🎓THIS WEBSITE IS UNDER CONSTRUCTION (LAST MODIFICATION: 25/09/26)
I am Associate Professor at Università di Bologna since 2022 (after three years as Senior assistant professor; RTDb, in the Italian system). I have been working on the (cross-language) assessment of text looking at different aspects such as originality (e.g., plagiarism detection) and intent (e.g., propaganda, hate speech).
Since 2025, I serve as co-chair of the CLEF initiative, which promotes research, innovation, and development of information access systems with an emphasis on multilingual and multimodal information with various levels of structure. I am also special chief editor of the NLP Section of Frontiers in AI
Visit my UniBO website for university matters.
Before landing at UniBO, I spent 5 years as a Scientist at the Language Technologies group of QCRI and 2 as research fellow at TALP.
Publications
Citations
h-index
I am an Associate Professor at Università di Bologna. My main mission is bringing (real) computing to the Department of Interpreting and Translation.
I research on the analysis and identification of harming contents online —from hate speech to propaganda and disinformation. I was the PI of projects GIARA and !Trans, where we explored NLP solutions for Gastronomy. Laterly I am engaged with varieties of languages.
Do not hesitate to reach out 😃
Overview On the evening of the 29th of April, the efforts of over 40 parents from the city of Forlì, concerned with a healthy use of technology by young people (from social media to smart devices), culminated with the signature of the first Patto Digitale of the city of Forlì (Italy).
Overview Dependency parsing is the task of inferring natural language structure, often approached by modeling word interactions via attention through biaffine scoring. This mechanism works like self-attention in Transformers, where scores are calculated for every pair of words in a sentence.
Overview Research on knowledge graph construction (KGC) has recently shown great promise also thanks to the adoption of large language models (LLM) for the automatic extraction of structured information from raw text.
Overview This study examines whether the psycholinguistic and demographic characteristics of authors of online texts are correlated with the way harmful language, such as toxicity and hate speech, is judged. We apply artificial intelligence models to two harmful language datasets, Jigsaw’s Special Rater Pool dataset and the Measuring Hate Speech dataset, to generate probabilities for different text aspects, namely inferring demographic information of the author behind the suspicious text in terms of age and gender, as well as the expressed emotions, emotionality, sentiment and communication style.
Overview Electronic mail (email) is one of the most popular communication media for direct and private communication. Being typically a free service and anonymity-friendly, massive spam email campaigns are common. Nowadays, spam email encompasses scam, phishing, malware distribution, and various other cybersecurity threats.
