Mapping the Global Conversation on Sports Analytics: A Methodology for Twitter Data Collection (Preprint)

• DOI: 10.2196/preprints.52994
• Publication Date: 2023-09-22T03:46:21Z
• Authors: Alexander Walker ...; Kyla Pyndiura; Scott Thomas

BACKGROUND Twitter has been extensively used for understanding public opinion in various domains, yet the discourse surrounding sports analytics has not been thoroughly examined.

OBJECTIVE The aim of this study is to map and characterize the global conversation on sports analytics as it occurs on Twitter, focusing on geographic distribution, topics of interest, and user engagement.

METHODS We employed a multi-stage data collection methodology, starting with three seed accounts involved in sports analytics. Tweets and metadata were collected from users followed by these seed accounts over the last three years. Noun phrases were identified using the spaCy toolkit and were scored based on their frequency relative to a random sample of 1.6 million tweets. Subsequently, term pairs were queried to collect more tweets, focusing on user interactions and topics discussed.

RESULTS A total of 3,159,738 tweets were collected from over two million authors. Tweet frequency varied significantly across the seed accounts, with Sportlogiq having the highest median tweets per account. About 1.7% of users provided geolocation data. Topics were largely consistent across different countries, focusing on sports, technology, and business. Community detection algorithms identified 34 clusters with at least 1,000 members each, discussing topics ranging from specific sports to technology.

CONCLUSIONS The sports analytics discourse on Twitter is active and internationally based, albeit with a significant presence in the United States, the United Kingdom, and Canada. Seed accounts did not bias geographic distribution. Topics were consistent across countries, emphasizing the global nature of this community.