Class-based tag recommendation and user-based evaluation in online audio clip sharing

Abstract

Online sharing platforms often rely on collaborative tagging systems for annotating content. In this way, users themselves annotate and describe the shared contents using textual labels, commonly called tags. These annotations typically suffer from a number of issues such as tag scarcity or ambiguous labelling. Hence, to minimise some of these issues, tag recommendation systems can be employed to suggest potentially relevant tags during the annotation process. In this work, we present a tag recommendation system and evaluate it in the context of an online platform for audio clip sharing. By exploiting domain-specific knowledge, the system we present is able to classify an audio clip among a number of predefined audio classes and to produce specific tag recommendations for the different classes. We perform an in-depth user-based evaluation of the recommendation method along with two baselines and a former version that we described in previous work. This user-based evaluation is further complemented with a prediction-based evaluation following standard information retrieval methodologies. Results show that the proposed tag recommendation method brings a statistically significant improvement over the previous method and the baselines. In addition, we report a number of findings based on the detailed analysis of user feedback provided during the evaluation process. The considered methods, when applied to real-world collaborative tagging systems, should serve the purpose of consolidating the tagging vocabulary and improving the quality of content annotations.

Harvesting and Structuring Social Data in Music Information Retrieval

“…Members of our research group have already done some research in this area. Freesound.org has been developed at the Music Technology Group, and there are various publications analyzing its resources, folksonomy and community [23], [8], [24] and [25].…”

Folksonomy-Based Recommender Systems: A State-of-the-Art Review

“…99, a topic ontology is build based upon the Open Directory Project categories, extracting semantic information from Wikipedia and WordNet, for generating tag suggestions to blogs. Font et al 100 presented an approach for exploiting domainspecific knowledge for tag recommendation in the context of an online platform for audio clip sharing. This system classifies an audio clip among a number of predefined audio classes to produce specific tag recommendations for the different classes.…”

Freesound technical demo

“…Inside the Music Technology Group there have been publications dealing with topics such as soundscape generation and content-based audio-clip classification [7,4], database discovery [9], community characterization and network analysis [8] or folksonomy analysis and tag recommendation [2,3]. Moreover, outside the Music Technology Group Freesound data has also been used for research on creative interfaces, composition [1,10], annotation of environmental sounds [6] and statistical methods for dimensionality reduction (using freesound data without considering domain-specific information, [5]).…”