A Semantic Collaborative Filtering-Based Recommendation System to Enhance Geospatial Data Discovery in Geoportals
Bibliographic record
Abstract
Traditional geoportals depend primarily on keyword-based search, which often fails to retrieve relevant datasets when metadata are heterogeneous, incomplete, or inconsistent with user terminology. This limitation reduces the efficiency of data discovery and selection, particularly in domains where metadata quality varies widely. This study aims to address this challenge by developing a semantic collaborative filtering recommendation system designed to enhance dataset discovery in geoportals through the analysis of implicit user interactions. The system captures users’ search queries, viewed datasets, downloads, and applied filters to infer feedback and organize it into a user–item matrix. Because interaction data are typically sparse, semantic user clustering is applied to mitigate this limitation by grouping users with semantically related interests through hierarchical relationships represented in the Simple Knowledge Organization System (SKOS). However, as users often need complementary datasets to complete specific tasks, association rule mining is employed to identify co-occurrence patterns in search histories and enhance task-related result diversity. The final recommendation scores are then computed by factorizing the user–item matrix with Alternating Least Squares (ALS), using cosine similarity on the latent user vectors to identify nearest neighbors, and applying a standard user-based neighborhood prediction model to rank unseen datasets. The system is implemented within an existing ontology-based geoportal as a standalone, configurable component, requiring only access to user interaction logs and dataset identifiers. Evaluation using precision, recall, and Precision@5 demonstrates that increasing user interactions improves recommendation performance by strengthening behavioral evidence used for ranking. The findings indicate that integrating semantic relationships and behavioral patterns can strengthen dataset discovery in geoportals and complement conventional metadata-based search mechanisms.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".