Related Experiment Video
Updated: Jul 27, 2026
09:20
Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
Published on: February 23, 2019
Can abstract screening workload be reduced using text mining? User experiences of the tool Rayyan
Hanna Olofsson1, Agneta Brolund1, Christel Hellberg1
1Swedish Agency for Health Technology Assessment and Assessment of Social Services, Stockholm, Sweden.
Research Synthesis Methods
|April 5, 2017
Summary
Text mining in Rayyan efficiently identifies relevant studies for systematic reviews. This tool helps reviewers find crucial research early, saving significant time and effort in the screening process.
Area of Science:
- Information Science
- Medical Informatics
Background:
- Systematic reviews require extensive abstract screening, a time-consuming process.
- Text mining offers a solution to streamline abstract screening by prioritizing relevant studies.
Purpose of the Study:
- To evaluate the effectiveness of Rayyan's text mining feature for abstract screening.
- To gather user feedback on the Rayyan abstract screening tool.
Main Methods:
- Rayyan's text mining tool was utilized for abstract screening across six systematic reviews.
- Screeners recorded relevant references after screening 25%, 50%, and 75% of abstracts.
- A user survey was administered to collect feedback on the tool's performance.
Main Results:
- Screening 50% of abstracts with Rayyan identified 86%–99% of relevant references.
- 96%–100% of ultimately included studies were found within the first half of the screening.
- Users provided a high satisfaction rating, averaging 4.5 out of 5 stars.
Conclusions:
- Rayyan's text mining functionality significantly aids reviewers in early identification of relevant studies.
- The tool effectively reduces the burden of abstract screening in systematic reviews.
