First Faculty Advisor
Second Faculty Advisor
Twitter; NHL; performance; sentiment
This study offers a new perspective on collecting and analyzing Twitter data surrounding the National Hockey League (NHL) to identify any trends or relationships between the data and overall performance during the 2021 abbreviated season. This paper provides and in-depth analysis by studying a sample of sixty of the top NHL players, specifically those who are typically top performers in the league, spanning over all thirty-one teams and all positions, this study was able to identify a deeper and broader perspective of what implications can be drawn from analyzing data from Twitter to both predict and reflect both individual player and team performance. In using a set of identified statistics to study performance, as well as analysis techniques, primarily focusing on sentiment and volume to study the Twitter data, this paper defines key relationships which can be used to draw future implications on performance. This paper combines multiple tests and models incorporating platforms and programming languages including Python, Visual Basic for Applications, and Structured Query Language (SQL) to identify trends in these leading players and teams in order to identify if there are any predictive or reflective features which can be identified when comparing Twitter data to performance. My analysis is highly relevant to the NHL and can be replicated across many other teams, leagues, and platforms as they can benchmark these results against one another, in hopes that players, coaches, analysts, and viewers can all benefit from these findings. In this study, multiple tests are conducted to find the characteristics of the most and least successful players and teams within the league. The results of this study show clear indications of my initial predictions of this study: a positive relationship exists between the Twitter data, specifically volume and sentiment, and performance among players and teams.