Scholar
Dirk Hovy
Google Scholar ID: 7xluaTAAAAAJ
Bocconi University
Natural Language Processing
Machine Learning
Computational Sociolinguistics
Computational Social Science
Ethics in NLP
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
10,232
H-index
46
i10-index
97
Publications
20
Co-authors
175
list available
Contact
Email
dirk.hovy@unibocconi.it
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
22 items
Diffusion Language Models Are Natively Length-Aware
2026
Cited
0
Do Large Language Models Adapt to Language Variation across Socioeconomic Status?
2026
Cited
0
PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors
2026
Cited
0
Do Prompts Reshape Representations? An Empirical Study of Prompting Effects on Embeddings
2025
Cited
0
SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
2025
Cited
0
Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
2025
Cited
0
Biased Tales: Cultural and Topic Bias in Generating Children's Stories
2025
Cited
0
No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
Authored over 150 articles on these topics
Recipient of 3 best paper awards and 1 outstanding paper award
Published two textbooks on text processing in Python for social scientists
Co-founded and organized workshops on computational social science and ethics in NLP
Local organizer for EMNLP 2017 conference
Research Experience
Former CS faculty at the University of Copenhagen
Awarded an ERC Starting Grant (2020) for research on demographic bias in NLP
Leads multiple research projects, including:
- INDOMITA: Innovative Demographically-aware Hate Speech Detection in Online Media in Italian
- MENTALISM: Measuring, Tracking, and Analyzing Inequality using Social Media
- INTEGRATOR: Incorporating Demographic Factors into Natural Language Processing Models
- MiMac: Mixed methods for analyzing political parties’ promises to voters during election campaigns
- Twitter Healthy Conversations: Devising Metrics for Assessing Echo Chambers, Incivility, and Intolerance on Twitter
Background
Full Professor in the Computing Sciences Department of Bocconi University, Milan
Co-leads the MilaNLP lab with Debora Nozza
Scientific Director of the Data and Marketing Insights research unit
Research interests focus on the interaction between language, society, and machine learning
Also interested in ethical issues of bias and algorithmic fairness in machine learning
Co-authors
175 total
Federico Bianchi
TogetherAI
Barbara Plank
Professor, LMU Munich, Visiting Prof ITU Copenhagen
Debora Nozza
Assistant Professor, Bocconi University
Anders Søgaard
Full Professor in NLP and Machine Learning, University of Copenhagen
Co-author 5
Paul Röttger
Postdoctoral Researcher, Bocconi University
Eduard Hovy
University of Melbourne, CMU
Giuseppe Attanasio
Postdoctoral Researcher, Instituto de Telecomunicações
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up