The discovery of listening experiences, interactive seminar by Enrico Daga (KMi, Open University, UK)

The LED project.

An important goal of digital humanities is to enhance the ability of scholars to carry out large scale studies by facilitating the reuse and sharing of sources of investigation.
The Listening Experience Database Project (LED) is an initiative funded by the UK’s Arts and Humanities Research Council (AHRC), which has developed a repository of accounts of people’s private experiences of listening to music, to support cultural studies in music perception and music history.
Since 2012, the LED team has been exploring a wide variety of sources, collecting over 10.000 unique listening experiences. However, this has been a highly expensive process, as the identification and extraction of listening experiences from sources has been essentially a manual task. Hence, automated support is needed, to improve the efficiency and effectiveness of this process and to enable the discovery and collection of listening experiences at scale.
In the first part of the talk, we will focus on this issue and report on the design of a thorough experimentation framework for testing and evaluating competing approaches to the discovery of listening experiences, including the development of a gold standard. The experiments involve machine learning, statistical NLP, word embeddings, and semantic technologies, and include a novel, hybrid approach that combines these methods to produce a highly accurate solution to the task.
In the second part, we will discuss future directions of research, focusing on characterising listening experiences and identifying their constituents at a linguistic and semantic level, with the ultimate objective of developing a collection of patterns characterising different types of listening experiences. An interactive part of the session will include hands-on tasks where we will invite participants to analyse listening experiences and identify their linguistic and semantic features.

Bio:
Enrico Daga has a PhD in Artificial Intelligence and has carried out research on Web Semantics and Ontology Engineering since 2008, first at the Italian National Research Council (CNR) and then at the Knowledge Media Institute of The Open University in the UK, where he leads the OU Linked Data initiative. After playing key roles in R&D projects related to the development of intelligent systems for Ontology Engineering (NeOn) and Smart Cities (MK: Smart), he is currently Technical Director of the award-winning MK: Data Hub and the related CityLABS innovation programme. His research is exploring the application of knowledge-based methods to support scholarship in the humanities and developing novel data curation pipelines through intelligent processing of metadata, particularly in the context of the LED Project.
A former student of Music and Performing Arts (University RomaTRE), Enrico is founder and chair of the WHiSe Workshop on Humanities in the Semantic Web (http://whise.kmi.open.ac.uk)