A generic Data Mart architecture to support Web mining
Bibliographic record
Abstract
Visits in a Web site leave behind important information about the behavior of the visitors. This information is stored in log files, which can contain many registers but part of them do not contain relevant information. In such cases, user behavior analysis turns out to be a complex and time-consuming task. In order to analyze Web site visits, the relevant information has to be filtered and studied in an efficient way. We introduce a generic Data Mart architecture to support advanced Web mining, which is based on a Star model and contains the relevant historical data from visits to the Web site. Its fact table contains various additive measures that support the intended data mining tasks, whereas the dimension tables store the parameters necessary for such analysis, e.g. period of analysis, range of pages within a session. This generic repository allows one to store different kinds of information derived from visits to a Web site, such as e.g. time spent on each page in a session and sequences of pages in a session. Since the Data Mart has a flexible structure that allows one to add other interesting parameters describing visitors navigation, it provides a flexible research platform for various kinds of analysis. Based on these sources, user behavior can be characterized and stored in user behavior vectors that serve as input for data mining. For example, similar visits can be grouped together and typical user behavior can be identified, which allows improvement of Web sites and an understanding of user behavior. The application of the presented methodology to the Web site of a Chilean university shows its benefits. We analyzed visits to the respective Web site and could identify clusters of typical visitors. The analysis of these clusters is used for improved online marketing activities.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".