/ EN
2026-07-29 00:00 Papers Foundations & Methods Translated from EN

EmoWrite BCI Converts Thought to Text with 90% Accuracy

Summary Researchers in Pakistan and South Korea have built EmoWrite, a brain-computer interface that uses sentiment analysis to turn thought into text, typing at 6.6 words per minute with 90.36% accuracy in tests with 72 volunteers. The system adds a dynamic keyboard and visual feedback to make the interface easier to use.
Why it matters The 87.55 bits/min command rate matters more here than the accuracy headline: it puts a non-invasive speller at a throughput where the limit shifts from signal quality to how well the interface predicts what the user wants to say.

BCIwiki (bciwiki.com) — A new brain-computer interface (BCI) system called EmoWrite achieved 90.36% accuracy in converting thought to text, with a typing speed of 6.6 words per minute, in a study of 72 volunteers reported on July 29, 2026, in the International Journal of Human–Computer Interaction. Developed by researchers at COMSATS University Islamabad in Pakistan and Yeungnam University in South Korea, the system aims to address shortcomings in existing BCI systems, including typing speed, accuracy, and emotional state capture.

EmoWrite uses a user-centric recurrent neural network, incorporates visual feedback, and introduces a dynamic keyboard with contextually adaptive character appearance. Data were collected from 72 volunteers (40 male, 32 female) aged 18 to 40 years. The system achieved information transfer rates of 87.55 bits/min for commands and 72.52 bits/min for letters, with a low interface latency of 2.685 seconds. The research team said EmoWrite excels in capturing emotional states compared with other systems and offers a more intuitive user interface.

Compiled by BCIwiki from public sources

Sources · 1
doi.org 2026-07-29
Read original ↗
Suggest a correction Revisions · none / EN
© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About