AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies

The proliferation of AI-powered bots and sophisticated fraudsters poses a significant threat to the integrity of scientific studies reliant on online surveys across diverse disciplines, including health, social, environmental and political sciences. We found a substantial decline in usable responses...

Full description

Saved in:
Bibliographic Details
Main Authors: Natalia Pinzón, Vikram Koundinya, Ryan E. Galt, William O'R. Dowling, Marcela Baukloh, Namah C. Taku-Forchu, Tracy Schohr, Leslie M. Roche, Samuel Ikendi, Mark Cooper, Lauren E. Parker, Tapan B. Pathak
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Research Metrics and Analytics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frma.2024.1432774/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846145138517082112
author Natalia Pinzón
Natalia Pinzón
Vikram Koundinya
Vikram Koundinya
Ryan E. Galt
Ryan E. Galt
William O'R. Dowling
Marcela Baukloh
Namah C. Taku-Forchu
Tracy Schohr
Leslie M. Roche
Leslie M. Roche
Samuel Ikendi
Mark Cooper
Lauren E. Parker
Lauren E. Parker
Tapan B. Pathak
Tapan B. Pathak
author_facet Natalia Pinzón
Natalia Pinzón
Vikram Koundinya
Vikram Koundinya
Ryan E. Galt
Ryan E. Galt
William O'R. Dowling
Marcela Baukloh
Namah C. Taku-Forchu
Tracy Schohr
Leslie M. Roche
Leslie M. Roche
Samuel Ikendi
Mark Cooper
Lauren E. Parker
Lauren E. Parker
Tapan B. Pathak
Tapan B. Pathak
author_sort Natalia Pinzón
collection DOAJ
description The proliferation of AI-powered bots and sophisticated fraudsters poses a significant threat to the integrity of scientific studies reliant on online surveys across diverse disciplines, including health, social, environmental and political sciences. We found a substantial decline in usable responses from online surveys from 75 to 10% in recent years due to survey fraud. Monetary incentives attract sophisticated fraudsters capable of mimicking genuine open-ended responses and verifying information submitted months prior, showcasing the advanced capabilities of online survey fraud today. This study evaluates the efficacy of 31 fraud indicators and six ensembles using two agriculture surveys in California. To evaluate the performance of each indicator, we use predictive power and recall. Predictive power is a novel variation of precision introduced in this study, and both are simple metrics that allow for non-academic survey practitioners to replicate our methods. The best indicators included a novel email address score, MinFraud Risk Score, consecutive submissions, opting-out of incentives, improbable location.
format Article
id doaj-art-5f8bdfb882a84db7b92015733c29ffdd
institution Kabale University
issn 2504-0537
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Research Metrics and Analytics
spelling doaj-art-5f8bdfb882a84db7b92015733c29ffdd2024-12-02T06:23:20ZengFrontiers Media S.A.Frontiers in Research Metrics and Analytics2504-05372024-12-01910.3389/frma.2024.14327741432774AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategiesNatalia Pinzón0Natalia Pinzón1Vikram Koundinya2Vikram Koundinya3Ryan E. Galt4Ryan E. Galt5William O'R. Dowling6Marcela Baukloh7Namah C. Taku-Forchu8Tracy Schohr9Leslie M. Roche10Leslie M. Roche11Samuel Ikendi12Mark Cooper13Lauren E. Parker14Lauren E. Parker15Tapan B. Pathak16Tapan B. Pathak17Geography Graduate Group, University of California, Davis, Davis, CA, United StatesRhizobia LLC, San Francisco, CA, United StatesGeography Graduate Group, University of California, Davis, Davis, CA, United StatesUniversity of California Cooperative Extension, Davis, CA, United StatesGeography Graduate Group, University of California, Davis, Davis, CA, United StatesAgricultural Sustainability Institute, College of Agricultural and Environmental Sciences, University of California, Davis, Davis, CA, United StatesRhizobia LLC, San Francisco, CA, United StatesRhizobia LLC, San Francisco, CA, United StatesNatural Resources Institute, University of Wisconsin-Madison, Madison, WI, United StatesUniversity of California Cooperative Extension, Davis, CA, United StatesGeography Graduate Group, University of California, Davis, Davis, CA, United StatesUniversity of California Cooperative Extension, Davis, CA, United StatesDivision of Agriculture and Natural Resources, University of California, Merced, Merced, CA, United StatesGeography Graduate Group, University of California, Davis, Davis, CA, United StatesGeography Graduate Group, University of California, Davis, Davis, CA, United StatesCalifornia Climate Hub, United States Department of Agriculture (USDA), Davis, CA, United StatesUniversity of California Cooperative Extension, Davis, CA, United StatesDivision of Agriculture and Natural Resources, University of California, Merced, Merced, CA, United StatesThe proliferation of AI-powered bots and sophisticated fraudsters poses a significant threat to the integrity of scientific studies reliant on online surveys across diverse disciplines, including health, social, environmental and political sciences. We found a substantial decline in usable responses from online surveys from 75 to 10% in recent years due to survey fraud. Monetary incentives attract sophisticated fraudsters capable of mimicking genuine open-ended responses and verifying information submitted months prior, showcasing the advanced capabilities of online survey fraud today. This study evaluates the efficacy of 31 fraud indicators and six ensembles using two agriculture surveys in California. To evaluate the performance of each indicator, we use predictive power and recall. Predictive power is a novel variation of precision introduced in this study, and both are simple metrics that allow for non-academic survey practitioners to replicate our methods. The best indicators included a novel email address score, MinFraud Risk Score, consecutive submissions, opting-out of incentives, improbable location.https://www.frontiersin.org/articles/10.3389/frma.2024.1432774/fullsurveysonline data collectionfraud detectionsurvey farmsAI bots
spellingShingle Natalia Pinzón
Natalia Pinzón
Vikram Koundinya
Vikram Koundinya
Ryan E. Galt
Ryan E. Galt
William O'R. Dowling
Marcela Baukloh
Namah C. Taku-Forchu
Tracy Schohr
Leslie M. Roche
Leslie M. Roche
Samuel Ikendi
Mark Cooper
Lauren E. Parker
Lauren E. Parker
Tapan B. Pathak
Tapan B. Pathak
AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
Frontiers in Research Metrics and Analytics
surveys
online data collection
fraud detection
survey farms
AI bots
title AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
title_full AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
title_fullStr AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
title_full_unstemmed AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
title_short AI-powered fraud and the erosion of online survey integrity: an analysis of 31 fraud detection strategies
title_sort ai powered fraud and the erosion of online survey integrity an analysis of 31 fraud detection strategies
topic surveys
online data collection
fraud detection
survey farms
AI bots
url https://www.frontiersin.org/articles/10.3389/frma.2024.1432774/full
work_keys_str_mv AT nataliapinzon aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT nataliapinzon aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT vikramkoundinya aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT vikramkoundinya aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT ryanegalt aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT ryanegalt aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT williamordowling aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT marcelabaukloh aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT namahctakuforchu aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT tracyschohr aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT lesliemroche aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT lesliemroche aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT samuelikendi aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT markcooper aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT laureneparker aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT laureneparker aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT tapanbpathak aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies
AT tapanbpathak aipoweredfraudandtheerosionofonlinesurveyintegrityananalysisof31frauddetectionstrategies