Analysis of text data from news articles for application in an aggregation system
This primary research outcomes for this project are to develop the system for automatic classification of news content, in terms of keywords, topics, and broader categories using NLP, text mining, and machine learning, for potential use in a social news aggregation, a proposed alternative method of news curation on the web.
The applicant will brainstorm, hypothsize, and implement machine learning algorithms on text data from news articles scraped from the web, to achieve the desired results (categories, keywords, and topics)
Applicant's Learning Objectives:
The applicant will gain proficiency in the field of data mining, NLP, and machine learning using Python, as well as experience with web-scraping. These skills will be provide invaluable skills and insight for any student considering pursuing the field of machine learning/AI as a profession or research subject for MPhil or PhD studies.