RECORD
Metadata Integration for Spam Reviews Detection on Vietnamese E-commerce Websites
Computation and Language · Submitted 22 May 2024
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim In our experiments, the product category proved effective when combined with deep neural network (DNN) models, while text features performed well on both DNN models and the model achieved state-of-the-art performance in the problem of detecting spam reviews on Vietnamese e-commerce websites, namely PhoBERT.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The problem of detecting spam reviews (opinions) has received significant attention in recent years, especially with the rapid development of e-commerce. Spam reviews are often classified based on comment content, but in some cases, it is insufficient for models to accurately determine the review label. In this work, we introduce the ViSpamReviews v2 dataset, which includes metadata of reviews with the objective of integrating supplementary attributes for spam review classification. We propose a novel approach to simultaneously integrate both textual and categorical attributes into the classification model. In our experiments, the product category proved effective when combined with deep neural network (DNN) models, while text features performed well on both DNN models and the model achieved state-of-the-art performance in the problem of detecting spam reviews on Vietnamese e-commerce websites, namely PhoBERT. Specifically, the PhoBERT model achieves the highest accuracy when combined with product description features generated from the SPhoBert model, which is the combination of PhoBERT and SentenceBERT. Using the macro-averaged F1 score, the task of classifying spam reviews achieved 87.22% (an increase of 1.64% compared to the baseline), while the task of identifying the type of spam reviews achieved an accuracy of 73.49% (an increase of 1.93% compared to the baseline).
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The problem of detecting spam reviews (opinions) has received significant attention in recent years, especially with the rapid development of e-commerce. | background 1.00 | 0.03 | 0.02 | asserted 1.00 |
| s1 | Spam reviews are often classified based on comment content, but in some cases, it is insufficient for models to accurately determine the review label. | gap 0.78 | 0.07 | 0.02 | asserted 0.61 |
| s2 | In this work, we introduce the ViSpamReviews v2 dataset, which includes metadata of reviews with the objective of integrating supplementary attributes for spam review classification. | contribution 0.94 | 0.94 | 0.05 | asserted 0.99 |
| s3 | We propose a novel approach to simultaneously integrate both textual and categorical attributes into the classification model. | contribution 0.54 | 0.87 | 0.06 | asserted 0.97 |
| s4 | In our experiments, the product category proved effective when combined with deep neural network (DNN) models, while text features performed well on both DNN models and the model achieved state-of-the-art performance in the problem of detecting spam reviews on Vietnamese e-commerce websites, namely PhoBERT. | result 0.98 | 0.94 | 0.50 | asserted 1.00 |
| s5 | Specifically, the PhoBERT model achieves the highest accuracy when combined with product description features generated from the SPhoBert model, which is the combination of PhoBERT and SentenceBERT. | result 0.97 | 0.90 | 0.30 | asserted 1.00 |
| s6 | Using the macro-averaged F1 score, the task of classifying spam reviews achieved 87.22% (an increase of 1.64% compared to the baseline), while the task of identifying the type of spam reviews achieved an accuracy of 73.49% (an increase of 1.93% compared to the baseline). | result 1.00 | 0.95 | 0.34 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The problem of detecting spam reviews (opinions) has received significant attention in recent years, especially with the rapid development of e-commerce. Spam reviews are often classified based on comment content, but in some cases, it is insufficient for models to accurately determine the review label. In this work, we introduce the ViSpamReviews v2 dataset, which includes metadata of reviews with the objective of integrating supplementary attributes for spam review classification. We propose a novel approach to simultaneously integrate both textual and categorical attributes into the classification model. In our experiments, the product category proved effective when combined with deep neural network (DNN) models, while text features performed well on both DNN models and the model achieved state-of-the-art performance in the problem of detecting spam reviews on Vietnamese e-commerce websites, namely PhoBERT. Specifically, the PhoBERT model achieves the highest accuracy when combined with product description features generated from the SPhoBert model, which is the combination of PhoBERT and SentenceBERT. Using the macro-averaged F1 score, the task of classifying spam reviews achieved 87.22% (an increase of 1.64% compared to the baseline), while the task of identifying the type of spam reviews achieved an accuracy of 73.49% (an increase of 1.93% compared to the baseline).
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Uses the method or tool of 1 paper
-
Taking advantage of the benefits of this model, we performed fine-tuning on SBERT using two pre-trained Vietnamese models comprised of PhoBERT [ref] and BERT4News [ref] , in order to generate embedding vectors for product descriptions.
NLPBK at VLSP-2020 shared task: Compose transformer pretrained models for Reliable Intelligence Identification on Social network · Product Description · 0.96
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.