A researcher from the University of Bucharest has received the award for the best doctoral thesis in Natural Language Processing (NLP), as part of the 42nd International Congress of SEPLN – Sociedad Española para el Procesamiento del Lenguaje Natural, held from September 22 to 25 at the University of León, Spain.
The award was presented to Ana-Maria Bucur for her thesis, “Computational Approaches to Mental Health Disorders Detection from Social Media Texts, Images and Videos – PDF,” carried out within the Interdisciplinary School of Doctoral Studies (ISDS) of the University of Bucharest, in co-supervision with Universitat Politècnica de València. The thesis was supervised by Prof. Liviu P. Dinu, PhD, faculty member at the Faculty of Mathematics and Computer Science of the University of Bucharest, and Prof. Paolo Rosso, faculty member at Universitat Politècnica de València in Spain.

The thesis investigates how natural language processing methods and computational models can be used to identify indicators associated with mental health problems in content published on social media.
Among other topics, the research addresses the detection of depression, self-harm behaviors, and pathological gambling by analyzing linguistic patterns in data collected from social media. An important element of the thesis is the use of multimodal approaches, which combine information from text, images, and videos.
Ana-Maria Bucur completed her doctoral studies within the Interdisciplinary School of Doctoral Studies (ISDS) of the University of Bucharest, in co-supervision with Universitat Politècnica de València. Her public defense took place on October 6, 2025.
The SEPLN Award for the Best Doctoral Thesis in Natural Language Processing reached its 25th edition in 2026. According to the competition rules, the award aims to promote and disseminate research in the field of natural language processing, with theses evaluated according to criteria such as quality of presentation, technical and methodological rigor, relevance, originality, development and evaluation of resources, and the researcher’s scientific trajectory during the doctoral period.

This year, the award is presented during the 42nd International Congress of the Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN 2026), a congress that brings together researchers, professionals, companies, and students from several countries around the latest developments in natural language processing and computational linguistics.
The SEPLN 2026 award thus brings into focus doctoral research carried out at the University of Bucharest and developed through an international collaboration at the intersection of artificial intelligence, computational linguistics, and the analysis of data available on social media.



