I am interested in how social research is evolving in the digital age. In 2024, I joined a dual career PhD programme at the United Nations University - Maastricht Economic and Social Research Institute on Innovation and Technology (UNU-MERIT), and in 2019 and 2020, I enrolled in courses on Machine Learning and Programming for Data Science at the Department for Continuing Education at the University of Oxford. Below is a small portfolio of selected projects coming from these experiences.
Large Languagge Models: Building a local-RAG (November 2025)
Using LLMs to make sense of large unstructured data sources.
Text Analysis: PDF to Python (July 2020)
How to extract words from a pdf file and conduct some basic text analysis.
Text Analysis: Natural Processing Language (June 2020)
Text analysis, Sentiment Analysis and Topic Modelling using open-ended survey data.
Machine Learning: Supervised Learning (April 2020)
Predict the level of humidity given all the other parameters in the SZEGD weather dataset, from Kaggle (https://www.kaggle.com/budincsevity/szeged-weather)
On this topic, check out also:
Coronavirus and web data analysis, a podcast I recorded with Nicole Schwitter, author of Going digital: web data collection using Twitter as an example, and Alexia Pretari, where we discuss how web and social media data can be used to understand our reality, as well as its limitations and ethical considerations;
GDPR and the right to privacy in practice for impact evaluations, a podcast, recorded with Jaynie Vonk, where we discuss GDPR, data security and data privacy for impact evaluations;
Big data and development research, a paper written together with Nicole Schwitter, Alexia Pretari, William Marwa, and Ulf Liebe and published in Frontiers in Sociology.