Skip to content

Latest commit

 

History

History
126 lines (98 loc) · 17.6 KB

README.md

File metadata and controls

126 lines (98 loc) · 17.6 KB
Raw

Gitpod ready-to-code

🇮🇳 🤖 Social Media Intelligence for Brand Analysis 🚀

Contributions Welcome

Git MIT license

Socialis is Social media intelligence for brand analysis, we’ve built this tool for companies to better analyse their customers sentiments and get better, organized feedback on a product.

We also published a research paper in IEEE based on this project. Here is the link

Goals of this project:

  • Build a real time social media analytics tool
  • Understand how social media users from different regions react to a specific brand
  • Use Sentiment Analysis and Named Entity Recognition to understand the user's perceptions towards different entities.

Site:

Time Series Analyis of tweets

This graph plots the time series data plotting the number of tweets per unit of time categorized by their sentiments.

Wordcloud plot

This bar chart plots the most frequently mentioned words in the tweets containing the word 'Facebook'

Named Entity Plot

This bar chart plots the most frequently mentioned named entities in the tweets containing the word 'Facebook'. The named entities have been extracted using the Stanford's NER tagger.

Bigram Analysis Plot

This bar chart plots the most frequently mentioned Bigrams in the tweets containing the word 'Facebook'.

Sentiment Volume Analysis Plot

This pie chart plots the distribution of tweets based on their sentiments containing the word 'Facebook'. It can be observed that Neutral Tweets are the highest in number followed by Positive tweets and Negative tweets.

Influencer Analysis

Top 10 twitter users whose tweet containing the word 'Facebook' has received the highest engagement.

Most Popular User Analaysis

Top 10 twitter users who were mentioned in the tweets containing the word 'Facebook'.

Tech Stack of this Project:

  • Language: Python3
  • Servers: AWS EC2, Heroku
  • Front End: Streamlit, Matplotlib, Seaborn
  • Dependencies: Stanford NER Tagger, Twitter Developer API, PostgreSQL
  • Libraries: Available in requirements.txt.

To run this Project:

  • Clone this repo and pip install the requirements 
git clone https://github.com/parthnagarkar875/Socialis
cd Socialis
pip install -r requirements.txt
python scraper.py

This project still has scope of development, so you can also contribute to this Project as follows:

  • Fork this Repository.
  • Clone your Fork on a different branch:
    • git clone -b <name-of-branch> https://github.com/parthnagarkar875/Socialis.git
  • After adding any feature:
    • Go to your fork and create a pull request.
    • I will test your modifications and merge changes.

Developed with ❤️ by: 

 Parth Nagarkar