Abstract

We present an algorithm that organizes a song repository upon recording a user’s memory experiences from previous music listening activities. Our method forms an affectively annotated network of songs. The network’s connections correspond to a person’s recorded memory experiences related to song preferences when the person is at different states of affective bias. Upon formation of this network, an intelligent affect-sensitive network navigation algorithm synthesizes playlists that conform to desired affective states. The method for the network formation is highly individualized, in the sense that it takes in account an individual’s music preferences which are typically subjective and may differ from user to user. Also, the method is content independent, in the sense that it does not rely or favor any particular music genre. In fact, the method is applicable to any type of media, not only songs. We implement our method and present evaluation results from the introspection of our algorithms’ execution and from feedback recorded during the evaluation by human test subjects. The evaluation results clearly indicate that the proposed method significantly outperforms the most typical paradigm of random song selection.

Highlights

  • AND BACKGROUNDOrganization and retrieval mechanisms for media repositories is a topic of vigorous research activity during the past several years The issues addressed in such research are content-based organization and retrieval mechanisms and efficiency in data access (e.g., [1, 2])

  • (2) Quality of the K-line mesh navigation algorithm of Part C, in terms of its ability to deliver playlists that conform to a desired State of Mind (SM). (3) comparison of the overall quality of our method against the most frequently used typical alternative of random song selections

  • E-Stage I corresponds to Part A together with Part B of section 2-i.e., the initial creation of the K-lines followed by the creation of the K-line mesh

Read more

Summary

Introduction

Organization and retrieval mechanisms for media repositories is a topic of vigorous research activity during the past several years The issues addressed in such research are content-based organization and retrieval mechanisms and efficiency in data access (e.g., [1, 2]). All the reported mechanisms are useful in the sense that they facilitate organization and retrieval based on characteristics of the content of the media, such as the semantic or grammatical relevance of text from a publication, and the relevance of a theme from an image or a video clip. Solutions that facilitate efficient data access are useful, especially when dealing with large and public media collections. Work which combines emotion involving issues and these disciplines has evolved into a new discipline, under the name Affective Computing [9, 10]. One of the possibilities that is pointed in [11] and [9] is to enable a machine to select and play music according to someone’s emotions

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call