Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/soxoj/bellingcat-hackathon-watchcats
📊 Adana - 1-click analytical dashboard for OSINT researchers
https://github.com/soxoj/bellingcat-hackathon-watchcats
analytics bellingcat dataset datasets hackathon sentiment-analysis topics-classification twitter twitter-sentiment-analysis
Last synced: 10 days ago
JSON representation
📊 Adana - 1-click analytical dashboard for OSINT researchers
- Host: GitHub
- URL: https://github.com/soxoj/bellingcat-hackathon-watchcats
- Owner: soxoj
- License: mit
- Created: 2023-11-15T12:53:06.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2024-04-23T14:42:29.000Z (7 months ago)
- Last Synced: 2024-10-17T15:39:10.221Z (19 days ago)
- Topics: analytics, bellingcat, dataset, datasets, hackathon, sentiment-analysis, topics-classification, twitter, twitter-sentiment-analysis
- Language: Jupyter Notebook
- Homepage: https://adana.soxoj.com
- Size: 7.01 MB
- Stars: 33
- Watchers: 3
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Adana: Analytical DAshboard (for NArratives)
📊 1-click analytical dashboard for OSINT researchers
#### 👉 [Try Adana online](https://bellingcat-hackathon-watchcats-uearyc7iggn84xznppgq5k.streamlit.app/)
## The idea
Analytical tool to extract insights (shown on a simple dashboard) from social media posts about narratives, sentiments, initiators, influencers and clusters of accounts.
It should be applicable for studying disinformation campaigns, analysing public opinion, and assessing risks related to some topics.
It's a project created by team Watch Cats during participation in [Bellingcat's First In-person Hackathon](https://www.bellingcat.com/bellingcats-first-in-person-hackathon/).
Inspired by [4CAT](https://4cat.nl/) and [twitter explorer](https://twitterexplorer.org/).
The development process is documented in [this Google document](https://docs.google.com/document/d/10xOgmZmvLM-BJeak-KNXzkx7H5oqnbn834-o94WbM50/edit#heading=h.m0d3jrsts18t).
# MVP
Available by the link: https://bellingcat-hackathon-watchcats-uearyc7iggn84xznppgq5k.streamlit.app/
## Team members
**[@soxoj](https://soxoj.com/)**, **[@dizvyagintsev](https://github.com/dizvyagintsev)**
## Datasets
[Twitter posts on various topics (1-20K)](https://drive.google.com/drive/u/0/folders/1GtUZkfD0cZ2xBBZ3FiDpH1Cgw_u-m1wh), including datasets enriched with topics and sentiments.
Instructions:
- [How to prepare dataset with Zeeschuimer](https://docs.google.com/document/d/19MAiqX7Vx1FcNJ44K-vSdnKDVC5gcFwtrSQiewnwW8A/edit)
- [How to prepare CSV dataset](https://docs.google.com/document/d/1TTulgfIhSEZRQODRem9ufJWXZ7tGJdHEVYSVk8Teit4/edit)
- Check utils/cluster_n_sentiments.ipynb for instructions on how to enrich datasets with sentiments and topics
**How can I get topics and sentiments for my dataset?** Cause it’s a resource- and time-consuming operation, we implemented it in the Jupyter Notebook script available on our GitHub. For tweets vectorization we are using hkunlp/instructor-large model, for clusterization – MiniBatchKMeans, for the detection of topics – GPT-4-Turbo API, for the sentiment analysis of tweets – cardiffnlp/twitter-roberta-base-sentiment-latest mode. All steps are reproducible.
## Installation
For local installation you need Python and pip installed.
```sh
pip install -r requirements.txt
streamlit run dashboard.py
```
For private cloud installation, you need:
1. Login (register) to GitHub
2. Fork [this repository](https://github.com/soxoj/bellingcat-hackathon-watchcats/fork)
3. Login (register) in [Streamlit](https://streamlit.io/) by GitHub account
4. Create a new project in Streamlit from a forked repository
5. Deploy (*no payment method required!*)
6. Voila!
## Utils
`utils` folder contains:
- CSV tweet datasets formatter (to Twitwi)
- `cluster_n_sentiments.ipynb`: ML stuff (enrichment of datasets with sentiments and topics)
### SOWEL classification
This tool uses the following OSINT techniques:
- [SOTL-5.2. Analyse Sentiments](https://sowel.soxoj.com/sentiments)
## Some other results
An example of a hashtag network built with [Twitter Explorer](https://twitterexplorer.org/) using one of the datasets
