Bengali Fake Reviews: A Benchmark Dataset and Detection System

TL;DR

This paper introduces the first Bengali fake review dataset and develops a high-accuracy detection system using an ensemble of transformer models, addressing the underexplored area of fake review detection in Bengali.

Contribution

The creation of the Bengali Fake Review Detection (BFRD) dataset and the development of a novel ensemble detection system using multiple pre-trained transformers.

Findings

Weighted F1-score of 0.9843 on test data.

Ensemble model outperforms individual transformers.

Effective handling of non-Bengali words via translation pipeline.

Abstract

The proliferation of fake reviews on various online platforms has created a major concern for both consumers and businesses. Such reviews can deceive customers and cause damage to the reputation of products or services, making it crucial to identify them. Although the detection of fake reviews has been extensively studied in English language, detecting fake reviews in non-English languages such as Bengali is still a relatively unexplored research area. This paper introduces the Bengali Fake Review Detection (BFRD) dataset, the first publicly available dataset for identifying fake reviews in Bengali. The dataset consists of 7710 non-fake and 1339 fake food-related reviews collected from social media posts. To convert non-Bengali words in a review, a unique pipeline has been proposed that translates English words to their corresponding Bengali meaning and also back transliterates Romanized Bengali to Bengali. We have conducted rigorous experimentation using multiple deep learning and pre-trained transformer language models to develop a reliable detection system. Finally, we propose a weighted ensemble model that combines four pre-trained transformers: BanglaBERT, BanglaBERT Base, BanglaBERT Large, and BanglaBERT Generator . According to the experiment results, the proposed ensemble model obtained a weighted F1-score of 0.9843 on 13390 reviews, including 1339 actual fake reviews and 5356 augmented fake reviews generated with the nlpaug library. The remaining 6695 reviews were randomly selected from the 7710 non-fake instances. The model achieved a 0.9558 weighted F1-score when the fake reviews were augmented using the bnaug library.