Detecting Spam Reviews on Vietnamese E-commerce Websites

TL;DR

This paper introduces ViSpamReviews, a dataset for detecting spam reviews on Vietnamese e-commerce sites, and demonstrates PhoBERT's effectiveness in classifying spam reviews and their types.

Contribution

The paper presents a new annotated dataset for spam review detection in Vietnamese and evaluates PhoBERT's performance on binary and multi-class classification tasks.

Findings

PhoBERT achieved 86.89% macro F1 on spam detection.

PhoBERT achieved 72.17% macro F1 on spam type classification.

The dataset has a strict annotation process for reliable evaluation.

Abstract

The reviews of customers play an essential role in online shopping. People often refer to reviews or comments of previous customers to decide whether to buy a new product. Catching up with this behavior, some people create untruths and illegitimate reviews to hoax customers about the fake quality of products. These are called spam reviews, confusing consumers on online shopping platforms and negatively affecting online shopping behaviors. We propose the dataset called ViSpamReviews, which has a strict annotation procedure for detecting spam reviews on e-commerce platforms. Our dataset consists of two tasks: the binary classification task for detecting whether a review is spam or not and the multi-class classification task for identifying the type of spam. The PhoBERT obtained the highest results on both tasks, 86.89% and 72.17%, respectively, by macro average F1 score.