Challenges and Lessons Learned in Managing Web-Based Survey Fraud for the Garnering Effective Outreach and Research in Georgia for Impact Alliance–Community Engagement Alliance Survey Administrations
2024

Managing Web-Based Survey Fraud in Public Health Research

Sample size: 4934 publication 10 minutes Evidence: moderate

Author Information

Author(s): Craig Leslie S, Evans Christina L, Taylor Brittany D, Patterson Jace, Whitfield Kaleb, Hill Mekhi, Nwagwu Michelle, Mubasher Mohamed, Bednarczyk Robert A, McCray Gail G, Gaddis Cheryl L R, Taylor Natasha, Thompson Emily, Douglas Ursula, Latimer Saundra K, Spivey Sedessie G, Henry Akintobi Tabia, Quarells Rakale Collins

Primary Institution: Morehouse School of Medicine

Hypothesis

This study aims to contribute to an evolving evidence base on data integrity threats associated with web-based survey research.

Conclusion

The study found that implementing additional security tools during web-based surveys improved the detection and management of survey fraud.

Supporting Evidence

  • Suspicious activity during Survey I led to the implementation of additional security tools in Survey II.
  • 42.2% of responses from Survey I were retained for analysis compared to 50.1% from Survey II.
  • Daily monitoring of survey responses was essential for detecting unusual patterns.
  • Use of hidden questions and CAPTCHA improved the quality of responses in Survey II.
  • Community engagement was crucial for effective participant recruitment.

Takeaway

This study shows that online surveys can be tricked by fake responses, but using special tools can help keep the data real and useful.

Methodology

The study used web-based surveys administered through Qualtrics, with various security measures to detect and exclude fraudulent responses.

Potential Biases

Potential bias in participant recruitment and data collection methods may affect the generalizability of the results.

Limitations

Not all authentication tools were implemented in both survey waves, which may affect the robustness of the findings.

Participant Demographics

Participants were adults (18 years and older) of Black or African American race or Hispanic or Latino ethnicity, primarily from Georgia.

Digital Object Identifier (DOI)

10.2196/51786

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication