This paper investigates the potential of semi-supervised Generative Adversarial Networks (GANs) to fine-tune pretrained language models in order to classify Bengali fake reviews from real reviews with a few annotated data. With the rise of social media and e-commerce, the ability to detect fake or deceptive reviews is becoming increasingly important in order to protect consumers from being misled by false information. Any machine learning model will have trouble identifying a fake review, especially for a low resource language like Bengali. We have demonstrated that the proposed semi-supervised GAN-LM architecture (generative adversarial network on top of a pretrained language model) is a viable solution in classifying Bengali fake reviews as the experimental results suggest that even with only 1024 annotated samples, BanglaBERT with semi-supervised GAN (SSGAN) achieved an accuracy of 83.59% and a f1-score of 84.89% outperforming other pretrained language models - BanglaBERT generator, Bangla BERT Base and Bangla-Electra by almost 3%, 4% and 10% respectively in terms of accuracy. The experiments were conducted on a manually labeled food review dataset consisting of total 6014 real and fake reviews collected from various social media groups. Researchers that are experiencing difficulty recognizing not just fake reviews but other classification issues owing to a lack of labeled data may find a solution in our proposed methodology.
翻译:Translated Abstract:
本文研究了半监督生成对抗网络(GANs)的潜力,用于微调预训练语言模型,以几个标注数据区分孟加拉语的假评论和真实评论。随着社交媒体和电子商务的崛起,检测虚假或欺骗性评论的能力变得更加重要,以保护消费者免受虚假信息的误导。任何机器学习模型都会难以识别虚假评论,特别是对于孟加拉语这样的低资源语言。我们已经证明了所提出的半监督 GAN-LM 架构(预训练语言模型的生成对抗网络)是一个可行的解决方案。实验结果表明,即使只有1024个标注样本,带有半监督 GAN 的BanglaBERT 实现了83.59%的准确率和84.89%的F1分数,优于其他预训练语言模型 - BanglaBERT 生成器,Bangla BERT Base 和 Bangla-Electra 约3%, 4%和10%的准确率。实验在一份由多个社交媒体小组总共收集了6014个真实评论和假评论的食品评论数据集上进行。对于缺乏标记数据而遇到不仅是假评论也包括其他分类问题的研究人员,我们提出的方法可能是一种解决方案。