4315706479 cites W3105462378 @default.
- W4315706479 cites W3117056562 @default.
- W4315706479 cites W3120178545 @default.
- W4315706479 cites W3132954077 @default.
- W4315706479 cites W3134624922 @default.
- W4315706479 cites W3209391753 @default.
- W4315706479 cites W2920845749 @default.
- W4315706479 doi "https://doi.org/10.1145/3576840.3578312" @default.
- W4315706479 hasPublicationYear "2023" @default.
- W4315706479 type Work @default.
- W4315706479 citedByCount "0" @default.
- W4315706479 crossrefType "proceedings-article" @default.
- W4315706479 hasAuthorship W4315706479A5006194101 @default.
- W4315706479 hasAuthorship W4315706479A5044534211 @default.
- W4315706479 hasAuthorship W4315706479A5059100610 @default.
- W4315706479 hasAuthorship W4315706479A5066946791 @default.
- W4315706479 hasBestOaLocation W43157064791 @default.
- W4315706479 hasConcept C108583219 @default.
- W4315706479 hasConcept C119857082 @default.
- W4315706479 hasConcept C154945302 @default.
- W4315706479 hasConcept C162324750 @default.
- W4315706479 hasConcept C187736073 @default.
- W4315706479 hasConcept C23123220 @default.
- W4315706479 hasConcept C2780451532 @default.
- W4315706479 hasConcept C41008148 @default.
- W4315706479 hasConcept C557471498 @default.
- W4315706479 hasConcept C97541855 @default.
- W4315706479 hasConcept C97931131 @default.
- W4315706479 hasConceptScore W4315706479C108583219 @default.
- W4315706479 hasConceptScore W4315706479C119857082 @default.
- W4315706479 hasConceptScore W4315706479C154945302 @default.
- W4315706479 hasConceptScore W4315706479C162324750 @default.
- W4315706479 hasConceptScore W4315706479C187736073 @default.
- W4315706479 hasConceptScore W4315706479C23123220 @default.
- W4315706479 hasConceptScore W4315706479C2780451532 @default.
- W4315706479 hasConceptScore W4315706479C41008148 @default.
- W4315706479 hasConceptScore W4315706479C557471498 @default.
- W4315706479 hasConceptScore W4315706479C97541855 @default.
- W4315706479 hasConceptScore W4315706479C97931131 @default.
- W4315706479 hasFunder F4320334627 @default.
- W4315706479 hasLocation W43157064791 @default.
- W4315706479 hasLocation W43157064792 @default.
- W4315706479 hasLocation W43157064793 @default.
- W4315706479 hasLocation W43157064794 @default.
- W4315706479 hasOpenAccess W4315706479 @default.
- W4315706479 hasPrimaryLocation W43157064791 @default.
- W4315706479 hasRelatedWork W2353457699 @default.
- W4315706479 hasRelatedWork W3014300295 @default.
- W4315706479 hasRelatedWork W3113470404 @default.
- W4315706479 hasRelatedWork W4223943233 @default.
- W4315706479 hasRelatedWork W4225161397 @default.
- W4315706479 hasRelatedWork W4297095626 @default.
- W4315706479 hasRelatedWork W4309045103 @default.
- W4315706479 hasRelatedWork W4312200629 @default.
- W4315706479 hasRelatedWork W4360585206 @default.
- W4315706479 hasRelatedWork W4364306694 @default.
- W4315706479 isParatext "false" @default.
- W4315706479 isRetracted "false" @default.
- W4315706479 workType "article" @default.