WHO HAS GOT THE GPT RADAR?

Test your ability to distinguish between human-written and GPT-generated reviews

Can you spot the difference between human-written and AI-generated reviews?

Here, you have 50 reviews to distinguish.

The top 10 scorers will be shown in the leaderboard.

Good luck!

Leader board

Not seeing your name? Reload the page after completing the challenge and it should appear!

Background

Considerable research has been conducted on consumer insight analysis, which relies heavily on user-generated content as a crucial data source for obtaining these insights [1]. Customers frequently depend on online reviews to evaluate the utility and quality of various offerings, not just for physical products but also for experiential services like hotels and restaurants. Similarly, businesses use these reviews to enhance their marketing efforts.

However, recent studies show that humans often struggle to recognise AI-generated reviews [2], [3].

From a marketing perspective, this trend is harmful as it can skew public perception and brand reputation.

For businesses, fake negative reviews can also become weapons of attack.
For consumers, fake reviews can bias decision-making processes. Consumer decisions should be based on accurate and genuine information.

From another perspective, the increase of fake data on the internet is also damaging in the current environment [4], where more data are being generated and used to train language models. This can compromise the quality of the models themselves.

As language models continue to improve, the distinction between human and AI-generated text may become even more blurred. However, the degree to which people can identify AI-generated content can also depend on several factors [5], [6].

Introduction

In light of these concerns, we would like to better understand and enhance our ability to distinguish between human-written reviews and AI-generated reviews.

We set this up as a part of a pilot study to see how well we can tell apart real reviews from those generated by generative language models. Think of this as your playground to test your skills, have some fun, and help us gather important data at the same time.

Your participation will not only give you a firsthand experience of the challenge but also contribute significantly to our research.

About the Competition

Participate and see if you have a radar to identify GPT-generated content!

The human-written reviews have been sampled from publicly available Amazon Review 2023 [7], while the fakes were crafted by the latest 'ChatGPT o1'.

There is no timer on this session, but try to make your choices as quickly as you can.

Once you make a selection, note that we won't reveal if it is right or wrong right away.

Coming soon: Advance mode

In our upcoming advanced mode, you won’t just be spotting differences in text. We will challenge you to identify the authenticity of reviews that include both text and images.

Ready to take your detective skills up a notch?

References

[1] Netzer, O., Feldman, R., Goldenberg, J., & Fresko, M. (2012). Mine your own business: Market-structure surveillance through text mining. Marketing Science, 31(3), 521-543.

[2] Salminen, J., Kandpal, C., Kamel, A. M., Jung, S. G., & Jansen, B. J. (2022). Creating and detecting fake reviews of online products. Journal of Retailing and Consumer Services, 64, 102771.

[3] Kovács, B. (2024). The Turing test of online reviews: Can we tell the difference between human-written and GPT-4-written online reviews?. Marketing Letters, 1-16.

[4] Xing, X., Shi, F., Huang, J., Wu, Y., Nan, Y., Zhang, S., ... & Yang, G. (2024). When AI Eats Itself: On the Caveats of Data Pollution in the Era of Generative AI. arXiv preprint arXiv:2405.09597.

[5] Xylogiannopoulos, K. F., Xanthopoulos, P., Karampelas, P., & Bakamitsos, G. A. (2024). ChatGPT paraphrased product reviews can confuse consumers and undermine their trust in genuine reviews. Can you tell the difference?. Information Processing & Management, 61(6), 103842.

[6] Jia, S. J., Chi, O. H., & Chi, C. G. (2025). Unpacking the impact of AI vs. human-generated review summary on hotel booking intentions. International Journal of Hospitality Management, 126, 104030.

[7] Hou, Y., Li, J., He, Z., Yan, A., Chen, X., & McAuley, J. (2024). Bridging language and items for retrieval and recommendation. arXiv preprint arXiv:2403.03952.

Contact

I'm always looking for new and exciting opportunities. Let's connect.

info@thinkbetterworld.com