Open Access. Powered by Scholars. Published by Universities.®

Communication Technology and New Media Commons

Open Access. Powered by Scholars. Published by Universities.®

PDF

Bard College

Theses/Dissertations

2022

Articles 1 - 1 of 1

Full-Text Articles in Communication Technology and New Media

Identifying The Relationship Between Page Content And Title, Yabo Ornella Detchou Jan 2022

Identifying The Relationship Between Page Content And Title, Yabo Ornella Detchou

Senior Projects Spring 2022

This project seeks to find the similarity score between content on the page and title using cosine similarity from a word2vec model. Frequent words and randomly chosen words from each article were analyzed and compared against the title using three samples. Frequent words were found to have a higher similarity score with the title than random words. Word frequency helps you identify the most relevant keyword on the page. The bigger goal of the project is to develop a keyword suggestion tool. Identifying which keywords are most relevant in writing content is the first step.