Hi, I'm Aida

Data Scientist & AI Engineer

I first got into NLP during my Master's in Taiwan, studying how people express blame on Twitter and discovering that self-blame is a stronger marker of depression than blaming others. That question of what language reveals stayed with me, and motivated my work in NLP.

View Projects Get in Touch

About Me

Dr. Aida Halitaj

I'm a data scientist and AI engineer based in London, currently at BT Group where I work on anomaly detection systems for large-scale mobile networks.

I hold a PhD in Computer Science from Queen Mary University of London, where my research focused on NLP for citation worthiness detection in low-resource Wikipedia languages.

Before my PhD, I led data science at Dua AG, driving product decisions through data analysis, ML modeling, and experimentation impacting user conversions and retention. My background spans NLP, deep learning, MLOps, and cloud infrastructure (AWS, GCP, Spark, Docker), with experience across research, startups, and enterprise.

I studied at Queen Mary University of London (PhD), National Tsing Hua University in Taiwan (MSc), and the University of Prishtina (BSc in Mathematics & Computer Science).

Outside work, most of my time belongs to my two-year-old son. I'm originally from a small village near Drini i Bardhë waterfall in Peja, Kosovo and that love of nature stuck. Thailand has been one of my favourite places so far; One day I would love to visit Hawai. When I get the chance, I enjoy swimming, skiing, badminton, and volleyball. I speak Albanian and English.

Projects

Customer Churn Prediction

End-to-end MLOps project — reproducible ML pipeline with DVC, interactive prediction dashboard with reactive sliders and what-if analysis, FastAPI backend, drift monitoring with PostgreSQL, and CI/CD deployment to Fly.io.

Python scikit-learn FastAPI DVC Docker Fly.io GitHub Actions

Publications

  1. ALPET: Active Few-Shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages

    Aida Halitaj, Arkaitz Zubiaga

    Expert Systems with Applications, vol. 281, 127503, 2025

    ScienceDirect arXiv

  2. Providing Citations to Support Fact-Checking: Contextualizing Detection of Sentences Needing Citation on Small Wikipedias

    Aida Halitaj, Arkaitz Zubiaga

    Natural Language Processing Journal, vol. 8, 100093, 2024

    ScienceDirect

  3. Towards Automating Citation Worthiness Detection for Sentences in Low-Resource Languages

    Aida Halitaj

    PhD Thesis, Queen Mary University of London, 2025

    Google Scholar

  4. Syntactic Features of Blaming in Social Media

    Aida Halitaj

    MSc Thesis, National Tsing Hua University, 2019

    Google Scholar

Resume

Data Scientist & AI Engineer at BT Group. PhD in Computer Science from Queen Mary University of London, specialising in NLP and few-shot learning. Experience across research, startups, and enterprise — from building ML pipelines on AWS to publishing in top Elsevier journals.

Blog

Coming Soon

I'll be sharing thoughts on NLP research, data science, and more.

Contact

Feel free to reach out! I'm always open to interesting conversations and collaborations.

GitHub LinkedIn Email Google Scholar