Investigating NLP-Based Approaches for Predicting Manual Test Case Failure
Bibliographic record
Abstract
System-level manual acceptance testing is one of the most expensive testing activities. In manual testing, typically, a human tester is given an instruction to follow on the software. The results as "passed" or "failed" will be recorded by the tester, according to the instructions. Since this is a labourintensive task, any attempt in reducing the amount of this type of expensive testing is essential, in practice. Unfortunately, most of the existing heuristics for reducing test executions (e.g., test selection, prioritization, and reduction) are either based on source code or specification of the software under test, which are typically not being accessed during manual acceptance testing. In this paper, we propose a test case failure prediction approach for manual testing that can be used as a noncode/ specifcation-based heuristic for test selection, prioritization, and reduction. The approach uses basic Information Retrieval (IR) methods on the test case descriptions, written in natural language. The IR-based measure is based on the frequency of terms in the manual test scripts. We show that a simple linear regression model using the extracted natural language/IR-based feature together with a typical history-based feature (previous test execution results) can accurately predict the test cases' failure in new releases. We have conducted an extensive empirical study on manual test suites of 41 releases of Mozilla Firefox over three projects (Mobile, Tablet, Desktop). Our comparison of several proposed approaches for predicting failure shows that a) we can accurately predict the test case failure and b) the NLP-based feature can improve the prediction models.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".