Featured Project

Automate Research Data Collection with LLM Intelligence

Transform weeks of manual paper review into hours. Extract entities, structure events, and build quantitative datasets from qualitative sources—powered by Large Language Models and designed for researchers.

Why Researchers Choose This Solution

Dramatically Reduce Data Collection Time

Automate the manual work of extracting data from hundreds of papers. Focus on analysis, not data entry.

Automatic Entity Recognition

Identify dates, locations, actors, and event attributes from any text source with LLM-powered parsing.

Process Multiple Sources Simultaneously

Collect data from news articles, reports, academic databases, and policy documents in parallel.

Maintain Research Standards

Full methodology transparency and reproducible workflows that meet academic research requirements.

Structure Unstructured Data

Convert qualitative text into quantitative datasets ready for statistical analysis.

Validated Output Quality

Built-in quality checks and validation ensure data accuracy and consistency.

Try the Tool Now

Interactive demo - no signup required

Technology Stack

Python LLMs Web Scraping NLP Streamlit API Integration

More Projects

Proof of Concept

PRO-TEST: Protest Violence Prediction

A machine learning proof-of-concept developed to predict the likelihood of violence at protest demonstrations. This educational project demonstrates the application of supervised learning to social science research questions.

13,000+ protest event records
80% prediction accuracy
Le Wagon Bootcamp Capstone (2022)
Python Scikit-learn Pandas Random Forest Streamlit

Educational project demonstrating technical proficiency in machine learning workflows, data preprocessing, model training, and deployment.

Interested in Research Collaboration?

I'm open to collaborating on research projects involving protest event data, Arabic-language text analysis, or machine learning applications for social science research.