Dataset for the research paper "Automated machine learning in research – a literature review"
<p>This repository contains the literature used in the research paper "Automated Machine Learning in Research – A Literature Review."</p> <p>The four BibTeX files contain the following collections of literature:</p> <table> <tbody> <tr> <td><strong>File</strong></td> <td><strong>Description</strong></td> <td><strong>Method</strong></td> </tr> <tr> <td><strong>01_Initial_papers.bib</strong></td> <td>385 Initial papers</td> <td>Keyword search in scientific databases Scopus and Web of Science</td> </tr> <tr> <td><strong>02_Primary_papers.bib</strong></td> <td>267 Primary papers</td> <td>Removing duplicate articles and filtering for full articles (i.e., conference and journal papers)</td> </tr> <tr> <td><strong>03_Possibly_relevant_papers.bib</strong></td> <td>54 Possibly relevant papers</td> <td>Identifying possibly relevant papers through abstract scan and application of inclusion criteria</td> </tr> <tr> <td><strong>04_Relevant_papers.bib</strong></td> <td>49 Relevant papers</td> <td>Inclusion of relevant papers after full-text analysis and backward and forward searches</td> </tr> </tbody> </table> <p>The following inclusion criteria were used to identify the 54 possibly relevant papers during the abstract scan:</p> <ul> <li>The abstract must mention autoML or related concepts such as low-code ML, meta-learning, or automated hyperparameter tuning and their potential use in research.</li> <li>The abstract must mention reproducibility or related concepts such as transparency or explainability in the context of autoML or the related concepts mentioned above</li> </ul>
ShareScore
32/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 4
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 8
- Engagement
- 0