/social-data-science

NLP project for creating simple analytic solution by scraping the data from your social.

Primary LanguageJupyter Notebook

social-data-science

NLP project for creating simple analytic solution by scraping the data from your social from your computer AKA. from your jupyter notebook 🤓.

This project still on progress, and it aims to have few functionality:

  1. Web Scraping. 👨‍💻
  2. Simple EDA with cleaning the data. 👨‍💻
  3. Sentiment Analysis with Hugging Face. 🛠️
  4. Advanced Sentiment Analysis with UCC data as the training data. 🛠️

Requirenent

Before you start using this project please checkout the requirement.txt so you can create new environment in your computer without any trouble.

Challenge/Problem in this project

  1. Twitter data will create duplicate since the way twitter handlind their data is unique, but no worries, in EDA notebook I already solved that problem without deleting any valuable data.

Web Scraping (Available👨‍💻)

This web sraping aims to collect comment, likes, datetimes, even retweet and views by using selenium. Available platform to collect data:

  1. Instagram.
  2. Twitter.

Simple EDA with cleaning the data (Available👨‍💻)

Available Notebook to process the data:

  1. Instagram.
  2. Twitter.

The Flow for the next update

  1. Green = Can be used
  2. Orange = Semi complete
  3. Red = Still in progress graph