Project: FIN-CLARIAH
Grant agreement: Research Council of Finland no. 358720
Start date: 01-01-2024
Duration: 24 months
WP 4.1: Report on Enrich survey data with register data and unstructured text
Date of reporting: 12-12-2024
Report authors: Adeline Clarke (University of Helsinki), Maria Valaste (University of Helsinki)
Contributors: Adeline Clarke (University of Helsinki), Maria Valaste (University of Helsinki)
Deliverable location: https://cran.r-project.org/web/packages/finnsurveytext/index.html
The finnsurveytext R package has been developed to aid researchers in analyzing responses to open-ended survey questions and other structured text data. This user-friendly tool facilitates reproducible analysis of text data by providing features such as summarizing response properties, identifying frequent words and phrases, visualizing responses, and generating concept network plots. The second version of the package, released in August 2024, integrates with the widely-used R package survey, allowing for survey design to be incorporated into the analysis. Although originally designed for analyzing text in Finnish, the package is versatile and can be used for text analysis in other languages as well.
R package finnsurveytext was released with 2 updates to CRAN. The R package is located at CRAN and additional material is available on the website. An article on the package has been written and is available on Zenodo and for review in the new DARIAH publication.
The results of the work package were presented at two events: an invited lecture at the Workshop on Survey Statistics 2024, held in Poznan, Poland from 26-30 August, and at Statistics Sweden and Örebro University Summer School 2024 in August 28.
FIN-CLARIAH project has received funding from the European Union – NextGenerationEU instrument and is funded by the Research Council of Finland under grant number 358720.
