Date of Submission

Spring 2014

Academic Programs and Concentrations

Computer Science

Project Advisor 1

Robert McGrail

Abstract/Artist's Statement

This project sought to find a reasonable predictor of web page relevancy. Software was created to collect and visualize a variety of data pertaining to a user’s web browsing. A version of this software was used to collect data from 14 volunteers who browsed the web for three hours. The software used also surveyed volunteers about whether the pages they visited were relevant or not relevant. Comparing the data from pages which were deemed relevant by the volunteers to pages deemed not relevant we found several aspects of the data predicted page relevancy with a high degree of confidence. We concluded the best predictor was view time, or the total amount of time a user spent viewing a page.

Open Access Agreement

On-Campus only

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.

Bard Off-campus Download

Bard College faculty, staff, and students can login from off-campus by clicking on the Off-campus Download button and entering their Bard username and password.