Welcome to the website of Sean Hamilton Palicki. I am a data scientist and social science researcher with 12+ years of experience working at the intersection of AI, big data, and applied statistics. I specialize in natural language processing, large language models, and building end-to-end data analytics using Python, R, and Spark.

I have worked at agile startups and in academic research groups across the US and Europe, with a focus on designing responsible AI systems that support social good, sustainability and continuous quality improvement.

Academic Research

I have an MSc in Big Data Analytics from Birmingham City University (UK) and I’m currently completing a PhD in Computational Social Science at the Technical University of Munich (GER), where I use big data and AI for media and political communication research. My doctoral work is conducted in collaboration with the Emmy Noether Junior Research Group, under the supervision of Dr. Stefanie Walter at TUM and Dr. Wouter Van Atteveldt at VU Amsterdam.

In my research, I analyze millions of international news articles using large-scale NLP, AI and machine learning methods to compare media portrayals of diverse social groups. I also identify how seemingly “neutral algorithms” can reinforce discrimination, bias and inequality related to immigration, race and ethnicity, gender, religion and social status, while proposing more aligned solutions.

I’ve published in peer-reviewed journals, presented at international conferences, delivered workshops, and developed open-source tools for researchers.

  • Podcast Interview: In this interview with the “What is it about computational communication science?” podcast, I discuss my paper about multilingual information retrieval, vector databases and the hidden validity risks of machine translation tools.

Applied Data Science

In my previous role, I was a founding developer and later Director of Product Development at Acorn Evaluation, a data science training and evaluation company. Acorn primarily supports the Head Start program of the US Department of Health and Human Services, which provides early childhood education and health services to low-income children and families. During my 6 years there, I led data processing and analysis efforts to deliver automated visualization dashboards, service maps, and impact reports. This role combined software development with consulting, as I traveled across the US conducting program evaluations and delivering data literacy workshops for executives, educators and policymakers.

While many projects remain private, here’s an annual report that includes my data quality research efforts and (below) one of my public projects.

  • Head Start Map: Visualizing how early childhood services were distributed across California. This kind of impact data played a role in defending the program during proposed budget cuts under the Trump administration (see more data science in political advocacy).

As I near the end of my doctorate, I’m seeking a role where I can continue advancing NLP, LLMs, and responsible AI within R&D groups, mission-aligned startups, or innovative data science teams.

You can find me on the following platforms: