Projects per year
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.
|Title of host publication||Proceedings of the 2023 Conference on Human Information Interaction and Retrieval|
|Place of Publication||New York, NY|
|Number of pages||12|
|Publication status||E-pub ahead of print - 23 Mar 2023|
|Event||AGM SIGIR Conference on Human Information Interaction and Retrieval - Austin, United States|
Duration: 19 Mar 2023 → 23 Mar 2023
|Conference||AGM SIGIR Conference on Human Information Interaction and Retrieval|
|Abbreviated title||ACM CHIIR 2023|
|Period||19/03/23 → 23/03/23|
- user behaviour
- deep reinforcement learning
FingerprintDive into the research topics of 'Why people skip music? On predicting music skips using deep reinforcement learning'. Together they form a unique fingerprint.
- 1 Active
Doctoral Training Partnership 2018-19 University of Strathclyde | Meggetto, Francesco
Moshfeghi, Y., Revie, C., Weir, G. & Meggetto, F.
EPSRC (Engineering and Physical Sciences Research Council)
1/10/19 → 1/07/23
Project: Research Studentship - Internally Allocated
- 1 Working Paper/Preprint
Why people skip music? On predicting music skips using deep reinforcement learningMeggetto, F., Revie, C., Levine, J. & Moshfeghi, Y., 10 Jan 2023, (Submitted) Ithaca, New York, p. 1-12, 12 p.
Research output: Working paper › Working Paper/PreprintFile4 Downloads (Pure)