Deceptive reviews are becoming increasingly common, especially given the
increase in performance and the prevalence of LLMs. While work to date has
addressed the development of models to differentiate between truthful and
deceptive human reviews, much less is known about the distinction between real
reviews and AI-authored fake reviews. Moreover, most of the research so far has
focused primarily on English, with very little work dedicated to other
languages. In this paper, we compile and make publicly available the MAiDE-up
dataset, consisting of 10,000 real and 10,000 AI-generated fake hotel reviews,
balanced across ten languages. Using this dataset, we conduct extensive
linguistic analyses to (1) compare the AI fake hotel reviews to real hotel
reviews, and (2) identify the factors that influence the deception detection
model performance. We explore the effectiveness of several models for deception
detection in hotel reviews across three main dimensions: sentiment, location,
and language. We find that these dimensions influence how well we can detect
AI-generated fake reviews.

通过对 MAiDE-up 数据集进行语言分析，研究了 AI 生成的虚假评论与真实评论的区别，并确定了影响欺诈检测模型性能的因素。发现情感、位置和语言等因素对于检测 AI 生成的假评论的准确性产生影响。

MAiDE-up: GPT 生成的酒店评论的多语言欺诈检测

MAiDE-up: Multilingual Deception Detection of GPT-generated Hotel  Reviews

In recent years, online reviews play a vital role for promoting any kind of
product or services. Businesses may embed fake reviews in order to attract
customers to purchase their products. They may even highlight the benefits of
their own product or criticize the competition's product. Marketers,
advertisers, and other online business users have incentive to create fake
positive reviews for products which they want to promote or give fake negative
reviews for products which they really don't like. So now-a-days writing a
deceptive review is inevitable thing for promoting their own business or
degrading competitor's reputation. Thus, identifying deceptive reviews is an
intense and on-going research area. This research paper proposes machine
learning model approach to identify deceptive reviews. The paper investigates
the performance of the several experiments done on a Deceptive Opinion Spam
Corpus dataset of restaurants reviews. We developed a n-gram model and max
features to identify deceptive contents with a particular focus on fake
reviews. Further, we conduct a benchmark study to investigate the performance
of two different features extraction techniques and apply five machine learning
classification techniques. The experimental results show that passive
aggressive classifier outperforms other algorithms, and it reaches the highest
accuracy not only in text classification but also to fake reviews. We also
study the data augmentation and implement different deep learning techniques.

利用机器学习模型鉴别欺诈评论，研究表明被动侵略型分类器在文本分类和欺诈评论中表现最佳。

利用文本分类检测欺诈评论

Detecting deceptive reviews using text classification

In the past few years, consumer review sites have become the main target of
deceptive opinion spam, where fictitious opinions or reviews are deliberately
written to sound authentic. Most of the existing work to detect the deceptive
reviews focus on building supervised classifiers based on syntactic and lexical
patterns of an opinion. With the successful use of Neural Networks on various
classification applications, in this paper, we propose FakeGAN a system that
for the first time augments and adopts Generative Adversarial Networks (GANs)
for a text classification task, in particular, detecting deceptive reviews.
Unlike standard GAN models which have a single Generator and Discriminator
model, FakeGAN uses two discriminator models and one generative model. The
generator is modeled as a stochastic policy agent in reinforcement learning
(RL), and the discriminators use Monte Carlo search algorithm to estimate and
pass the intermediate action-value as the RL reward to the generator. Providing
the generator model with two discriminator models avoids the mod collapse issue
by learning from both distributions of truthful and deceptive reviews. Indeed,
our experiments show that using two discriminators provides FakeGAN high
stability, which is a known issue for GAN architectures. While FakeGAN is built
upon a semi-supervised classifier, known for less accuracy, our evaluation
results on a dataset of TripAdvisor hotel reviews show the same performance in
terms of accuracy as of the state-of-the-art approaches that apply supervised
machine learning. These results indicate that GANs can be effective for text
classification tasks. Specifically, FakeGAN is effective at detecting deceptive
reviews.

本文提出了一种名为 FakeGAN 的系统，它是在文本分类任务中首次采用生成对抗网络（GANs）进行增强，用于检测欺骗性评论。通过使用两个鉴别器模型和一个生成模型，FakeGAN 避免了模式崩溃的问题， 并在 TripAdvisor 酒店评论数据集上表现出与现有监督学习方法相当的性能。