Skip to content

jimy-r/NLP-Topic-Modelling-BERTopic-and-KMeans-Hybrid-

Repository files navigation

Date created 19.08.2024

Project Title: Master of Data Science - MA5851 - Assessment 3 - WebCrawler and NLP System

Description: Building a prototype NLP solution using webscraping and machine learning.

The analysis includes:

data_collection.py - PART 1 - Python script with WebCrawler, RSS requests and API calls

nlpmodel.py - PART 2 - Data Preprocessing, Exploratory Analysis, and NLP Models

crypto_news.JSON/raw_data.JSON - Subsequent raw data output from data_collection. 1108 news articles.

preprocessed_data - Preprocessed data before model application

About

Webcrawler and NLP System

Topics

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages