What it does

A powerful AI-ML enabled model to analyze your social media contents. Perform one step curated sentiment analysis to categorize your posts based on user's emotion along with hash tag & caption generator which will help you to connect with people interested in similar content.

How we built it

The back end is built using python, tweepy, instaloader, tkinter, beautifulsoup VADER Sentiment Analysis, etc. Whereas the frontend uses HTML, CSS and javascript as the core tech stacks.

Sentiment Analysis In the Sentiment analysis we are calculating compound score from the tweet description and post using Valence Aware Dictionary and sEntiment Reasoner. The Compound score is a metric that calculates the sum of all the lexicon ratings which have been normalized between -1(most extreme negative) and +1 (most extreme positive). positive sentiment : (compound score >= 0.05) neutral sentiment : (compound score > -0.05) and (compound score < 0.05) negative sentiment : (compound score <= -0.05)

Hashtag Generator Here, we have written code that takes some text input from the user, converts it to a hashtag and then retrieves top tweets with that hashtag from twitter. The code will then scrape the retrieved tweets for other hashtag and finally return a list of all the hashtags for the user to review/use.

We have used open source and indestructible SQL database for VADER dictionary dataset. With the CData Python Connector for CockroachDB and the SQLAlchemy toolkit, you have build CockroachDB-connected Python webapps like hashtag generator and sentiment analyzer for twitter and instagram. With built-in optimized data processing, the CData Python Connector helped us in providing great performance for interacting with live CockroachDB data in Python. engine = create_engine("cockroachdb:///?User=root&Password=****&Database=system&Server=localhost&Port=26257")

We have used the VERTEX AI, a part of AutoML initiative of Google Cloud to build, train & deploy our ML model.

Built With

Share this project:

Updates