Thanks for checking out our analysis of large scale news stories in the media ecosystem. This repo contains (or points to) a number of resources for further large-scale study of news using computational methods.
- Our scalable news article similarity model can be found at https://huggingface.co/Blablablab/newsSimilarity.
- Our dataset of millions of news articles with new story cluster labels can be found here: https://huggingface.co/datasets/Blablablab/mediaStorms/blob/main/storyClusterData.tsv.gz
- Our dataset of news articles which have been identified as taking part in media storms between April 2020 and December 2021 can be found here: https://huggingface.co/datasets/Blablablab/mediaStorms/blob/main/mediaStormArticles.tsv
If you would like to rerun our pipeline and create your own news-story clusters, our pipeline for doing so is found in mediaStorms/scripts/similarityAnalysis/runClusteringPipeline.sh. First, pairs of articles which may pertain to the same story or event are identified using Named Entity Recognition. Next, pairwise cosine similarity is computed for all of these pairs using our fine-tuned news-similarity model. Finally, we create a graph based on pairwise similarity, drop edges below a given similarity threshold, and identify the connected components of this graph.
├── LICENSE
├── Makefile <- Makefile with commands like `make data` or `make train`
├── README.md <- The top-level README for developers using this project.
├── data
│ ├── external <- Data from third party sources.
│ ├── interim <- Intermediate data that has been transformed.
│ ├── processed <- The final, canonical data sets for modeling.
│ └── raw <- The original, immutable data dump.
│
├── docs <- A default Sphinx project; see sphinx-doc.org for details
│
├── models <- Trained and serialized models, model predictions, or model summaries
│
├── notebooks <- Jupyter notebooks. Naming convention is a number (for ordering),
│ the creator's initials, and a short `-` delimited description, e.g.
│ `1.0-jqp-initial-data-exploration`.
│
├── references <- Data dictionaries, manuals, and all other explanatory materials.
│
├── reports <- Generated analysis as HTML, PDF, LaTeX, etc.
│ └── figures <- Generated graphics and figures to be used in reporting
│
├── requirements.txt <- The requirements file for reproducing the analysis environment, e.g.
│ generated with `pip freeze > requirements.txt`
│
├── setup.py <- makes project pip installable (pip install -e .) so src can be imported
├── src <- Source code for use in this project.
│ ├── __init__.py <- Makes src a Python module
│ │
│ ├── data <- Scripts to download or generate data
│ │ └── make_dataset.py
│ │
│ ├── features <- Scripts to turn raw data into features for modeling
│ │ └── build_features.py
│ │
│ ├── models <- Scripts to train models and then use trained models to make
│ │ │ predictions
│ │ ├── predict_model.py
│ │ └── train_model.py
│ │
│ └── visualization <- Scripts to create exploratory and results oriented visualizations
│ └── visualize.py
│
└── tox.ini <- tox file with settings for running tox; see tox.readthedocs.io
Project based on the cookiecutter data science project template. #cookiecutterdatascience