Tripadvisor’s new AI-generated review summaries for hotels have not picked up on reports of food poisoning, sexual harassment and hygiene failures, an investigation has found.

Consumer champion platform Which? has been testing out Tripadvisor’s new AI tool that summarises hotel reviews left by users, concluding that it has failed to give a clear picture of some of the accommodations’ serious shortcomings.

While browsing Tripadvisor, users will now see an AI summary in the hotel’s reviews section, which collects recent reviews and outlines them in generated sentences.

Which? noticed in one case that the summary of the five-star, all-inclusive Riu Palace Santa Maria in Cape Verde included phrases such as “popular with many travellers”, “diverse restaurants” that earn “rave reviews”, and cleanliness described as “spotless”.

Yet some reviewers told a different story, with recent guests saying the hotel had “exceptionally poor hygiene” and food that was “'awful, bland, unsafe and inedible”.

One reviewer described being served raw chicken, while another shared a photograph of flies and birds in the buffet food. A third guest said they spotted “dead little roasted mice by the sitting area” on her “nightmare” holiday.

Which? said that in March this year, there were 102 mentions of food poisoning at the Riu Palace, along with 32 one or two-star reviews posted between December 2025 and April 2026. Some 14 of these said at least one member of the party fell seriously ill due to food poisoning.

A spokesperson from RIU Hotels & Resorts said that “the health and safety of our guests is always our main priority”.

They added: “Let us assure that we operate with the highest standards of professionalism and service, placing hygienic-sanitary safety as our top priority. Our hotels in Cape Verde follow the strictest international health and hygiene standards, certified by external prestigious consultancy firms, specialised in health and safety.”

The AI-generated summary also lauded a hotel in the Dominican Republic for its “abundant” amenities, but did vaguely nod to “inconsistent” cleanliness and “maintenance issues”.

Meanwhile, recent reviewers mentioned the lack of access to running water, with one guest resorting to showering with bottled water, while others complained of the hotel smelling of sewage and mould.

Which? also pointed to a hotel in Turkey, where some guests had left Tripadvisor reviews last summer stating that they had felt unsafe due to sexual harassment from male hotel staff, including inappropriate jokes and gestures, and repeated requests to connect on social media.

Yet the AI summary of reviews said the service at the hotel was “friendly” and only mentions “lapses [in service] noticed by a few”.

Tripadvisor said it “fundamentally disagrees” with the premise of Which? investigation. A spokesperson for Tripadvisor said the AI summaries were designed to uphold “integrity and transparency”.

They added: “They provide snapshots based on high volumes of user-generated content and explicitly are not intended to replace individual reviews. Users can easily click to see the traveller quotes behind each review element or access all reviews for that listing, eliminating any need to blindly trust AI-generated content.

“We also have comprehensive safeguards in place to ensure important safety information is properly reflected across our platform. Our AI systems are designed to capture all types of traveller feedback, and we continuously monitor and refine our models.

“Our systems automatically suppress AI Summaries for listings that feature warnings from travellers about serious safety incidents such as death, drugging or sexual assault, helping ensure this content is highly visible to our community.

Which? Also tested out Tripadvisor’s AI chatbot, which they said failed to warn holidaymakers of poor hygiene at hotels.

“Our AI-powered chat assistant draws from a selection of reviews based on detail and recency, and matches by language and context,” the Tripadvisor spokesperson said. “We are actively looking into the examples where reviews did not match the intended property, and, as with all products in development, we will use the feedback to improve the traveller experience.

“No review content has been suppressed or hidden by the introduction of these tools, and the suggestion they pose danger to travellers is an unfounded claim that seems designed to generate controversy rather than inform readers.

“We believe our community understands that AI technology is still developing and has the common sense to check any AI advice against Tripadvisor's billion-plus reviews and contributions.”

Rory Boland, Editor of Which? Travel said: “The platform has a responsibility to revisit the accuracy of its AI summaries and AI chatbot.

“In the meantime, users should scroll past these summaries and look at guest reviews, particularly one-star ratings, and at reviews on other sites, to make sure their next stay is a safe one.”

Read more: UK-based travel company enters administration with all bookings cancelled from September

Read More