Text Mining of Key Audit Matters–Analysis By Using AI Application
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
<p>The objectives of this paper are: (1) Text mining of Key Audit Matters (hereafter &ldquo;KAM&rdquo;) (2) Analysis of KAM by a logistic regression model Conclusions are: (1) There are significant differences in the words used in KAM reports between Big 4 auditing firms and small and medium accounting firms. (2) In the Toshiba scandal of 2015, its investigation committee pointed out several fraudulent accounting procedures. After the Toshiba scandal, Big 4 auditing firms were sensitive to a keyword &ldquo;construction&rdquo; and the client&rsquo;s judgment. (3) Small and medium accounting firms are very sensitive to accounting fraud and they used the word &ldquo;fraud&rdquo; in their KAM reports. (4) The probability of Big 4 auditing firms using &ldquo;construction&rdquo;was much higher than small and medium accounting firms. On the contrary, small and medium accounting firms tended to use keyword &ldquo;fraud&rdquo; in theirKAMreports. (5)While AI-powered text mining in KAMand financial statement analysis by CPAs offers great potential to improve efficiency and uncover valuable insights, addressing ethical issues is crucial. As AI technology evolves, integrating ethical principles into its application is necessary.</p> <p>&nbsp;</p>
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 it