Quality and readability of AI-generated information on bipolar disorder: a cross-sectional content analysis
Ibrahim Karakaya · 2026
Read Quality and readability of AI-generated information on bipolar disorder: a cross-sectional content analysis by Ibrahim Karakaya (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13479570.txt.
Description
Ibrahim Karakaya published a 2026 cross-sectional content analysis, as sole author, of how well chatbots explain bipolar disorder. People increasingly ask large language models about this sensitive and complex condition, where fuzzy information can delay care or distort treatment choices. Twenty questions drawn from Google Trends were put to ChatGPT, Gemini, and DeepSeek, each in three fresh sessions, yielding 180 responses.
Two trained scales measured information quality and reading difficulty, including grade level and reading ease scores. Statistical models accounted for repeated answers to the same question when comparing the three systems. The study benchmarks which model explains bipolar disorder most completely and most readably, giving clinicians and developers evidence for guiding patients toward safer sources.
Catalog record
| CREATOR | Ibrahim Karakaya |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42735 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |