What if smartwatch-you can detect what you’re feeling? It sounds rather improbable.
However, there is a software for wearable devices that can do just that: detect the emotions of what is spoken of the users. The software was developed by a research team at the Massachusetts Institute of Technology (MIT), United States (US).
This software uses an algorithm to monitor voice, text transcribing and bio-signals to determine what is perceived user. The researcher team says that the level of accuracy of the software reaches 83 percent if measured based emotional speech intonation.
They found that certain signals, such as monotone, long pauses, increased activity and restlessness may signal heart sad emotions. Meanwhile, this software detects emotion every five seconds of each conversation with a 18 percent accuracy rate.
The software is currently used by Simband, wearable platform development company based Tizen OS Samsung. However, they plan to bring it in commercial products, such as Apple Watch.
They hope that this software can be useful as a wearable device that can help coach based artificial intelligence to help people who have high anxiety.
Imagine if at the end of each conversation, we can repeat and know that there are people around us who have high anxiety.