We started by trying different Name Entity Recognition algorithms for Python. After landing on nltk, we used regex syntaxis to define language patterns that would help us identify, entities, and events on the data frame given. After that data was scraped, recognition of product data was scraped by using a list of common leather items and comparing it to the text. Data compiled was graphed and uploaded to a website on a local host.
IDS Project Hackathon 2024
Data visualization project using natural language processing from data scraped by Leather Manufacturing.
Updates
Leave feedback in the comments!
Log in or sign up for Devpost to join the conversation.