Sentiment Analysis in Social Networks during the 2021 and 2022 Formula 1 Seasons: A Study Using Natural Language Processing on Twitter

Abstract

Sentiment Analysis is an emerging research area that focuses onextracting semantic and emotional inferences from natural language,paving the way for analyses that deal with a high volume oftextual data. The growing importance of data in strategic decisionmakingand the recognition of social networks as vast repositoriesof public opinion have propelled this study, which aimed to explorethe interaction between human emotions and motorsport events.Thus, this study focused on applying Natural Language Processingto extract and analyze sentiments expressed in tweets about Formula1. Advanced machine learning and deep learning techniqueswere employed to train various models in the sentiment classificationtask. Among these, Logistic Regression and LSTMs stood out,achieving accuracies of 78.21% and 78.08%, respectively. The LSTMmodel, in particular, was implemented on a public dataset of tweetscollected during the 2021 and 2022 Formula 1 seasons. The modelwas used to classify the sentiments expressed by fans, allowingfor an exploratory analysis of data correlated to specific events ofthe races. The findings revealed significant engagement patterns,with notable spikes in emotional reactions coinciding with criticalmoments of the seasons. These discoveries illustrate how particularevents can profoundly influence the emotions and behavior of fans.From a detailed analysis of expressed sentiments, valuable data canbe obtained that may be leveraged for developing more effectivemarketing and communication strategies in the sport.