Time series are ubiquitous, and a measure to assess their similarity is a core part of many computational systems. In particular, the similarity measure is the most essential ingredient of time series clustering and classification systems. Because of this importance, countless approaches to estimate time series similarity have been proposed. However, there is a lack of comparative studies using empirical, rigorous, quantitative, and large-scale assessment strategies. In this article, we provide an extensive evaluation of similarity measures for time series classification following the aforementioned principles. We consider 7 different measures coming from alternative measure 'families', and 45 publicly-available time series data sets coming from a wide variety of scientific domains. We focus on out-of-sample classification accuracy, but in-sample accuracies and parameter choices are also discussed. Our work is based on rigorous evaluation methodologies and includes the use of powerful statistical significance tests to derive meaningful conclusions. The obtained results show the equivalence, in terms of accuracy, of a number of measures, but with one single candidate outperforming the rest. Such findings, together with the followed methodology, invite researchers on the field to adopt a more consistent evaluation criteria and a more informed decision regarding the baseline measures to which new developments should be compared.

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.

The use of community detection algorithms is explored within the framework of cover song identification, i.e. the automatic detection of different audio renditions of the same underlying musical piece. Until now, this task has been posed as a typical query-by-example task, where one submits a query song and the system retrieves a list of possible matches ranked by their similarity to the query. In this work, we propose a new approach which uses song communities (clusters, groups) to provide more relevant answers to a given query. Starting from the output of a state-of-the-art system, songs are embedded in a complex weighted network whose links represent similarity (related musical content). Communities inside the network are then recognized as groups of covers and this information is used to enhance the results of the system. In particular, we show that this approach increases both the coherence and the accuracy of the system. Furthermore, we provide insight into the internal organization of individual cover song communities, showing that there is a tendency for the original song to be central within the community. We postulate that the methods and results presented here could be relevant to other query-by-example tasks.