17,858 Hits in 6.3 sec

Order, context and popularity bias in next-song recommendations

Andreu Vall, Massimo Quadrana, Markus Schedl, Gerhard Widmer
2019 International Journal of Multimedia Information Retrieval  
song context and the song popularity, and their relation to the recommendation of playlist continuations.  ...  While the accuracy achieved in next-song recommendations is important, in this work we shift our focus toward a deeper understanding of fundamental playlist characteristics, namely the song order, the  ...  context and the song order for next-song recommendations.  ... 
doi:10.1007/s13735-019-00169-8 fatcat:pc3jefk2afanfit2ruk4ib2cma

The Importance of Song Context and Song Order in Automated Music Playlist Generation [article]

Andreu Vall, Massimo Quadrana, Markus Schedl, Gerhard Widmer
2018 arXiv   pre-print
In order to predict the next song in a playlist, some of the playlist models proposed so far consider the current and previous songs in the playlist (i.e., the song context) and possibly the order of the  ...  Our results indicate that the song context has a positive impact on the quality of next-song recommendations, even though this effect can be masked by the bias towards very popular songs.  ...  Still, as we observed in previous works, the bias towards populars songs can mask the importance of considering the song context.  ... 
arXiv:1807.04690v1 fatcat:xpvr4imkxzet5isx6qeqke3lvi

Temporal Dynamics in Music Listening Behavior: A Case Study of Online Music Service

Chan Ho Park, Minsuk Kahng
2010 2010 IEEE/ACIS 9th International Conference on Computer and Information Science  
Modeling temporal dynamics in user behavior is not trivial, and it is challenging to study its effect in order to provide better recommendation results to users.  ...  Although temporal context may significantly affect the popularity of items and user preference over items, traditional information filtering techniques such as recommender systems have not sufficiently  ...  We are also grateful to Professor Sang-goo Lee, Dongjoo Lee, Sung Eun Park, and Sangkeun Lee at Seoul National University for comments and helping us to co-operate.  ... 
doi:10.1109/icis.2010.142 dblp:conf/ACISicis/ParkK10 fatcat:gcl5f2pu3feebd535vww5vaeay

Large-scale user modeling with recurrent neural networks for music discovery on multiple time scales

Cedric De Boom, Rohan Agrawal, Samantha Hansen, Esh Kumar, Romain Yon, Ching-Wei Chen, Thomas Demeester, Bart Dhoedt
2017 Multimedia tools and applications  
Our experimental analysis on large-scale user data shows that our model can be used to predict future songs a user will likely listen to, both in the short and long term.  ...  In this paper, we present a new approach to model users through recurrent neural networks by sequentially processing consumed items, represented by any type of embeddings and other context features.  ...  We greatly thank Nvidia for its donation of a Tesla K40 and Titan X GPU to support the research of the IDLab group at Ghent University.  ... 
doi:10.1007/s11042-017-5121-z fatcat:wdkmzavmmrafde3ktyydaqygda

Improving sales diversity by recommending users to items

Saúl Vargas, Pablo Castells
2014 Proceedings of the 8th ACM Conference on Recommender systems - RecSys '14  
The second approach, as well as the first, ultimately result in substantial sales diversity enhancements, and improved trade-offs with recommendation precision and novelty.  ...  We address the inverted task by two approaches: a) inverting the rating matrix, and b) defining a probabilistic reformulation which isolates the popularity component of arbitrary recommendation algorithms  ...  The formulation is however useful as it enables a probability-based manipulation of the popularity bias in recommendation algorithms, as we see next.  ... 
doi:10.1145/2645710.2645744 dblp:conf/recsys/VargasC14 fatcat:pd5snrotnvehtg7jehmjkcvkxi

Taming the Unpredictability of Cultural Markets with Social Influence

Andrés Abeliuk, Gerardo Berbeglia, Pascal Van Hentenryck, Tad Hogg, Kristina Lerman
2017 Proceedings of the 26th International Conference on World Wide Web - WWW '17  
We investigate strategies for creating markets in which the popularity of products is better-and more predictablyaligned with their underlying quality.  ...  Unpredictability stems from the "rich get richer" effect, whereby small fluctuations in the market share or popularity of products are amplified over time by social influence.  ...  Work was partly funded by CSIRO's Data61, the ARO (W911NF-15-1-0142) and NSF (SMA-1360058).  ... 
doi:10.1145/3038912.3052680 dblp:conf/www/AbeliukBHHL17 fatcat:wrqvbuje5vfzlmhn5z6py6l6ke


Timanshi Bhardwaj, Manav Rachna International Institute of Research and Studies, Aastha Jain, Karan Choudhary, Manav Rachna International Institute of Research and Studies, Manav Rachna International Institute of Research and Studies
2021 International Journal of Engineering Applied Sciences and Technology  
Despite these advancements, recommender systems must still be developed to a greater level in order to be more successful in giving correct suggestions on a wide range of topics.  ...  We explore Music recommender systems in particular, as well as numerous types of recommendation strategies and the issues they encounter, in this study.  ...  , introduce the concept of popularity, calculate the popularity prediction, and use it for further screening the client recommended resource collection; finally, to integrate the environment context information  ... 
doi:10.33564/ijeast.2021.v06i08.019 fatcat:dxj5l6m4ybfcbnfmh6zvj4alsq

Case-Based Sequential Ordering of Songs for Playlist Recommendation [chapter]

Claudio Baccigalupo, Enric Plaza
2006 Lecture Notes in Computer Science  
Some experiments with different trade-offs between the diversity and the popularity of songs in playlists are analysed and discussed.  ...  Our CBR approach focuses on recommending new and meaningful playlists, i.e. selecting a collection of songs that are arranged in a meaningful sequence.  ...  Users can select an input song, the desired length, and other parameters, and can compare the (meaningfully ordered) recommendation generated with the presented approach with the playlist proposed by the  ... 
doi:10.1007/11805816_22 fatcat:jimsgm4xg5ae3cky5a2bup5bny

Web-Scale Media Recommendation Systems

Gideon Dror, Noam Koenigstein, Yehuda Koren
2012 Proceedings of the IEEE  
One area in which such systems are particularly useful is that of media products, such as movies, books, television, and music.  ...  To this end, we introduce a music rating data set that is likely to be the largest of its kind, in terms of both number of users, items, and total number raw ratings.  ...  In order to establish recommendations, CF systems need to relate two fundamentally different entities: items and users.  ... 
doi:10.1109/jproc.2012.2189529 fatcat:57aw7gwa6rdvfj2d553rx3dmki

Using offline metrics and user behavior analysis to combine multiple systems for music recommendation [article]

Andres Ferraro, Dmitry Bogdanov, Kyumin Choi, Xavier Serra
2019 arXiv   pre-print
As a proof of concept, we conduct experiments combining two recommendation systems, a Matrix Factorization model and a popularity-based recommender.  ...  In this work we focus on music recommendation and propose a new way to improve recommendations, with respect to a desired metric of choice, by combining multiple systems for each user individually based  ...  ., and partially funded by the European Unions Horizon 2020 research and innovation programme under grant agreement No 688382 (AudioCommons) and the Ministry of Economy and Competitiveness of the Spanish  ... 
arXiv:1901.02296v1 fatcat:t22q5hcfxrbjhgmsslu3saoqs4

Design of a Music Recommendation Model on the Basis of Multilayer Attention Representation

Wei Lu
2022 Scientific Programming  
In order to distinguish the differences in user preferences for multidomain features of songs, a feature-dependent attention network is designed; in order to distinguish the differences in user preferences  ...  The experimental results on 30Music and MIGU datasets show that the proposed model achieves significant improvement in recall and MRR compared with the current recommendation models.  ...  a large number of disliked popular songs to users in a specific scenario, i.e., the popularity bias, while those songs that are rarely listened to by users or new on the shelves are difficult to be recommended  ... 
doi:10.1155/2022/7763726 doaj:900ef4cddc15455eac25f42cf95a79df fatcat:g2akitltfnbjxe2p2vt4jm4nce


Zhiyong Cheng, Jialie Shen
2014 Proceedings of International Conference on Multimedia Retrieval - ICMR '14  
In the paper, we present a novel recommender system called Just-for-Me to facilitate effective social music recommendation by considering users' location related contexts as well as global music popularity  ...  The fast growth of online communities and increasing popularity of internet-accessing smart devices have significantly changed the way people consume and share music.  ...  Distinguished from the previous approaches in the domain of context-aware music recommendation, our approach can effectively combine local context and dynamics of global music popularity to facilitate  ... 
doi:10.1145/2578726.2578751 dblp:conf/mir/ChengS14 fatcat:7jsv4soxhzcf5fe6tmablqautm

Popularity Bias in Recommendation: A Multi-stakeholder Perspective [article]

Himan Abdollahpouri
2020 arXiv   pre-print
Prior research has examined various approaches for mitigating popularity bias and enhancing the recommendation of long-tail items overall.  ...  In this dissertation, I study the impact of popularity bias in recommender systems from a multi-stakeholder perspective.  ...  In other words, a great amount of care must be taken in order to make sure no additional biases are introduced, as bias correction is often difficult.  ... 
arXiv:2008.08551v1 fatcat:yiuamp6lcnc2bmhzkklakq6ui4

Deep Learning in Music Recommendation Systems

Markus Schedl
2019 Frontiers in Applied Mathematics and Statistics  
In addition, we discuss major challenges faced in MRS, in particular in the context of the current research on deep learning.  ...  Like in many other research areas, deep learning (DL) is increasingly adopted in music recommendation systems (MRS).  ...  Compared to a popularity-based recommender and an item-based CF system, the RNN yields more stable results and is unaffected by popularity bias.  ... 
doi:10.3389/fams.2019.00044 fatcat:vvosxlygrravloyrj3qubflnoe

Evaluating The Quality Of Generated Playlists Based On Hand-Crafted Samples

Geoffray Bonnin, Dietmar Jannach
2013 Zenodo  
the most popular songs of the artists appearing in the user's listening history.  ...  This popularity bias results in the fact that simple popularity-based approaches, which present the same set of popular items to everyone, can represent a comparably hard baseline [7] .  ... 
doi:10.5281/zenodo.1418000 fatcat:oxt3tt74pjg3feybb5zjfsz6mu
« Previous Showing results 1 — 15 out of 17,858 results