This repository contains Jupyter notebooks and resources for the work-in-progress textbook on computational social media analysis. The notebooks will cover various topics related to social media data analysis, natural language processing, and machine learning.
Notes on (Computational) Social Media Research is a work-in-progress website being developed by Michael Achmann as part of his Ph.D. research and teaching at the Chair for Media Informatics, University of Regensburg. The textbook aims to provide comprehensive guidance on computational social media analysis, exploring various methodologies, techniques, and tools for social media research and will accompany the research seminar "Computational Analysis of Visual Social Media" in the 2023/24 winter semester.
Additional tutorials are available on Medium, the corresponding notebooks are hosted in the ig-tutorial repository.
As the project is still in progress, the notebooks will be added to the notebooks/directory gradually. Stay tuned for updates!
The repository may also include datasets for use with the notebooks. If applicable, datasets will be made available in the datasets/ directory.
To use the notebooks in this repository, you have two options:
You can run the Jupyter notebooks locally on your computer. To do this, you will need to have Jupyter Notebook installed. If you don't have it installed, you can follow the installation instructions on the Jupyter website. Once you have Jupyter Notebook installed, you can clone this repository using the following command:
git clone https://github.com/michaelachmann/social-media-lab.gitThen, navigate to the repository directory:
cd social-media-labStart the Jupyter Notebook server:
jupyter notebookOpen any notebook file (e.g., example_notebook.ipynb) to begin exploring social media analysis techniques.
If you prefer to use Google Colab, you can run the notebooks directly from your web browser. Google Colab is a free cloud-based platform that provides access to Jupyter notebooks with integrated GPU support. It allows you to run code, including Python and TensorFlow, on Google's servers without any local installation.
To run a notebook in Google Colab, simply click on the "Open in Colab" badge 
Please note that while Google Colab is convenient for quick experimentation, you might need to sign in with your Google account and save a copy of the notebook to your Google Drive for long-term storage.
We welcome contributions to the project. If you have ideas, improvements, or would like to add new notebooks or datasets, please open an issue or submit a pull request. For significant contributions, please first discuss the changes in the issues section.
The content of this project, including the Jupyter notebooks and other resources, is licensed under the GNU General Public License version 3.0 (GPL-3.0). For more details, see the LICENSE.md file.
Please use one of the following options for citing the content of this repository when using the notebooks and examples in your academic work.
Michael Achmann. (2023). michaelachmann/social-media-lab: DOI Release (v0.0.1). Zenodo. https://doi.org/10.5281/zenodo.8199902
@software{michael_achmann_2023_8199902,
author = {Michael Achmann},
title = {michaelachmann/social-media-lab: DOI Release},
month = jul,
year = 2023,
publisher = {Zenodo},
version = {v0.0.1},
doi = {10.5281/zenodo.8199902},
url = {https://doi.org/10.5281/zenodo.8199902}
}If you have any questions or need further assistance, you can reach Michael Achmann at:
- Website: Michael Achmann
- Email: [email protected]