Detecting Fraudulent Language in ICO White Papers: A Cross-Country Linguistic Analysis

Gatot, Eliot
(2025)

Files

Gatot_64092000_2025.pdf
  • Closed access
  • Adobe PDF
  • 734.5 KB

Details

Supervisors
Thewissen, James
Faculty
Louvain School of Management
Degree label
Master [120] en sciences de gestion, à finalité spécialisée
Abstract
enThis thesis analyses 1,202 ICO white papers (402 scams) to identify linguistic markers of fraud, combining them with cultural and regulatory context. Logistic regression models show that certain cues, such as modal verbs and low readability, are more common in scams, while cultural effects are limited except for a notable Masculinity × Competition interaction. The findings provide insights for more context-aware fraud detection in crypto markets.