Yolina Petrova, PhD
Chief Operations & AI Officer, Identrics
Yolina combines Cultural Studies and Cognitive Science. She is Chief Operations & AI Officer at Identrics and lectures Statistics and cognitive courses at NBU. Her research focuses on trust dynamics between humans and AI systems and cognitive modelling.
Credentials
- PhD Cognitive Science
- Lecturer, New Bulgarian University
Areas of expertise
- Cognitive science
- Responsible AI
- Human-AI trust
- Large language models
Selected appearances
2022
The Importance of ELG for the Media Intelligence Industry
Speaker, European Language Grid META-Forum
View presentation
Research and publications
2025
WASPer: A Bulgarian-Language Model for Detecting Propaganda in Social Media Content
Lead author
With Todor Kiriakov, Devora Kotseva, and Boryana Kostadinova
Read the paper2021
Monitoring Fact Preservation, Grammatical Consistency and Ethical Behavior of Abstractive Summarization Neural Models
Co-author, RANLP 2021
With Iva Marinova, Milena Slavcheva, Petya Osenova, Ivaylo Radev, and Kiril Simov
Read on ACL Anthology2019
Relation-based categorization and category learning as a result from structural alignment: The RoleMap model
Co-author, Frontiers in Psychology
With Georgi Petkov
Read the paper2019
Crossmodal Spatial Mappings as a Function of Online Relational Analyses?
Co-author, Cognitive Science Society proceedings
With Yoana Zafirova and Georgi Petkov
Read the paper
Projects
2024-2025
WASPer
Research lead and co-author
An open-source Bulgarian-language model for detecting synthetic text and propaganda techniques.
Explore WASPer2026
PROPer-BG and Bulgarian AI-text detection research
Co-author
Bulgarian-language datasets and methods presented through the CLIB research programme.
View research announcement
Posts by Yolina Petrova
Product · 1 May 2025
What Is Entity-Based Sentiment Analysis?
Beyond general sentiment - pinpoint exactly who or what people feel positive or negative about, and why it matters for media intelligence.
Read postProduct · 22 Jun 2024
What It Takes to Tailor and Fine-Tune Large Language Models
What large language models are, how they are pre-trained and fine-tuned, and why responsible AI development matters.
Read post