AI Against Smishing in Kenya: Culturally Adapted SMS Scam Detection for Digital Trust
Bibliographic record
Abstract
Kenya’s mobile-financial ecosystem, driven by M-Pesa and a mobile penetration rate above 133%, has advanced commerce and financial inclusion but also exposed users to SMS-based scams exploiting linguistic diversity, cultural trust, and psychological manipulation. Existing fraud-reporting mechanisms such as keyword filtering and manual reporting, remain reactive and inadequate against these evolving threats. To fill this gap, this study develops a culturally adapted, machine learning–driven approach to SMS scam detection tailored to Kenya’s multilingual environment. Using a crowdsourced dataset of 738 SMS messages (427 scams, 311 legitimate), XGBoost achieved 83.8% accuracy with strong precision and F1-scores, while Logistic Regression offered superior recall (91.8%) in detecting fraudulent content. SHAP analysis revealed urgency cues, code-switching features, and social proof language as the most influential predictors of scams. The proposed model, designed for integration via APIs into USSD platforms, enables real-time detection and fosters user confidence through explainable alerts. This study provides a scalable, context-aware framework for fraud prevention in mobile-first economies and actionable insights for telecom operators, fintech platforms, and policymakers seeking to strengthen digital trust.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".