4,215 Hits in 11.5 sec

How Much Metadata Do We Need In Music Recommendation? A Subjective Evaluation Using Preference Sets

Dmitry Bogdanov, Perfecto Herrera
2011 Zenodo  
ACKNOWLEDGMENTS The authors would like to thank all participants involved in the evaluation.  ...  Evaluation Methodology We performed subjective listening tests on the 19 participants using our in-house music collection (see Section 2).  ...  One of the problems of existing research on music recommendation lies in a difficulty to conduct comprehensive subjective evaluations with real listeners.  ... 
doi:10.5281/zenodo.1415103 fatcat:i3w5zpd6dbcsbenxjriq4q3f4i

Music Recommendation: A multi-faceted approach

Oscar Celma, Xavier Serra
2006 Zenodo  
This thesis presents the current methods used to recommend music assets, and reviews also some proposals of modelling user's musical preferences.  ...  As a test–bed example, two prototypes have been developed a music search engine and music discovery based on music similarity, and a hybrid music recommender.  ...  Subjective evaluation of playlists In our case, we are planning to carry on two different evaluations.  ... 
doi:10.5281/zenodo.3743108 fatcat:wcfdl34jnzeqtmzjzamjjvdt44

How to Get the Recommender Out of the Lab? [chapter]

Jérome Picault, Myriam Ribière, David Bonnefoy, Kevin Mercer
2010 Recommender Systems Handbook  
It will present the different aspects that must be studied before the design is even started, and how to avoid pitfalls, in a hands-on approach.  ...  This can make the task of building such a recommender system daunting. This chapter intends to be a guide to the design, implementation and evaluation of personalised systems.  ...  Screen real-estate: a point that is easily overlooked in the early stages of the design is how much screen space the recommendations will use.  ... 
doi:10.1007/978-0-387-85820-3_10 fatcat:bl2ofp7p4jbxhok47cxrflh3mq

Location-aware music recommendation

Matthias Braunhofer, Marius Kaminskas, Francesco Ricci
2013 International Journal of Multimedia Information Retrieval  
To address this problem we have used emotional tags assigned to both music tracks and POIs, and we have considered a set of similarity metrics for tagged resources to establish a match between music tracks  ...  In this work we consider a particular kind of contextaware recommendation task -selecting music content that fits a place of interest (POI).  ...  the recommended music, namely: a) "How much did you like the place of interest?"  ... 
doi:10.1007/s13735-012-0032-2 fatcat:rsnuezqbqrg65axa5d242th6xe

Explainability in Music Recommender Systems [article]

Darius Afchar, Alessandro B. Melchiorre, Markus Schedl, Romain Hennequin, Elena V. Epure, Manuel Moussallam
2022 arXiv   pre-print
Then, we show how explainability components can be integrated within a MRS and in what form explanations can be provided.  ...  In this article, we discuss how explainability can be addressed in the context of MRSs.  ...  Do these really address our needs w. r. t. to incompleteness? Or are they a proxy for it? In the latter case, how do we assert/evaluate their understandability w. r. t. our goal?  ... 
arXiv:2201.10528v1 fatcat:k4mhwh2nhzexxgyvz3dppv3j5i

Smarter Than Genius? Human Evaluation Of Music Recommender Systems

Luke Barrington, Reid Oda, Gert R. G. Lanckriet
2009 Zenodo  
We now consider how a music recommender system could take advantage of both content-based information and metadata, when available, to perform as well or better than Genius, without the need for massive  ...  In other words, when subjects did not know (or like) a song, and presumably could make less use of artist associations, they preferred Genius' recommendations.  ... 
doi:10.5281/zenodo.1417803 fatcat:jdzrcpdpz5akrerqfhbm2eagf4

Automatic news recommendations via aggregated profiling

Erik Mannens, Sam Coppens, Toon De Pessemier, Hendrik Dacquin, Davy Van Deursen, Robbie De Sutter, Rik Van de Walle
2011 Multimedia tools and applications  
In this paper, we show how personalised recommendation and distribution of news events, described using an RDF/OWL representation of the NewsML-G2 standard, can be enabled by automatically categorising  ...  As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful news event information that goes beyond basic information  ...  Innovation by Science and Technology in Flanders (IWT), the Fund for Scientific Research-Flanders (FWO-Flanders), and the European Union.  ... 
doi:10.1007/s11042-011-0844-8 fatcat:bfo52776hffcfm5fc2t5has4qm

Scalable music recommendation by search

Rui Cai, Chao Zhang, Lei Zhang, Wei-Ying Ma
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
In this paper, aiming at providing an efficient and general solution, we present a search-based solution for scalable music recommendations.  ...  The growth of music resources on personal devices and Internet radio has increased the need for music recommendations.  ...  In the following, we evaluate both the quantitative and subjective qualities of our recommendation results in Section 5.3 and Section 5.4.  ... 
doi:10.1145/1291233.1291466 dblp:conf/mm/CaiZZM07 fatcat:xpjunfiiv5flrligi2ranz4kua

