Commit afb7b905 authored by Kaczmirek, Lars's avatar Kaczmirek, Lars
Browse files


EvalAnswer is a tool for automatically detecting different types of nonresponse in answers to open-ended questions. It was specifically developed for use in web probing procedures but it can be used in any online survey that asks open-ended questions. EvalAnswer automatically detects and codes cases of nonresponse and suggests follow-up questions which are tailored to reduce nonresponse. Once implemented in a survey, researchers have a powerful survey aid that helps to automatically increase data quality during the interview process by eliciting better answers to open-ended questions. Furthermore, the tool can be used in the post-processing of answers after data collection. The tool can be adapted to be used in one’s own survey. This paper describes the survey methodology that led to developing the tool and it gives details on its validity and effectiveness.
Additional online resources:
Video showing how web probing works with the tool EvalAnswer:
Demonstration and test environment:
Source code for the tool EvalAnswer and project file for import in the online survey software tool questback EFS:
Suggested citation for this document: Kaczmirek, Lars, Meitinger, Katharina, & Behr, Dorothée. GESIS - Leibniz Institute for the Social Sciences (Ed.). EvalAnswer. A tool for identifying and reduc-ing nonresponse in open-ended questions. Cologne, 2017 (GESIS Papers 2017, 1).
Suggested citation for the tool EvalAnswer: Kaczmirek, L., Meitinger, K., & Behr, D. (2016). EvalAnswer [software]. Retrieved from Mannheim, Germany: GESIS - Leibniz Institute for the Social Sciences.
This work was supported by two research grants: “Optimierung von Probe-Techniken für interna-tionale Online-Umfragen” [Optimizing probing techniques in international online surveys], (2012-2015, CICOM2, BR 908/5-1) and “Improving intercultural comparative research by the application of cognitive techniques using the Internet in several countries” as part of SPP 1292: Survey Methodology (2010-2013, CICOM, BR 908/3-1). Principal investigators in both projects were Michael Braun, Wolfgang Bandilla, and Lars Kaczmirek.
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment