EUVIMEDEUVIMED entdecken
Crossref

SBERT-RF: A Scalable Model for Fake Review Detection

N. Kumara Swamy, V. Bindu Priya, P. Yaswitha, K. Hanuman, N. Manikanta, .G. Nagaraju

INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 09.04.2026 · 10 (04) · 1-9

DOI: 10.55041/ijsrem59639 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 09.04.2026. Verfasst von N. Kumara Swamy und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Abstract—Fake reviews have become a persistent problem on restaurant and hospitality platforms, quietly eroding the trust consumers place in peer ratings. Most existing detection approaches rely solely on either text-based natural language processing or simple behavioral heuristics, leaving meaningful predictive signal untapped. This paper introduces ReviewScan, a three-stream ensemble that processes each review through three parallel channels: (i) 384-dimensional dense embeddings from a Sentence-BERT (SBERT) transformer; (ii) 27 behavioral features drawn from reviewer profile metadata, including 10 novel interaction terms developed specifically for this work; and (iii) 32 scalar outputs from a Mamdani fuzzy inference engine that converts expert suspicion rules into continuous scores. All three channels are concatenated into a single 443-dimensional vector and fed to a class-balanced Random Forest of 300 trees. On the publicly available Yelp Chicago restaurant review benchmark of 26,955 labeled samples, ReviewScan achieves 88.63% accuracy and an AUC-ROC of 0.9393, outperforming TF-IDF baselines, a standalone SBERT model, and behavioral-only classifiers. A seven-way ablation study confirms statistically significant, non-overlapping contributions from each channel (p < 0.05, McNemar's test). The full pipeline runs as a REST API and completes end-to-end inference in 152 ms on standard CPU hardware. Index Terms—Fake review detection, opinion spam, Sentence-BERT, fuzzy logic, Mamdani inference, ensemble learning, Random Forest, behavioral feature engineering, Yelp dataset, real-time classification.

Zitieren

APA

Swamy, N. K., Priya, V. B., Yaswitha, P., Hanuman, K., Manikanta, N., & Nagaraju, G. (2026). SBERT-RF: A Scalable Model for Fake Review Detection. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem59639

Vancouver

Swamy NK, Priya VB, Yaswitha P, Hanuman K, Manikanta N, Nagaraju G. SBERT-RF: A Scalable Model for Fake Review Detection. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem59639

BibTeX
@article{Swamy2026,
  author = {Swamy, N. Kumara and Priya, V. Bindu and Yaswitha, P. and Hanuman, K. and Manikanta, N. and Nagaraju, .G.},
  title = {SBERT-RF: A Scalable Model for Fake Review Detection},
  journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  volume = {10},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsrem59639}
}
Kostenlos starten →