A Scalable Platform to Collect, Store, Visualize, and Analyze Big Data in Real Time
Bibliographic record
Abstract
Twitter has withstood the test of time as a successful social networking platform. In many circles globally, the majority of users choose Twitter when choosing a social media outlet for reliable scientific information and news. However, the Twitter application programming interface (API) limitations do not allow for low-cost data science options for academia. It becomes very expensive for academic researchers to gain the full potential of data analytics available from Twitter using a free API account. In this article, we present our big data analytics platform developed at our DaTALab at Lakehead University, Canada, that allows users to focus on their Twitter search criteria and gain access to large amounts of Twitter data at the touch of a button. The platform supports the collection of social media data and applies many filters for cleaning and further use for machine learning (ML) and artificial intelligence (AI)-based systems. Our focus has been primarily on healthcare-related research, which shows the strength of the presented platform. However, the platform itself is malleable to any topic of interest. Data collected and processed are suitable for further AI/ML analysis. We present our platform using a specific healthcare search topic to emphasize the power of our system for future research endeavors in the healthcare field.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.004 | 0.009 |
| Open science | 0.003 | 0.008 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.018 | 0.018 |
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".