This repository contains an R package called finnsurveytext. For further details on how to use the package, please see the package website which contains tutorials covering all the functions available in finnsurveytext.

A video demonstrating use of the package is available here


Install the released version of finnsurveytext from CRAN: install.packages(“finnsurveytext”)


DARIAH-FI is one of two components of FIN-CLARIAH which is a research infrastructure project for Social Sciences and Humanities (SSH) in Finland. DARIAH-FI involves all Finnish universities with research in SSH.

Our package, finnsurveytext, is the output of WP3.3 of DARIAH-FI. This is a joint work package with Tampere University, University of Eastern Finland, University of Jyvaskyla and University of Helsinki with the objective of “better use of unstructured textual data in the context of Finnish surveys.”


Open-ended questions are an important but challenging way to obtain informative data in surveys. Open-ended question data usually requires extra time investment (Fielding et al., 2013), but open-ended questions are particularly useful if researchers do not want to constrain respondents’ answers to pre-specified selections. Open-ended questions allow respondents to provide diverse answers based on their experience, and some answers are probably never thought of by researchers. (He & Schonlau, 2021.)

There’s limited support for conductive qualitative analysis on Finnish open-ended survey responses and many researchers are more confident analysing responses to closed questions within surveys.

This package aims to provide a useful and user friendly set of tools for social science researchers to be able to analyse and understand responses to open-ended questions within their surveys.


There are 5 sets of functions included in the finnsurveytext package. These are:

  1. Preparation functions (R/01_prepare_conll-u.R)
  2. Data exploration functions (R/02_data_exploration.R)
  3. Concept Network functions (R/03_concept_network.R)
  4. Comparison functions (R/04_comparison_functions.R)
  5. Comparison concept network functions (R/05_comparison_concept_network.R)

Function Demos and Tutorials

Tutorials accompanying each of these R scripts can be found in the ‘Articles’ tab within the website. These tutorials use the sample data outlined below.

Sample Data

Our repository also contains sample data which can be used to demonstrate and learn the functionality of finnsurveytext.

The sample data comes from 2 surveys and can be found in the ‘data’ folder. The raw data (just from the relevant open-ended questions) is in data/bullying_data.rda and data/dev_data.rda. The data folder also contains examples of this data after the preparation functions have been applied and split by sample cohort groups.

The raw data can also be downloaded from the Finnish Social Science Data Archive.

  1. Bullying Data
  2. Development Cooperation Data

Installation and License

The package is available under the MIT license. Currently, the package can only be installed through this Github repository.


Fielding, J., Fielding, N., & Hughes, G. (2013). Opening up open-ended survey data using qualitative software. Quality & Quantity, 47(6), 3261–3276.

Finnish Children and Youth Foundation: Young People’s Views on Development Cooperation 2012 [dataset]. Version 2.0 (2019-01-22). Finnish Social Science Data Archive [distributor].

He, Z., & Schonlau, M. (2021). Coding Text Answers to Open-ended Questions: Human Coders and Statistical Learning Algorithms Make Similar Mistakes. Methods, Data, Analyses, 15(1), Article 1.

The Office of Ombudsman for Children: Child Barometer 2016 [dataset]. Version 1.0 (2016-12-09). Finnish Social Science Data Archive [distributor].