Inspiration
We wanted to mix lightning-fast speed with a news affinity analysis tool! At Kachow, we are really passionate about diluting information down into a singular source of truth so our users don't have to read in the dark.
What it does
Kachow mainly analyses news articles but can analyse almost any web page; even itself! It then gives the user a simple sentiment analysis score on the vibe of the webpage.
How we built it
We heavily used git to collaborate whilst using python for our backend, with tools like: flask, openai, and our own sentiment algorithm. Over in the front end we used HTML, CSS and JS.
Challenges we ran into
At first we struggled a lot with our own personal sentiment algorithm. This was overcame by working together and deeply understanding the process of using similarities of word embeddings to determine the affinity of the word.
Accomplishments that we're proud of
We are extremely proud of the lightning speed at which we can deliver sentiment analysis especially at a larger scale; making use of a centralized database to store the complex data.
What we learned
We learned a lot about web development, new technologies and, more importantly, each other.
What's next for Kachow
The timeline for Kachow will hone into the accuracy algorithm, and the user feedback on sentiment the tool gives.
Built With
- css
- html
- javascript
- new-please
- openai
- python
Log in or sign up for Devpost to join the conversation.