Inspiration
Products have reviews that are one star to 5 stars, but the problem is that there are a lot of reviews to search from. Some 3 star reviews might be saying, "This product is good!" while others might be saying, "This product could use some improvement". A 4 star review may also point out some areas of improvement for the product. As a result, I made the sentiment analysis system to sort out the negative and positive reviews.
What it does
The sentiment analysis system takes multiple reviews, and tells which ones are negative and which ones are positive. It also gives a bar graph on the number of positive and negative reviews
How we built it
I used HTML and Bootstrap to design the webpage. I used javascript to make the graph for the positive and negative reviews. I used python and django for the calculation on wether the reviews are positive and negative.
Challenges we ran into
Challenges I ran into included: designing the webpage, and making sure the machine learning model is accurate.
Accomplishments that we're proud of
An accomplishment that I am proud about is training a machine learning model for a text-related task.
What we learned
I learned that I could use chart.js to make a graph in javascript.
What's next for Sentiment Analysis System
The next step for the Sentiment Analysis System is finding out how much of a review is negative, and how much is positive and then sorting all reviews based on most positive, and least positive.
Log in or sign up for Devpost to join the conversation.