Large Scale Discovery of Seasonal Music From User Data
This addresses the need for better recommendation or search systems by mining trends from user data, but it is incremental as it applies an existing method to a specific domain.
The paper tackled the problem of identifying seasonal music by classifying songs as seasonal using a large dataset of user listening data, achieving strong performance in classifying Christmas music with Gaussian Mixture Models.
The consumption history of online media content such as music and video offers a rich source of data from which to mine information. Trends in this data are of particular interest because they reflect user preferences as well as associated cultural contexts that can be exploited in systems such as recommendation or search. This paper classifies songs as seasonal using a large, real-world dataset of user listening data. Results show strong performance of classification of Christmas music with Gaussian Mixture Models.