README.md

---
title: Tweet NLP Sentiment Analysis
emoji: 🐦
colorFrom: indigo
colorTo: gray
sdk: streamlit
app_file: app.py
pinned: true
---

# Configuration

`title`: _string_  
Display title for the Space

`emoji`: _string_  
Space emoji (emoji-only character allowed)

`colorFrom`: _string_  
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)

`colorTo`: _string_  
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)

`sdk`: _string_  
Can be either `gradio` or `streamlit`

`sdk_version` : _string_  
Only applicable for `streamlit` SDK.  
See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.

`app_file`: _string_  
Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
Path is relative to the root of the repository.

`pinned`: _boolean_  
Whether the Space stays on top of your list.

# HISTORY OF THIS PROJECT
 1. This project began when I saw the Twitter announcement by Facebook that they were re-branding to Meta, and I was curious what the public sentiment of this announcement would be. I suspected that it would be more negative than positive due to various reasons, but I wanted to find out nonetheless.
 
 2. Tweet replies from the Facebook/Meta announcement were extracted using Twitter's API, then saved to a CSV file.
 
 3. Due to Twitter's developer policies, I cannot share that file of extracted Tweet replies and associated metadata, so I ran sentiment analysis on those Tweet replies outside of this app and saved the results to the `df_redacted.csv` file. This file DOES contain the ids of the tweets which were analyzed, which is allowed per Twitter's policies. The sentiment model I used was VADER.
 
 4. In future revisions, I plan on finding a way to post my code from the extraction portion of the project, along with demonstrating various methods of cleaning the Tweets and how that affects the outcome of the analysis.