Unapređenje upotrebljivosti otvorenih podataka definisanjem metode kategorizacije zasnovane na metapodacima portala otvorenih podataka
Bibliographic record
Abstract
Due to numerous data transparency and open government initiatives, a large volume of data was published on open data portals. To make it more accessible and visible, these portals have introduced data filtering by category, tags, format, organization, etc. This information is stored as metadata and provided when publishing the data. However, the metadata is not always complete. The lack of data categories has a great impact on the data visibility, accessibility, and usability of information. As the data increases on the portals, it becomes harder to find and identify the wanted information when the category is missing. Within this doctoral dissertation, an analysis of metadata on open data portals, as well as an analysis of categories and tags usage, and their connections on open data portals was performed. Afterward, the problem of missing data categories was addressed by proposing a methodology for data categorization based on the combination of tags. Within the methodology, the hierarchical organization of tags in a category was defined based on their usage in categorized data. Then, a tool was presented for visual analysis of the hierarchical organization of tags, and a proposal was given for the data categorization based on the combination of tags. The presented categorization relies on the way tags are used in categorized data, i.e. their hierarchical organization. The approach calculates the similarity between two tags, and two combinations of tags, as well as defines the parameters for categorizing the combination of tags with categories on the portal. Afterward, an algorithm was defined that proposes the categories for a dataset with a given combination of tags. For the proposed categorization, an evaluation was performed using the data from the Canadian open data portal. Lastly, within the doctoral dissertation, a model was proposed for supplementing the datasets’ metadata on open data portals.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".