Tools to Detect Fabricated Interviews

Research question/goal: 

This project will use a recent case study that allows retrospective identification of faked interviews in the IAB-BAMF-SOEP Refugee Survey and test various fraud detection tools, which will facilitate a prospective strategy for identifying possible interviewer fraud in empirical surveys. Furthermore, other case studies will be added. The knowledge gained from this empirical study will be particularly useful to survey sponsors and survey organizations who may not have the time or resources to conduct their own evaluation study. Moreover, the project will contribute to the broader discussion of “best practices” for detecting and possibly preventing interviewer fraud in survey research.

Current stage: 

The major aim of the project was to retrospectively identify fraudulent interviews in the IAB-BAMF-SOEP Survey of Refugees in Germany and evaluate various fraud detection tools. The results were presented at several international conferences and will soon be published. The project will be continued to further investigate the innovative use of machine learning tools in this field of research.

Fact sheet

Funding: 
University of Mannheim
Duration: 
2018 to 2022
Status: 
in preparation
Data Sources: 
various survey data sources

Publications