Andrea is a Post-Doctoral Research Associate in Latin Linguistics in the Department of Digital Humanities, working on the ERC-selected project Computational Corpus Annotation for Quantitative Analysis of Latin Lexical Semantics (COALA). He holds a PhD in Digital Humanities (King’s College London), which was funded by a UKRI scholarship from the London Arts & Humanities Partnership (LAHP). With a background in Classics (University of Milan) and Theoretical and Applied Linguistics (University of Pavia), he specialises in semantic annotation and has contributed to global projects such as the Greek, Latin, and Sanskrit WordNets. During his PhD, he developed PrevNet, a cross-linguistic database for preverbs, with a case study focusing on Ancient Greek and Latin.

Andrea is committed to advancing open access research, particularly in Classical studies, and serves as Senior Editor and Senior Social Media Editor for the Journal of Open Humanities Data. He is the creator and convenor of the Data in Historical Linguistics international seminar series. He is a member of the Computational Humanities Research Group at King’s and of the Regional Advisory Committee of the Global Council for Anthropological Linguistics for the European area. He is also part of the CLARIN Trainers' Network and leads the King’s Linguistics Network within King’s.

Research interests

• Corpus-based analysis of diachronic semantics in ancient languages, particularly Latin and Ancient Greek, including the syntax–semantics interface- Quantitative analysis of preverbs from a cross-linguistic perspective
• Development of computational tools and methods for Historical Linguistics
• Application of generative AI (e.g. Large Language Models) to quantitative analyses of historical languages
• Data-driven approaches to the Ancient World, with a focus on dataset creation, curation, and their use in Digital and Computational Humanities research

PrevNet is an open, cross-linguistic database of preverbs, and Andrea is keen to expand the resource by incorporating research and data on preverbs from additional languages. Contributions from researchers working on preverbs across different linguistic, historical, and methodological contexts would further enhance the database’s coverage, usability, and effectiveness as a resource for comparative research. Researchers interested in collaborating on PrevNet or contributing relevant datasets are very welcome to get in touch with Andrea by email.

Selected publications

• Farina, Andrea, Michele Ciletti, Barbara Mcgillivray, and Andrea Ballatore. 2026. Sense-Based Annotation of Geographical Nouns in Ancient Greek and Latin: A Diachronic Study with LLMs. In Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature 2026, 266–279, Rabat, Morocco. Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.latechclfl-1.26

• Farina, Andrea, Marco Passarotti, Francesco Mambrini, Matteo Pellegrini, Giovanni Moretti, and Eleonora Litta. 2026. PREMOVE In LiLa: Integrating Latin Preverbed Motion Verbs With WordNet and VerbNet. In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026), 3672-3683. European Language Resources Association (ELRA). https://doi.org/10.63317/3ifm66wvmf86

• Farina, Andrea, and Michele Ciletti. 2026 (Forth). Probing Preverbs: Evaluating Large Language Models on Latin and Ancient Greek Preverbed Motion Verbs. Historical Languages and AI. March 5–6, 2026, Humboldt University Berlin (Germany).

• Farina, Andrea, Paola Marongiu, Mathilde Bru, and Daniele Borkowski. 2025. When data meets the past: data collection, sharing, and reuse in Ancient World studies. Open Information Science, 9, 1-20. https://doi.org/10.1515/opis-2025-0014

• Farina, Andrea. 2024. Guidelines for a linguistic annotation of preverbed verbs of motion. King’s College London. Figshare. https://doi.org/10.18742/25055573.