A Data Science Solution for Supporting Social and Economic Analysis
Bibliographic record
Abstract
In the current era of big data, the advancement in data generation and management has created an avenue for decision makers to utilize these huge data collected from many data-driven application domains for different purposes. Big data science enables application developers and data scientists to utilize these big data, to learn more about the data, and then to explore and model hidden features for analysis purposes. In this paper, we present a data science solution to support social and economic analysis. Our solution makes good use of data mining techniques to cluster similar data, analyze time series, find frequent patterns, reveal interesting associations, and visualize these relationships. We evaluate our solution with two sets of real-life employment data. Our solution utilizes employment data to support social and economic analysis. It enables users to explore and discover implicit, previously unknown information and useful knowledge from the data. This, in turn, can enable the decision makers to take appropriate actions for social good and/or economic benefits. As an example, it reveals to job seekers some interesting characteristics of different data-related jobs, which helps them to find jobs that match better with their needs and profiles. As another example, it also reveals to social scientists and economists impacts of COVID-19 to the job markets, which helps them to get a better understanding of social and economic situations at the COVID-19 pandemic era and plan for the post-pandemic era.
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 | 0.012 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.007 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.008 | 0.012 |
| Open science | 0.004 | 0.010 |
| Research integrity | 0.004 | 0.006 |
| Insufficient payload (model declined to judge) | 0.012 | 0.007 |
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".