Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/michael-spengler/slack-channel-sentiment-analyzer
https://github.com/michael-spengler/slack-channel-sentiment-analyzer
Last synced: 26 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/michael-spengler/slack-channel-sentiment-analyzer
- Owner: michael-spengler
- Created: 2021-04-14T07:25:06.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2021-05-04T14:36:15.000Z (over 3 years ago)
- Last Synced: 2024-05-09T18:59:51.990Z (6 months ago)
- Language: Python
- Size: 205 KB
- Stars: 4
- Watchers: 4
- Forks: 1
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# slack-channel-sentiment-analyzer
## Execute SA Server Locally
### Prerequisites
```sh
brew install python3
```
```sh
pip3 install -r requirements.txt
```
Create a `.env` file inside the `server` folder using the template file `.env.template`. Add all the required environment variables to the file (e.g. Slack bot token).
```sh
cd server
uvicorn main:app --reload
```
## How it Works
We created a Slack App called [Sentiment Analyzer](https://api.slack.com/apps/A01UWSD1YMT) which has the corresponding read messages of public channels permissions - see scopes file in assets folder.
We added this Slack App (via a slash command ("/invite")) in all channels for which we would like to conduct the sentiment analysis - see also screenshot in assets folder.
We took the token from "OAUTH Tokens for your Workspace".
... Raise an issue in case of questions.
... Raise a PR in case of improvement proposals.
## Background Info
### Retrieving Messages incl. Thread Messages
https://api.slack.com/messaging/retrieving
### Potentially Helpful Links
1. https://huggingface.co/transformers/model_doc/gpt.html
2. https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment
3. https://huggingface.co/transformers/quicktour.html