From information to knowledge: introducing WebStract's knowledge engineering approach
Bibliographic record
Abstract
Information overload is a problem because of the overwhelming volume of data that has become accessible through the Internet or other mass communication media. It is difficult for users to sift through this data and to locate useful knowledge because large amounts of unorganized, raw data are confusing to search engines as well as people. WebStract is an experimental tool to assist in the qualification, organization and distribution of information. It offers semi-automated mechanisms to transform raw electronic data into domain knowledge and it provides multiple views for easier user consumption. After introducing WebStract, the paper focuses on the three stage transformation process that is used to transform raw data into domain knowledge. The three stages are knowledge extraction, knowledge elucidation and knowledge presentation. Knowledge extraction retrieves information from electronic documents (e.g., accessible through the WWW) and analyzes it for useful syntactical patterns that are stored in a database. Knowledge elucidation analyzes the syntactical patterns, in a semi-automated fashion, to produce a prioritized, hierarchical summary of the original documents. A fuzzy filtering mechanism allows retrieval of the stored knowledge and the resulting organized summary is presented using the familiar "book" metaphor. Each book can provide several viewpoints for users to review the information. A main application of WebStract is the support of problem based learning in on-line course delivery. WebStract is currently in its third generation of development.
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.017 | 0.012 |
| Science and technology studies | 0.003 | 0.012 |
| Scholarly communication | 0.020 | 0.031 |
| Open science | 0.004 | 0.009 |
| Research integrity | 0.004 | 0.006 |
| Insufficient payload (model declined to judge) | 0.007 | 0.004 |
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".