https://github.com/aieng-lab/replication-kit-qtgpt-study
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.3%) to scientific vocabulary
Last synced: 9 months ago
·
JSON representation
Repository
Basic Info
- Host: GitHub
- Owner: aieng-lab
- License: apache-2.0
- Language: Jupyter Notebook
- Default Branch: main
- Size: 8.18 MB
Statistics
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 1
Created almost 2 years ago
· Last pushed almost 2 years ago
Metadata Files
Readme
License
README.md
Replication package
This repository contains the code and data in a study on the ability of large language models to impersonate public speakers in political debates.
Requirements
- Python 3 (tested with Python 3.10)
Structure
data/: Contains the data used in the experiments, including the debate questions, answers, generated answers, speaker biographies, linguistic markers, code book of the free text answers, and the results of the manual coding.figures/: Contains the figures generated in the analysis.markers/: Contains helper files with lists of linguistic markers required for the calcuation of the linguistic surface.- statistical_analysis.ipynb: Jupyter notebook with the statistical analysis of the data.
- calclingusticfeatures.ipynb: Jupyter notebook with the code to calculate the linguistic features that describe the linguistic surface.
Usage example for Ubuntu 22.04
Exectute the following commands in the terminal to clone the repository and install the required packages.
bash
git clone git@github.com:aieng-lab/replication-kit-qtgpt-study.git
cd replication-kit-qtgpt-study
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
You can then start Jupyter Lab and open it in a browser to view and execute the Juypter notebooks.
bash
jupyter lab
Owner
- Name: aieng-lab
- Login: aieng-lab
- Kind: organization
- Website: https://www.fim.uni-passau.de/ai-engineering
- Repositories: 1
- Profile: https://github.com/aieng-lab
GitHub organization of the Chair for AI Engineering of the University of Passau
GitHub Events
Total
Last Year
Dependencies
requirements.txt
pypi
- jupyterlab *
- lexicalrichness ==0.5.1
- matplotlib ==3.8.4
- numpy ==1.26.4
- pandas ==2.2.2
- pingouin ==0.5.4
- scipy ==1.13.0
- seaborn ==0.13.2
- spacy ==3.7.5
- statsmodels ==0.14.2