This app can read your mood

Feb 04, 2017 06:00 am

A team at the Massachusetts Institute of Technology (MIT), in the US, has built a wearable app that analyses a conversation to identify the user's emotions, reported The Verge.

The app, built into a fitness tracker for the research, collects physical and speech data to analyse the overall tone of the speech in real time.

Using artificial intelligence (AI), the app can also figure out which part of the conversation is happy or sad and tracks emotional changes in five-second intervals.

Generally, the AI associated long pauses or monotonous vocal tones as sad, while varied speech patterns were categorised as happy - with an 83 per cent accuracy.

In ongoing research at an MIT laboratory to study emotion detection, participants were asked to wear a Samsung Simband with the app installed and tell a story.

The band monitored changes in the participants' skin temperature and heart rate, or movements such as waving of arms or fidgeting.