Harvesting and Structuring Social Data in Music Information Retrieval

@inproceedings{Oramas2014HarvestingAS,
  title={Harvesting and Structuring Social Data in Music Information Retrieval},
  author={Sergio Oramas},
  booktitle={ESWC},
  year={2014}
}
An exponentially growing amount of music and sound resources are being shared by communities of users on the Internet. Social media content can be found with different levels of structuring, and the contributing users might be experts or non-experts of the domain. Harvesting and structuring this information semantically would be very useful in context-aware Music Information Retrieval (MIR). Until now, scant research in this field has taken advantage of the use of formal knowledge… 
Automatic Creation of Knowledge Graphs from Digital Musical Document Libraries
TLDR
A method to automatically extract meaningful knowledge from documents present in Digital Musical Document Libraries, by using Information Extraction techniques, is proposed, which is represented in a machine-readable format as a knowledge graph, where entities are represented as nodes, and relations as edges.
Natural language processing for music knowledge discovery
TLDR
Different Natural Language Processing approaches to harness the potential of text collections for automatic music knowledge discovery are presented, covering different phases in a prototypical NLP pipeline, namely corpus compilation, text-mining, information extraction, knowledge graph generation, and sentiment analysis.
Culture-Aware Approaches to Modeling and Description of Intonation Using Multimodal Data
TLDR
This thesis draws upon multimodal data sources concerning art music traditions, extracting culturally relevant and musically meaningful information about melodic intervals from each of them and structuring it with formal knowledge representations, resulting in a symbiosis mutually enriching their information.
AN ANALYTICAL STUDY ON VARIOUS DATA MINING METHODOLOGIES ON SOCIAL MEDIA APPLICATIONS
TLDR
This study presented experimental assessment of numerous advanced data mining techniques that is stated in the literature in order to identify the superior method underneath numerous performance measures such asF1-score and classification accuracy.
The survey of sentiment and opinion mining for behavior analysis of social media
TLDR
The comprehensive analysis of the methods which are used on user behavior prediction is presented and will provide a detailed information, pros and cons in the domain of sentiment and opinion mining.
FlaBase: Towards the Creation of a Flamenco Music Knowledge Base
This work was funded by the COFLA2 research project (Proyectos de Excelencia de la Junta de Andaluca, FEDER P12-TIC-1362) and the SIGMUS research project (TIN2012- 36650).

References

SHOWING 1-10 OF 26 REFERENCES
Exploiting Social Media for Music Information Retrieval
This chapter will first provide an introduction to information retrieval (IR) in general, before briefly explaining the research field of music information retrieval (MIR). Hereafter, we will discuss
Towards Semantic Music Information Extraction from the Web Using Rule Patterns and Supervised Learning
TLDR
Several approaches to identify and extract two specic semantic relations from related Web documents are presented and evaluated and are shown to be useful to relate (Web-)documents to musical artists.
A METHOD FOR EXTRACTING SEMANTIC INFORMATION FROM ON-LINE ART MUSIC DISCUSSION FORUMS
TLDR
The semantic relations are inferred from the co-occurrence of musical concepts in forum posts, using network analysis, and this methodology allows us to obtain meaningful and relevant information from forum discussions.
Harvesting microblogs for contextual music similarity estimation: a co-occurrence-based framework
TLDR
It is shown that collaborative chatter on music can be effectively used to develop music artist similarity measures, which are a core part of every music retrieval and recommendation system.
ANALYSIS OF THE FOLKSONOMY OF FREESOUND
TLDR
This paper analyzes the folksonomy of Freesound, an online audio clip sharing site which contains more than two million users and 150,000 user-contributed sound samples covering a wide variety of sounds, and compute some metrics that characterize the guysonomy both at the global level and at the tag level.
Inferring Semantic Facets of a Music Folksonomy with Wikipedia
TLDR
This paper presents a system that can automatically obtain a set of semantic facets underlying the folksonomy of the social music website Last.fm, and categorize Last.FM tags with respect to the obtained facets.
Bridging the gap between folksonomies and the semantic web: an experience report
TLDR
The experimental results show that, while semantic enrichment needs to be aware of the particular characteristics of folksonomies and the Semantic Web, it is beneficial for both.
A music information system automatically generated via Web content mining techniques
Folksonomy-based Tag Recommendation for Online Audio Clip Sharing
TLDR
This paper proposes four algorithm variants for tag recommendation based on tag co-occurrence in the Freesound folksonomy and shows how specific strategies for selecting the appropriate number of tags to be recommended can significantly improve algorithms’ performance.
Inferring Descriptions and Similarity for Music from Community Metadata
TLDR
Methods for unsupervised learning of text profiles for music from unstructured text obtained from the web and results indicate that they perform well when used to find similar artists.
...
...