Date of Graduation

12-2015

Document Type

Thesis

Degree Name

Bachelor of Science

Degree Level

Undergraduate

Department

Computer Science and Computer Engineering

Advisor/Mentor

Gashler, Michael

Committee Member

Gauch, Susan

Second Committee Member

Sullivan, Kelly

Abstract

This paper explores the value of information contained in spam tweets as it pertains to prediction accuracy. As a case study, tweets discussing Bitcoin were collected and used to predict the rise and fall of Bitcoin value. Precision of prediction both with and without spam tweets, as identified by a naive Bayesian spam filter, were measured. Results showed a minor increase in accuracy when spam tweets were included, indicating that spam messages likely contain information valuable for prediction of market fluctuations.

Share

COinS