Publication Date

Spring 2019

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Melody Moh

Second Advisor

Teng Moh

Third Advisor

Thomas Austin


Twitter, Sentiment, User relationship, Stanford NLP


Studies of online behavior often consider how users interact online, their posting behaviors, what they are tweeting about, and how likely they are to follow other people. The problem is there is that no deeper study on the people that a user has interacted with and how these other users affect them. This study examines if it is possible to draw similar sentiment from users with whom the target user has interacted with. The data collection process gathers data from Twitter users posting to popular political hashtags, which the highest at the time published were #MAGA and #TRUMP, as well as the tweets of people to whom they have tweeted. By applying weights based on the type of interactions as well as the amount, study how close the sentiments that the original user expressed are compared to the users they tweeted to. The weighting formula described above will be known as the Inferred Sentiment Score, or ISS for short. This study presents this scheme of gathering data to build user profiles and ISS to determine how similar a user’s sentimental expression is to the people they communicate with on Twitter. The main results of this study show that by using the ISS formula that there is a strong correlation of the sentiments expressed on Twitter by a user and the users that they communicate with.