Rafael Mestre Castillo

Research interests

Multimodal machine learning and Natural Language Processing

Computational social science

Digital Humanities

Accepting applications from PhD students.

About

Dr Mestre joined the University of Southampton in 2021. He holds a Bachelor’s Degree in Physics by the University of Granada, an Erasmus Mundus Joint Master in Nanoscience and Nanotechnology by KU Leuven and Université Grenoble Alpes and a PhD in Nanobiotechnology by the University of Barcelona.

He is currently a New Frontiers Fellow in Machine Learning at the School of Electronics and Computer Science of the University of Southampton. Prior to this, he was a Research Fellow in the 'Rebooting Democracy' project at the Politics and International Relations Department. His research is interdisciplinary and lies at the interface of computer science and political science. Much of his research efforts are focused on the development of argumentation mining (and computational social science in general) using multimodal machine learning methods; the study of digital tools for deliberation applied to democratic innovations; the ethics, social implications and governance of emergent technologies like natural language processing (NLP) and bio-hybrid robots; and the application of machine learning in digital humanities. He's a member of the steering committee of the Centre for Democratic Futures (CDF) and an Associate at the Digital Humanities (DH) hub of the University.

In the past, during his PhD, he researched at the Institute for Bioengineering of Catalonia (IBEC) in the development of bio-hybrid robotics and nanorobotics, at the interface of fields like tissue engineering, biomedicine, material science, physics, 3D-bioprinting, robotics and computer vision. He published his research in journals like Science Robotics, Advanced Materials Technologies or Biofabrication, he submitted a patent and collaborated with private companies.

Research

Research groups

Member of:

Research interests

Multimodal machine learning and Natural Language Processing
Computational social science
Digital Humanities
Bio-hybrid robotics
Democratic Innovations

Current research

Dr Mestre's current research very interdisciplinary in nature and ranges from computer science to political science. Some of his research efforts are focused on natural language processing (NLP) and multimodal machine learning, particularly applied, although not exclusively, to argumentation mining (the field of computer science that aims at extracting and analysing arguments from natural dialogue). His previous works have tackled the classification of arguments from presidential debates using audio-textual information, and he has developed datasets for this purpose.

He is also interested in the application of these multimodal machine learning techniques in computational social (political) science, from social media analysis to the study of public deliberation and parliamentary debates. He collaborates in the ‘Rebooting Democracy’ project, where he works in the development of digital tools for public deliberation based on argumentation maps and in the development of democratic innovations based on citizens’ assemblies or mini publics.

He is interested in the ethical and social implications of emergent technologies, as well as their public co-governance and co-design. For instance, his PhD research was focused on the development of bio-hybrid robotics (small bio-actuators composed of lab-grown muscle tissue that can move thanks to its contractions) and he is now concerned about the social implications of this technology, its governance and regulatory aspects. Currently, he is studying the biases and ethical aspects of novel machine learning technologies like large language models (LLMs), and the social critiques around them.

Finally, his interdisciplinary research bridges to other fields, like biomedical engineering, environmental science or digital humanities. He works in projects detecting and classifying maritime events from distributed acoustic sensing (DAS) systems using multimodal machine learning in collaboration with the National Oceanography Institute (NOC) and the detection and classification of sea pens in seafloor footage in collaboration with the Centre for Environment, Fisheries and Aquaculture Science (Cefas). He is currently PI of a University-funded project in digital humanities around multimodal machine learning and interactivity in an immersive space.