Multi-agent system application for music features extraction, meta-classification and context analysis

摘要

Manual music classification is a slow and costly process. Most recent works about music auto-classification such as genre or emotions make this process easier, but are focused on a single task. In this work, a music multi-classification platform is presented. This platform is based on multi-agent systems, allowing to distribute the extraction, classification, and service tasks among agents. The platform performs a musical genre and emotional classification and provides context information of songs from social networks such as Twitter and Last.fm. The methods chosen based on meta-classifiers to perform single-label and multi-label classification obtain great results. In the case of multi-label classification, better results are obtained than in other previous works.