Clustering Textual Features for Log Summarization in Large Software Systems
Bibliographic record
Abstract
Identifying which lines deserve attention within large software log files can be a challenging task. Log files have consistently increased, reflecting the growth of software development platforms that are becoming larger and integrated. However, software engineers rarely have the time to thoroughly analyze these files to identify important information. To address this issue, data mining methods have been proposed with the intent of summarizing log lines within large log datasets. In this work, we propose a supervised log summarization method based on clustering, which groups log data by using integrated information from (i) log line embeddings, (ii) identified variables extracted from parsed log lines, and (iii) the proximity between log lines. From the obtained clusters, we apply methods for topic modeling and word analysis to summarize and indicate which lines deserve more attention in a log file. Our quantitative analysis on various log datasets demonstrates that our approach outperforms state-of-the-art text summarization methods, thereby showing that the clustering method and the combination of (i)-(iii) are crucial in achieving high accuracy scores for diverse log structures. Finally, we outline the implementation of our method with our corporate partner, highlighting the feedback received and the adjustments made to enhance its practical use.
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 | 0.001 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".