VARTTA: A Visual Analytics System for Making Sense of Real-Time Twitter Data
Bibliographic record
Abstract
Through social media platforms, massive amounts of data are being produced. As a microblogging social media platform, Twitter enables its users to post short updates as “tweets” on an unprecedented scale. Once analyzed using machine learning (ML) techniques and in aggregate, Twitter data can be an invaluable resource for gaining insight into different domains of discussion and public opinion. However, when applied to real-time data streams, due to covariate shifts in the data (i.e., changes in the distributions of the inputs of ML algorithms), existing ML approaches result in different types of biases and provide uncertain outputs. In this paper, we describe VARTTA (Visual Analytics for Real-Time Twitter datA), a visual analytics system that combines data visualizations, human-data interaction, and ML algorithms to help users monitor, analyze, and make sense of the streams of tweets in a real-time manner. As a case study, we demonstrate the use of VARTTA in political discussions. VARTTA not only provides users with powerful analytical tools, but also enables them to diagnose and to heuristically suggest fixes for the errors in the outcome, resulting in a more detailed understanding of the tweets. Finally, we outline several issues to be considered while designing other similar visual analytics systems.
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 | 0.004 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.022 | 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".