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：本文探讨了半监督生成对抗网络（GANs）在微调预训练语言模型方面的潜力，旨在通过少量标注数据将孟加拉语虚假评论与真实评论进行分类。随着社交媒体和电子商务的兴起，检测虚假或欺骗性评论的能力变得日益重要，以保护消费者免受错误信息的误导。任何机器学习模型在识别虚假评论时都会遇到困难，尤其是对于像孟加拉语这样的低资源语言。我们证明了所提出的半监督GAN-LM架构（基于预训练语言模型的生成对抗网络）是分类孟加拉语虚假评论的可行解决方案，因为实验结果表明，即使只有1024个标注样本，采用半监督GAN（SSGAN）的BanglaBERT也达到了83.59%的准确率和84.89%的F1分数，在准确率上分别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%。实验在一个手动标注的食品评论数据集上进行，该数据集包含从多个社交媒体群组收集的共6014条真实和虚假评论。对于因缺乏标注数据而难以识别虚假评论或其他分类问题的研究人员，我们的方法可能提供一种解决方案。