Smartphone application for music recommendation based on musician network
|Abstract||This thesis is focused on presenting a system for recommending music to the smartphone users. The system takes the users favourite musician as input and generate recommendations based on this musiciansís social relations. The approach is based on the social networks of the musicians. Each of the different networks for the musicians are constructed and analysed to provide possible recommendation results. The most significant findings are also presented in the application as overview and suggestions for interesting musicians.|
This approach distingushes itself from the existing solutions and is implemented into a prototype to be tested for the functionality and potential market value. Users will be able to navigate through the musicians of interest and view their general information as well as recommendations based on these musicians. Each of the recommended musician includes an audio preview as presentation. The network approach can exceed the potential recommendation content of the content-based filtering and has potential to reach the widely used collaborative filtering in terms of recommendation diversity.
The prototype utilizes the web-based application framework to achieve crossfit comptatibility on both Android and iOS platforms. The advantages and
drawbacks of this framework is tested and discussed.
Finally a simplified version of user experience process and the gathered feedback validates the functionality and the potential market value of this application.
|Type||Bachelor thesis [Academic thesis]|
|Publisher||Technical University of Denmark, DTU Compute, E-mail: email@example.com|
|Address||Matematiktorvet, Building 303-B, DK-2800 Kgs. Lyngby, Denmark|
|Note||Michael Kai Petersen (DTU supervisor), firstname.lastname@example.org, DTU Compute|
|BibTeX data|| [bibtex]|
|IMM Group(s)||Intelligent Signal Processing|