A Music Recommendation System Based on Music and User Grouping

Chen, Hung-Chen; Chen, Arbee L. P.

doi:10.1007/s10844-005-0319-3

Cited by 77 publications

(42 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is a very difficult task to be automatically identified by a system based on genre or artist similarity, although the particular song can be evaluated as a correct result according to users' preferences for social tags, as users tend to tag the songs of "Placebo" and the corresponding song of "Nirvana" as "chillout" music. For example, if the proposed method was embedded into a recommendation system to perform ranking and topic searching, then a user could pose a "chill out" music request (see Chen & Chen 2005 for more information on recommendation systems). Then the list retrieved from the system would consist of songs, the vast majority of which, would be songs by "Placebo" and "Coldplay", i.e.…”

Section: Resultsmentioning

confidence: 99%

Building Tag-Aware Groups for Music High-Order Ranking and Topic Discovery

Rafailidis

Νανόπουλος

Manolopoulos

2010

International Journal of Multimedia Data Engineering and Management

View full text Add to dashboard Cite

In popular music information retrieval systems, users have the opportunity to tag musical objects. Through their tags, users express their personal preferences. Such preferences provide valuable insights about the formulation of user groups/communities. Here, we focus on the analysis of social tagging data to reveal coherent groups characterized by their users, tags and music objects, e.g. songs and artists. This analysis allows for the expression of discovered groups in a multi-aspect way. For each group we can reveal the most prominent users, tags, and music objects using a generalization of the popular web-ranking concept into the social data domain. We experiment with real data and our results show that each Tag-Aware group corresponds to a specific music topic and additionally, a three way ranking analysis is performed inside each group. We believe that building Tag-Aware groups is crucial in offering ways to add structure in the unstructured nature of tags.

show abstract

Section: Resultsmentioning

confidence: 99%

Building Tag-Aware Groups for Music High-Order Ranking and Topic Discovery

Rafailidis

Νανόπουλος

Manolopoulos

2010

International Journal of Multimedia Data Engineering and Management

View full text Add to dashboard Cite

show abstract

“…A popular application area for ranking methods is the area of recommendation systems, i.e., systems that make recommendations for the most appropriate actions/items for a specific user or situation. Recommendation systems can be used to recommend to users a diverse range of items, including movies (Koren, 2008), commercial products (Bridge, 2001), useful customer reviews (Zhang and Tran, 2010), images (Kim, Lee, Cho and Kim, 2004), or music (Chen and Chen, 2005).…”

Section: Related Workmentioning

confidence: 99%

Boosted ranking models: a unifying framework for ranking predictions

2011

View full text Add to dashboard Cite

Abstract. Ranking is an important functionality in a diverse array of applications, including web search, similarity-based multimedia retrieval, nearest neighbor classification, and recommendation systems. In this paper we propose a new method, called Boosted Ranking Model(BRM), for learning how to rank from training data. An important feature of the proposed method is that it is domain-independent, and can thus be applied to a wide range of ranking domains. The main contribution of the new method is that it reduces the problem of learning how to rank to the much more simple, and well-studied, problem of constructing an optimized binary classifier from simple, weak classifiers. Using that reduction, our method constructs an optimized ranking model using multiple simple, easy-to-define ranking models as building blocks. The new method is a unifying framework that includes, as special cases, specific methods that we have proposed in earlier publications for specific ranking applications, such as nearest neighbor retrieval and classification. In this paper we reformulate those earlier methods as special cases of the proposed BRM method, and we also illustrate a novel application of BRM, on the problem of making movie recommendations to individual users.

show abstract

“…The recommendation systems are to recommend items that users may be interested in based on their predefined preferences or access histories [4]. Many of the leading companies such as Amazon.com, Google, CDNOW, LA Times and eBay, are already using personalized recommendation systems to help their customers find products to purchase.…”

Section: Recommendation Systemsmentioning

confidence: 99%

“…In their system, the users' preferences are learned by mining the melody patterns, i.e., the pitch information, of the music they listened. Chen and Chen [4] proposed a music recommendation system that employed three recommendation mechanisms, i.e., content-based method, collaborative filtering and statistics-based method, for different users' needs. In their system, music objects are grouped according to the properties such as pitch, duration and loudness, and users are grouped according to their interests and behaviors derived from the access histories.…”

Section: Recommendation Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Music for My Mood: A Music Recommendation System Based on Context Reasoning

Lee¹,

Lee

2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The context-awareness has become one of the core technologies and the indispensable function for application services in ubiquitous computing environment. The task of using context data for inferring a user's situation is referred to as context reasoning. In this research, we incorporated the capability of context reasoning in a music recommendation system. Our proposed system contains such modules as Intention Module, Mood Module and Recommendation Module. The Intention Module performs context reasoning that infers whether a user wants to listen to music or not by using the environmental context data. The Mood Module determines the genre of the music suitable to the user's context. Finally, the Recommendation Module recommends the music to the user. Context reasoning is implemented using case-based reasoning.

show abstract

A Music Recommendation System Based on Music and User Grouping

Cited by 77 publications

References 11 publications

Building Tag-Aware Groups for Music High-Order Ranking and Topic Discovery

Building Tag-Aware Groups for Music High-Order Ranking and Topic Discovery

Boosted ranking models: a unifying framework for ranking predictions

Music for My Mood: A Music Recommendation System Based on Context Reasoning

Contact Info

Product

Resources

About