This repository is for the "Text as Data for Islamist Data" Project, including the Widening participation internship.
In the internship we have three aims:
- Text pre-processing tasks in English translations
- Text pre-processing tasks Arabic
- Compare results of English and Arabic Natural Language Processing, for either:
- Key words (as provided by Filippo) over time
- Most frequent words over time
- Comparison of Jerusalem Day speeches versus background
Later, we hope to bring this code into Filippo's Orange workflow to form part of future analyses.
| Team Member | Role | Internship Responsibilities |
|---|---|---|
| Filippo Dionigi | Principal Investigator | Providing data and advising on Arabic language and Middle Eastern politics. |
| Natalie Thurlby | Data Scientist, Jean Golding Institute | Advising on text analysis, reproducibility, and research software engineering best practices. |
| Bashir Ahmadi | Data Science Intern | Programming and writing up. |
This GitHub repository is where we are storing all code relating to the project. The code is Open Source under an MIT license.
This project was funded by the Jean Golding Institute as part of the University of Bristol's Widening Participation Internship Scheme.
Please contact [email protected] with any queries about this repository.