Rethinking directiveness in AI coaching chatbots.

Front Psychol · 2026 · PMC13337845 · PMID 42416164

Europe PMC DOI

hedged sentence

0.0800

closest p · 1.6× alpha

0.0800

boldest claim

The sentences

near-significantp = 0.08so close (0.05 < p ≤ 0.1)

For goal attainment, D-Bot was rated higher than N-Bot at a near-significant level (GA; p = 0.08; Cohen’s d = 0.28), suggesting a trend in favour of the directive chatbot.

also in 1,650 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.