Skip to content
View Emeierkeio's full-sized avatar
🎯
Focusing
🎯
Focusing
18 followers · 13 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report Emeierkeio

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
emeierkeio/README.md

Ciao, I'm Mirko 👋

Typing intro

LinkedIn X ORCID Email

Data scientist working on retrieval-augmented generation over knowledge graphs. The goal is AI answers you can verify: who said it, and with what authority.

  • 🎓 MSc Data Science @ University of Milano-Bicocca · BSc Computer Science @ University of Bologna
  • 📄 First-author paper at ISWC 2026 (In-Use Track): Who Speaks Matters
  • 🌱 Currently exploring: semantic axes for political-position mapping, temporal stance evolution
  • 📍 Rome / Roseto degli Abruzzi / Milan, Italy

🏛️ Featured — ParliamentRAG

RAG over the debates of the Italian Chamber of Deputies, with retrieval weighted by speaker authority. 45k+ full-text speeches and 6.3M individual votes; every citation is checked verbatim against the official record.

Live demo Source Dataset DOI ORKG ISWC 2026

🧰 Stack

Python TypeScript FastAPI Next.js Neo4j RDF / SPARQL OpenAI Docker Railway LaTeX

Pinned Loading

  1. ParliamentRAG ParliamentRAG Public

    Authority-aware, multi-view Graph-RAG over Italian parliamentary proceedings (ISWC 2026 In-Use). Neo4j knowledge graph with 170k+ speech chunks and 6.3M individual votes, balanced majority/oppositi…

    Python 2