Context-aware mobile music recommendation for daily activities

Xinxi Wang, David Rosenblum, Ye Wang
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
We present a probabilistic model to integrate contextual information with music content analysis to offer music recommendation for daily activities, and we present a prototype implementation of the model  ...  For instance, a user who is running generally will prefer loud, energizing music.  ...  Q1 helps in understanding user needs for a context-aware music experience; the results demonstrate that subjects generally prefer different music in different contexts.  ... 
doi:10.1145/2393347.2393368 dblp:conf/mm/WangRW12 fatcat:ytpu7hevm5b4ligdwkktz4rb54

Current challenges and visions in music recommender systems research

Markus Schedl, Hamed Zamani, Ching-Wei Chen, Yashar Deldjoo, Mehdi Elahi
2018 International Journal of Multimedia Information Retrieval  
Music recommender systems (MRS) have experienced a boom in recent years, thanks to the emergence and success of online streaming services, which nowadays make available almost all music in the world at  ...  the very essence of listener needs, preferences, and intentions, MRS research becomes a big endeavor and related publications quite sparse.  ...  Spread is a metric of how well the recommender algorithm can spread its attention across a larger set of items [104] .  ... 
doi:10.1007/s13735-018-0154-2 fatcat:56jsdgp5v5g3be7stpwnfvtkdi

Artist and style exposure bias in collaborative filtering based music recommendations [article]

Andres Ferraro, Dmitry Bogdanov, Xavier Serra, Jason Yoon
2019 arXiv   pre-print
The results of our analysis demonstrate the need for a better evaluation methodology for current music recommendation algorithms, not only limited to user-focused relevance metrics.  ...  Then, we simulate the effect of the system in the long term with a feedback loop.  ...  We also show a simulation of how these recommendations can affect user behavior in the long term.  ... 
arXiv:1911.04827v1 fatcat:6wfyc5hozbfaxiqonschbmpzre

A Mobile-Based System for Context-Aware Music Recommendations [chapter]

Börje F. Karlsson, Karla Okada, Tomaz Noleto
2012 IFIP Advances in Information and Communication Technology  
As mobile devices are always with users and music listening is a very personal and situational behaviour, contextual information could be used to greatly enhance music recommendations.  ...  We present a system for collecting context and usage data from mobile devices, but targeted at recommending music according to learned user profiles and specific situations.  ...  We'd like to thank Francimar Maciel and Maysa Martins for all the help in setting and running the trials.  ... 
doi:10.1007/978-3-642-33412-2_53 fatcat:5hvzkrzwdrayhg6ayf6q5ezamq

Combining Multiple Metadata Types in Movies Recommendation Using Ensemble Algorithms

Bruno Souza Cabral, Renato Dompieri Beltrao, Marcelo Garcia Manzato, Frederico Araújo Durão
2014 Proceedings of the 20th Brazilian Symposium on Multimedia and the Web - WebMedia '14  
In this paper, we analyze the application of ensemble algorithms to improve the ranking recommendation problem with multiple metadata.  ...  We propose three generic ensemble strategies that do not require modification of the recommender algorithm.  ...  how much u likes a description g ∈ G(.).  ... 
doi:10.1145/2664551.2664569 dblp:conf/webmedia/CabralBMD14 fatcat:q5odsoqm3jcinn5t6lr3qirs4u

Content-based Music Recommendation: Evolution, State of the Art, and Challenges [article]

Yashar Deldjoo, Markus Schedl, Peter Knees
2021 arXiv   pre-print
Based on a thorough literature analysis, we first propose an onion model comprising five layers, each of which corresponds to a category of music content we identified: signal, embedded metadata, expert-generated  ...  In this survey, we review 47 articles on content-driven music recommendation.  ...  : • How can we categorize, in an unambiguous manner, the various types of content features used in MRS research?  ... 
arXiv:2107.11803v1 fatcat:4hz4hqkkmvcapbdr3wvtp2t4iu

Evaluating Music Recommendations with Binary Feedback for Multiple Stakeholders [article]

Sasha Stoikov, Hongyi Wen
2021 arXiv   pre-print
Using the Piki Music dataset of 500k ratings collected over a two-year time period, we evaluate the performance of classic recommendation algorithms on three important stakeholders: consumers, well-known  ...  High quality user feedback data is essential to training and evaluating a successful music recommendation system, particularly one that has to balance the needs of multiple stakeholders.  ...  They are asked to like or dislike 30 second music video clips. Figure 1 shows how the interface presents the songs in batches, much like a social media story.  ... 
arXiv:2109.07692v1 fatcat:7ppjkcb5xncklguj36n7j3thum
« Previous Showing results 1 — 15 out of 4,215 results