A match‐making system for learners and learning objects
Bibliographic record
Abstract
We have proposed and implemented AgentMatcher, an architecture for match‐making in e‐Business applications. It uses arc‐labeled and arc‐weighted trees to match buyers and sellers via our novel similarity algorithm. This paper adapts the architecture for match‐making between learners and learning objects (LOs). It uses the Canadian Learning Object Metadata (CanLOM) repository of the eduSource e‐Learning project. Through AgentMatcher’s new indexing component, known as Learning Object Metadata Generator (LOMGen), metadata is extracted from HTML LOs for use in CanLOM. LOMGen semi‐automatically generates the LO metadata by combining a word frequency count and dictionary lookup. A subset of these metadata terms can be selected from a query interface, which permits adjustment of weights that express user preferences. Web‐based pre‐filtering is then performed over the CanLOM metadata kept in a relational database. Using an XSLT (Extensible Stylesheet Language Transformations) translator, the pre‐filtered result is transformed into an XML representation, called Weighted Object‐Oriented (WOO) RuleML (Rule Markup Language). This is compared to the WOO RuleML representation obtained from the query interface by AgentMatcher’s core Similarity Engine. The final result is presented as a ranked LO list with a user‐specified threshold.
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 | 0.007 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.005 | 0.011 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.003 | 0.002 |
| 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".