Researchers tested widely available generative AI models such as ChatGPT, Claude and LLaMa. They asked the AI to read short daily video diaries or longer recordings of people talking about their thoughts.
The data came from more than 160 people collected in real-life and lab settings. The AI then answered personality questions the way each person would. Older text-analysis methods did not perform nearly as well as these newer AI systems.
Results showed the AI scores closely matched how people rated themselves and often matched self-ratings better than ratings from friends or family. The AI ratings also predicted emotions, stress, social behaviour and whether someone had sought help for mental health.
Difficult words
- generative — that can create new text or content
- diary — a short daily personal written recorddiaries
- recording — a saved audio or video of speechrecordings
- model — a computer program that makes predictionsmodels
- personality — the usual ways a person thinks and behaves
- self-rating — a person's own score or opinion about themselvesself-ratings
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- Would you share a short video diary with an AI? Why or why not?
- Do you trust AI to understand people's feelings? Explain briefly.
Related articles
New method could link quantum computers over long distances
Researchers at the University of Chicago describe a theoretical method to connect quantum computers over about 2,000 km by improving how long atoms keep quantum states. The team used a different crystal growth process and will test links in the lab.
Study: Low numbers of women in science academies
An international analysis finds women made up about 19% of academy members in 2025, with little change in recent years. The report highlights leadership gaps, higher reports of harassment, and calls for stronger gender equality measures.
Social media can give early warning of displacement
Researchers find that analysing social media posts can give early warning of population movements and help humanitarian agencies respond faster. The study in EPJ Data Science tested methods across three case studies using nearly 2 million posts on X.