Improving web site search using web server logs
Bibliographic record
Abstract
Despite the success of global search engines, web site search engines are still suffering from poor performance. Since a web site is different from the whole web in link structure, access pattern, and data scale, it is not always successful when the methods which improve the performance of web search are applied to web site search. In this paper, we propose a novel algorithm to improve the retrieval performance by using web server logs. Web server logs are grouped into different sessions and the relationships of web pages in the session are analyzed based on their similarities. Then, a new web page representation is generated. Anchor text is used to create another representation. They are combined with original text-based representation in web site search. Two kinds of combination methods are investigated and tested: combination of document representations and combination of ranking scores. Our experimental results show that our algorithm can improve the retrieval accuracy for the four retrieval models we tested: Inference Network Model, Okapi Model, Cosine Similarity Model and TFIDF Model. The highest performance increase from web log analysis is from TFIDF model, and overall, inference network model with web log information achieves the best result.
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 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".