I am Lorenzo, a data scientist with a strong interest in social science and cultural studies, researching how Information and Communication Technology (ICT) is influencing human behaviour.
I am currently (2018-) a PhD Student at the Music Technology Group (MTG) of the University Pompeu Fabra (UPF) in Barcelona, part of the MIR (Music Information Research) lab, working under the supervision of Dr. Emilia Gómez and Dr. Carlos Castillo. My current research is at the intersection between Music Information Retrieval and Social Computing, exploring how music recommendation diversity is impacting our socio-cultural system.
I have been part of the the TROMPA (Towards Richer Online Music Public-domain Archives) Project, an international research project, sponsored by the European Union, investigating how make public-domain digital music resources more accessible. Now, I am collaborating with the Musical AI project, funded by the Ministry of Science and Innovation of the Spanish Government, investigating AI to support musical experiences towards a data-driven, human-centered approach.
I hold a Bachelor’s degree in Applied Mathematics from “La Sapienza” University of Rome (2009-2014), a Master’s degree in Sound and Music Computing (2014-2015), and a Master’s degree in Intelligent Interactive Systems (2016-2018) from Universitat Pompeu Fabra. I also had several work experiences in the music industry as Data Engineer (SoundCloud, MonkingMe, BMAT).
Here what has been my journey until now:
I am currently researching what may be the impact of Music Recommender Systems (Music RS) on human behavior, and how to assess such impact. Music RS are increasingly part of the music listening experience of people all over the world, but little is known about how they are influencing our ways of enjoying music.
The role of Music RS is to help listeners in finding music tailored to their interests and tastes, but while designing such systems several choices can be subject to criticism because of their power of reinforcing already existing cultural bias.
Therefore, I am trying to address the problem of how to assess the impact of music recommendation diversity, and this requires:
1. The formalization of a working definition of diversity in the music recommendation field.
2. The development of evaluation practices for estimating the diversity of music recommender system outcomes.
3. The analysis of the impact of music recommendation diversity.
4. The proposal of countermeasures for mitigating negative or reinforcing positive impact observed.
Basing on already known consequences of the (mis-)use of IT in political, economic, and social areas, the main goal of my research is to shed light on the cultural impact that music recommender systems may have on listeners, artists, and our society at large.
You can find the last outcomes of my research at this link:
My top recommended readings
- Benjamin, W. (1969). The Work of Art in the Age of Mechanical Reproduction, translated by Harry Zohn, from the 1935 essay. Hannah Arendt, ed., Illuminations. London: Fontana. (pdf)
- Molino, J., Underwood, J., & Ayrey, C. (1990). Musical fact and the semiology of music. Music Analysis, 9(2), 105–156. (pdf)
- Celma, O., & Cano, P. (2008). From hits to niches? or how popular artists can bias music recommendation and discovery. In 2nd Workshop on Large-Scale Recommender Systems and the Netflix Prize Competition (ACM KDD). (pdf)
- Born, G. (2020). Diversifying MIR : Knowledge and Real-World Challenges , and New Interdisciplinary Futures. Transactions of the International Society for Music Information Retrieval, 3, 193–204. (pdf)