Document Type


First Faculty Advisor

Kevin Mentzer


Yankees; Red Sox; Sentiment; Topic Analysis

Rights Management



This paper investigates data collected on twitter which references the Yankees or Red Sox during the 2020 Major League Baseball (MLB) season. The objective is to analyze the sentiment of tweets referencing the Yankees and Red Sox over the course of the season. In addition, an investigation of the networks within the data and the topics that were prevalent will be conducted. The 2020 MLB season was started late because of the COVID-19 pandemic and was a season like no other. The expectation of a dataset revolving around baseball is that the topics discussed would be about baseball. The findings from the 2020 season is that most of the topics were revolving around the COVID-19 pandemic and other political events. The average sentiment score of tweets talking about the Yankees and Red Sox was positive. Tweets talking about the Red Sox were slightly more positive than tweets talking about the Yankees. Performance of the teams seems to not have a strong effect on the sentiment score because the Yankees had a better season than the Red Sox and yet Red Sox sentiment was higher. This paper provides an overview of twitter dialog about these two teams.