Case Study of Analysis of Emoji Usage in Tweets at network level

This repository contains the scripts can collect tweets from the Twitter Streaming API using Python, save data in the local MongoDB database and data pre-processing for building a Co-mention Emoji Network.

Introduction

Twitter Emoji Co-mention Network.

This project begins to explore how the emoji network structure may compare to that of the accompanying text language network.

Process:

Streamline Twitter API calls for tweets containing keyword “art”
Save to MongoDB
Extract and preprocess the data

Setup instructions

Open terminal/command prompt.
Clone the repository to your local system in a dedicated folder.
CD to the repo directory.

Create and activate a virtual environment for this project.

On macOS or Linux:

python3 -m venv env
source env/bin/activate
which python

On Windows:

py -m venv env
.\env\Scripts\activate
where python

Install necessary packages
```
pip install -r requirements.txt
```

Run instructions

Set up your local database, run python mongodb_setup.py
Remember to modify your own configure information at config.py.
Run python stream_twitter.py to collect tweets from the Twitter Streaming API
Run python mongodb_df.py to extract useful tweets and write in a csv file. Can take different filter statements.

Quit instructions

Deactivate the venv to return to your terminal using deactivate.

Usage

Authors

Fangfang Sheng