Detecting Fraudulent Behavior on Crowdfunding Platforms: The Role of Linguistic and Content-Based Cues in Static and Dynamic Contexts

TLDR

Crowdfunding platforms enable founders to raise funds, but the rise of these platforms has increased fraud risk, with fraudulent founders providing inaccurate information or feigning interest. The study proposes deception detection support mechanisms and investigates whether dynamic communication, content-based cues, and linguistic cues can identify fraudulent behavior beyond static project information. The authors analyze a sample of fraudulent and nonfraudulent projects on a leading platform, examining dynamic communication and content‑ and linguistic‑based cues, and engineer features grounded in communication, psychology, and computational linguistics theories. The results provide useful insights for crowdfunding platform stakeholders and fraud detection researchers.

Abstract

Crowdfunding platforms offer founders the possibility to collect funding for project realization. With the advent of these platforms, the risk of fraud has risen. Fraudulent founders provide inaccurate information or pretend interest toward a project. Within this study, we propose deception detection support mechanisms to address this novel type of Internet fraud. We analyze a sample of fraudulent and nonfraudulent projects published at a leading crowdfunding platform. We examine whether the analysis of dynamic communication during the funding period is valuable for identifying fraudulent behavior—apart from analyzing only the static information related to the project. We investigate whether content-based cues and linguistic cues are valuable for fraud detection. The selection of cues and the subsequent feature engineering is based on theories in areas of communication, psychology, and computational linguistics. Our results should be helpful to the stakeholders of crowdfunding platforms and researchers of fraud detection.