The problem We Care - Let the worry fly and serenity pave in! solves

Social networks have been developed as a great point for its users to target people based on sexuality, background, career, etc, and share their opinions reflecting their feelings and sentiments. These criticisms have a negative impact on the mental health of some people. Studies have shown that the younger generation tends to use more social media and as a result have a substantially high rate of reported depression. In order to first tackle depression, it is necessary to make ourselves more aware which is why we have come up with the idea of "We Care-Let the worry fly and serenity pave in", a website aimed at reducing stress levels. Our project is based on sentiment analysis and allows users to analyze Twitter data. Using the Twitter Developer API's, we extracted about 2500 English tweets and trained our model using the Gaussian Naive Bayes Algorithm. This algorithm has been used to categorize tweets on basis of positive, negative or neutral and labelled them as 0,1,2 respectively. The modules used in this are sklearn, Tweepy, NumPy, pandas, regex and Matplotlib. However, our model has shown very promising results. We have attained an accuracy of 83.6%, a precision of 82.89%, recall 77.80%, and an F1 score of 79.49%. We believe that this will ensure that the safety, inclusion and respect of all communities are not compromised.

Challenges we ran into

We faced a major integrating and connecting our machine learning model with flask and the website. Along with this, we also struggled with displaying graphs in flask using JQuery. The graphs were not visible in the beginning as we are not well versed with JQuery and even JavaScript.