# Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection

arXiv: https://arxiv.org/abs/1907.09177 · HTML: https://mlsanity.com/paper/1907.09177/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jul 2019.

## Built on by (most cited first, 30 of 52)

- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods](https://mlsanity.com/paper/2210.07321/) (2022)
- [Multiscale Positive-Unlabeled Detection of AI-Generated Texts](https://mlsanity.com/paper/2305.18149/) (2023)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)
- [Provably Robust Multi-bit Watermarking for AI-generated Text](https://mlsanity.com/paper/2401.16820/) (2024)
- [Large Language Models can be Guided to Evade AI-Generated Text Detection](https://mlsanity.com/paper/2305.10847/) (2023)
- [Attacking Open-domain Question Answering by Injecting Misinformation](https://mlsanity.com/paper/2110.07803/) (2021)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Deepfake Text Detection: Limitations and Opportunities](https://mlsanity.com/paper/2210.09421/) (2022)
- [CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning](https://mlsanity.com/paper/2212.10341/) (2022)
- [Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russian](https://mlsanity.com/paper/2206.01583/) (2022)
- [Disinformation Capabilities of Large Language Models](https://mlsanity.com/paper/2311.08838/) (2023)
- [Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography](https://mlsanity.com/paper/2107.09287/) (2021)
- [Watermarking Techniques for Large Language Models: A Survey](https://mlsanity.com/paper/2409.00089/) (2024)
- [The Rise of AI-Generated Content in Wikipedia](https://mlsanity.com/paper/2410.08044/) (2024)
- [A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization](https://mlsanity.com/paper/2403.01152/) (2024)
- [A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications](https://mlsanity.com/paper/2202.02013/) (2022)
- [Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges](https://mlsanity.com/paper/2405.15604/) (2024)
- [DALD: Improving Logits-based Detector without Logits from Black-box LLMs](https://mlsanity.com/paper/2406.05232/) (2024)
- [Online Detection of LLM-Generated Texts via Sequential Hypothesis Testing by Betting](https://mlsanity.com/paper/2410.22318/) (2024)
- [DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm](https://mlsanity.com/paper/2509.15550/) (2025)
- [A Comparison of DeepSeek and Other LLMs](https://mlsanity.com/paper/2502.03688/) (2025)
- [Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction](https://mlsanity.com/paper/2505.05084/) (2025)
- [Mutation-Based Adversarial Attacks on Neural Text Detectors](https://mlsanity.com/paper/2302.05794/) (2023)
- [Conversational Agents: Theory and Applications](https://mlsanity.com/paper/2202.03164/) (2022)

## Abstract (arXiv)

Advanced neural language models (NLMs) are widely used in sequence generation tasks because they are able to produce fluent and meaningful sentences. They can also be used to generate fake reviews, which can then be used to attack online review systems and influence the buying decisions of online shoppers. To perform such attacks, it is necessary for experts to train a tailored LM for a specific topic. In this work, we show that a low-skilled threat model can be built just by combining publicly available LMs and show that the produced fake reviews can fool both humans and machines. In particular, we use the GPT-2 NLM to generate a large number of high-quality reviews based on a review with the desired sentiment and then using a BERT based text classifier (with accuracy of 96%) to filter out reviews with undesired sentiments. Because none of the words in the review are modified, fluent samples like the training data can be generated from the learned distribution. A subjective evaluation with 80 participants demonstrated that this simple method can produce reviews that are as fluent as those written by people. It also showed that the participants tended to distinguish fake reviews randomly. Three countermeasures, Grover, GLTR, and OpenAI GPT-2 detector, were found to be difficult to accurately detect fake review.