Published August 5, 2026 | Version v1

Machine Learning-Based Detection of Supply Chain Disinformation: A Systematic Five-Classifier Comparison Using TF-IDF Features — Dataset and Replication Code

  • 1. Khwaja Moinuddin Chishti Language University, Lucknow, India
  • 2. ROR icon Dr. B. R. Ambedkar National Institute of Technology Jalandhar
  • 3. ROR icon Integral University
  • 4. ROR icon Manipal University Jaipur

Description

This repository provides the complete replication package for the manuscript:

"Machine Learning-Based Detection of Supply Chain Disinformation: A Systematic 
Five-Classifier Comparison Using TF-IDF Features"

Submitted to Scientific Reports (Nature Portfolio).

CONTENTS:
1. Supplementary_Data_S1_merged_dataset_full.csv — 141 hand-verified labeled 
   statements (78 TRUE, 63 FAKE) spanning 18 supply chain topic areas (2020–2026). 
   Sources: DNAINDIA, INDIATODAY, FactCheck.org, PolitiFact, Snopes, BBC Verify, 
   AFP Fact Check, and government fact-check units.

2. run_all_experiments.py — Complete nested 5-fold cross-validation pipeline for 
   five classifiers (SVM, LR, Naive Bayes, Random Forest, XGBoost) with TF-IDF 
   feature extraction. Reproduces all tables and figures in the manuscript.

3. README.md — Full documentation, column definitions, and reproduction instructions.

4. requirements.txt — Python dependencies (Python 3.12, scikit-learn 1.8.0, 
   XGBoost 3.3.0, scipy 1.17.1).

5. LICENSE.txt — MIT License (code) + CC BY 4.0 (dataset).

KEY RESULT: Linear classifiers (SVM, LR, NB) consistently outperform ensemble 
tree methods (RF, XGBoost). LR achieves highest F1 (82.2%); SVM achieves highest 
AUC-PR (0.925). Friedman test: χ²(4)=7.435, p=0.115.

Runtime: approximately 8 minutes on a standard CPU.

Files

SupplyChainMgmt_upload_package.zip

Files (35.5 kB)

Name Size
md5:4eb808a414a40cd28709dba1064d2d70
35.5 kB Preview Download

Additional details

Dates

Available
2026-08-14