Ana Freire

Research topics

Artificial Intelligence (AI), Social Media Analysis, Mental Health, Bioinformatics, Web Search, Diversity and AI.

Leading the following Projects

• Artificial Intelligence and Mental Health
• STOP (Suicide prevenTion in sOcial Platforms)
• Project addressed to study mental health issues in social platforms. We increased by 60% the calls incoming from social media to a national hotline. In collaboration with: Universitat Pompeu Fabra, Computer Vision Centre (UAB), Hospital Parc Taulí, FITA Fundació, Fundació Ajuda i Esperança, Università della Svizzera Italiana, Université de Lyon.

• Diversity in Artificial Intelligence
• divinAI (diversity in Artificial Intelligence)
• We measure the diversity regarding sex, geographical location and business (academia vs industry) in top Artificial Intelligence conferences. In collaboration with: Universitat Pompeu Fabra, Joint Research Centre (European Commission).

• Gender gap in STEM
• Wisibilízalas
• International contest adressed to Primary and Secondary Schools to break gender stereotypes associated with STEM carreers. More than 3700 students from 5 different countries created more than 1200 websites including profiles of professional women in STEM. In collaboration with: Universitat Pompeu Fabra, FECYT (Spanish Ministry of Science and Innovation).

Highlighted Publications

• Characterization of Anorexia Nervosa on Social Media: Textual, Visual, Relational, Behavioral, and Demographical Analysis. Journal of Medical Informatics.
• Detection of Suicidal Ideation on Social Media: Multimodal, Relational, and Behavioral Analysis. Journal of Medical Informatics.
• Measuring Diversity of Artificial Intelligence Conferences. AAAI Workshop on Diversity in Artificial Intelligence.
• Enhanced Word Embeddings for Anorexia Nervosa Detection on Social Media. Advances in Intelligent Data Analysis XVIII.
• UPF's Participation at the CLEF eRISK 2018: Early Risk Prediction on the Internet. Conference and Labs of the Evaluation Forum (CLEF 2018).
• Understanding and Leveraging the Impact of Response Latency on User Behaviour in Web Search. ACM Transactions on Information Systems.
• A self-adapting latency/power tradeoff model for replicated search engines. 7th ACM international conference on Web search and data mining.