EPSRC Centre for Doctoral Training in Cyber Security

 dominika.nadia.wojtczak@bristol.ac.uk

Year 4 Student – 2020 Intake – Cohort 2

I did a MSc in Computer Science at the University of Bath where I have submitted my dissertation on Security of Online Payments. I have also had work experience in Data Analysis, Data Engineering and Data Science. My current research is on online misinformation, textual analysis (NLP), LLMs and cognitive analysis. Other interests include: ML, behavioural studies and IT law.

A Multimodal Machine Learning Based Study of Online Misinformation

My research focuses on a multimodal machine learning approach to studying online misinformation, focusing on underexplored modalities (e.g., images and videos, behavioural cues). After examining these modalities and text-based content, I began evaluating the cognitive abilities of large language models (LLMs) in detecting and interpreting misinformation. My work compares LLM performance with human annotators on tasks requiring complex judgment. I also investigate how different prompt-engineering strategies affect model performance and address ethical considerations in deploying LLMs for content moderation.

Supervisors: Dr Ryan McConville (Bristol), Dr Cheryl McQuire (Bristol), Luisa Zuccolo (Bristol), Dr Claudia Peersman (Bristol) 

wojtczak_poster_jan25 (PDF, 444kB)

Y1 Academic placement  with Dr. Ryan McConville

Y1 Industrial placement with Dr. Pauline Anthonysamy, Staff Privacy Engineer in Android

Study 1: Characterizing Discourse and Engagement Across Topics of Misinformation on Twitter

Study 2: Dataset of annotated X posts with metadata and GPT Responses

Study 3: The Performance of Large Language Models in Cognitive Analysis of Misinformation