For many tasks—including but not limited to systematic reviews and meta-analyses—scholars, medical doctors, journalists, and policymakers currently screen thousands of texts (e.g., scientific literature, newspapers) by hand to determine relevant texts to include in their review or meta-analysis. The Active learning for Systematic Reviews (ASReview) project, published in Nature Machine Intelligence, implements machine learning algorithms that interactively query the researcher to accelerate the screening of textual data as efficiently and transparently as possible.

When using ASReview to screen titles and abstracts in a systematic review, wordclouds can visualize the words that are used the most within the titles and/or abstracts. The package also allows to create wordclouds for the relevant inclusions only.

To collect quality survey data within budget, a growing number of survey designs are adapting data collection strategies for different members of the target population. Stratification of the population into subgroups is a crucial choice for determining the optimal adaptive survey design. For addressing nonresponse bias, this paper presents an approach that stratifies the target population into subgroups based on survey variables of interest predicted by the available auxiliary data such as population registers.