Mapping the Global Conversation on Sports Analytics: A Methodology for Twitter Data Collection (Preprint)
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.005 | 0.007 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".