RevManHAL: towards automatic text generation in systematic reviews
Background: Systematic reviews are a key part of healthcare evaluation. They involve important painstaking but repetitive work. A major producer of systematic reviews, the Cochrane Collaboration, employs Review Manager (RevMan) programme—a software which assists reviewers and produces XML-structured...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
BioMed Central
2017
|
| Online Access: | https://eprints.nottingham.ac.uk/41168/ |
| _version_ | 1848796213155987456 |
|---|---|
| author | Torres Torres, Mercedes Adams, Clive E. |
| author_facet | Torres Torres, Mercedes Adams, Clive E. |
| author_sort | Torres Torres, Mercedes |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Background: Systematic reviews are a key part of healthcare evaluation. They involve important painstaking but repetitive work. A major producer of systematic reviews, the Cochrane Collaboration, employs Review Manager (RevMan) programme—a software which assists reviewers and produces XML-structured files. This paper describes an add-on programme (RevManHAL) which helps auto-generate the abstract, results and discussion sections of RevMan-generated reviews in multiple languages. The paper also describes future developments for RevManHAL.
Methods: RevManHAL was created in Java using NetBeans by a programmer working full time for 2 months.
Results: The resulting open-source programme uses editable phrase banks to envelop text/numbers from within the prepared RevMan file in formatted readable text of a chosen language. In this way, considerable parts of the review’s ‘abstract’, ‘results’ and ‘discussion’ sections are created and a phrase added to ‘acknowledgements’.
Conclusion: RevManHAL’s output needs to be checked by reviewers, but already, from our experience within the Cochrane Schizophrenia Group (200 maintained reviews, 900 reviewers), RevManHAL has saved much time which is better employed thinking about the meaning of the data rather than restating them. Many more functions will become possible as review writing becomes increasingly automated. |
| first_indexed | 2025-11-14T19:44:24Z |
| format | Article |
| id | nottingham-41168 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:44:24Z |
| publishDate | 2017 |
| publisher | BioMed Central |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-411682020-05-04T18:35:28Z https://eprints.nottingham.ac.uk/41168/ RevManHAL: towards automatic text generation in systematic reviews Torres Torres, Mercedes Adams, Clive E. Background: Systematic reviews are a key part of healthcare evaluation. They involve important painstaking but repetitive work. A major producer of systematic reviews, the Cochrane Collaboration, employs Review Manager (RevMan) programme—a software which assists reviewers and produces XML-structured files. This paper describes an add-on programme (RevManHAL) which helps auto-generate the abstract, results and discussion sections of RevMan-generated reviews in multiple languages. The paper also describes future developments for RevManHAL. Methods: RevManHAL was created in Java using NetBeans by a programmer working full time for 2 months. Results: The resulting open-source programme uses editable phrase banks to envelop text/numbers from within the prepared RevMan file in formatted readable text of a chosen language. In this way, considerable parts of the review’s ‘abstract’, ‘results’ and ‘discussion’ sections are created and a phrase added to ‘acknowledgements’. Conclusion: RevManHAL’s output needs to be checked by reviewers, but already, from our experience within the Cochrane Schizophrenia Group (200 maintained reviews, 900 reviewers), RevManHAL has saved much time which is better employed thinking about the meaning of the data rather than restating them. Many more functions will become possible as review writing becomes increasingly automated. BioMed Central 2017-02-09 Article PeerReviewed Torres Torres, Mercedes and Adams, Clive E. (2017) RevManHAL: towards automatic text generation in systematic reviews. Systematic Reviews, 6 (27). pp. 1-7. ISSN 2046-4053 http://systematicreviewsjournal.biomedcentral.com/articles/10.1186/s13643-017-0421-y doi:10.1186/s13643-017-0421-y doi:10.1186/s13643-017-0421-y |
| spellingShingle | Torres Torres, Mercedes Adams, Clive E. RevManHAL: towards automatic text generation in systematic reviews |
| title | RevManHAL: towards automatic text generation in systematic reviews |
| title_full | RevManHAL: towards automatic text generation in systematic reviews |
| title_fullStr | RevManHAL: towards automatic text generation in systematic reviews |
| title_full_unstemmed | RevManHAL: towards automatic text generation in systematic reviews |
| title_short | RevManHAL: towards automatic text generation in systematic reviews |
| title_sort | revmanhal: towards automatic text generation in systematic reviews |
| url | https://eprints.nottingham.ac.uk/41168/ https://eprints.nottingham.ac.uk/41168/ https://eprints.nottingham.ac.uk/41168/ |