Research – ThePrint – ANIFeed

Tokyo (Japan), November 30 (ANI): Researchers at Tokyo Metropolitan University used long-term measurements of skin conductance to differentiate between emotions. Volunteers were presented with videos representing scary scenarios, family connections and humor, and their skin conductance was measured.

New horizons are opening up in consumer electronics: one day, digital devices will be able to offer services based on your emotional state. While this sounds amazing, it depends on whether the devices can correctly detect what people are feeling. The most common methods depend on facial expressions: although they have some success, such data may not always be available. This led researchers to look for various biological signals that could be interpreted to access emotional states, such as brain wave measurements or cardiograms.

A team of scientists led by Professor Shogo Okamoto from Tokyo Metropolitan University used skin conductivity as a pathway to human emotions. When people feel different things, the electrical properties of their skin change dramatically due to sweating, with signals appearing within one to three seconds of the original stimulus. Previous research has already shown that peak conductance measurements, for example, can correlate with certain emotions. In their latest work, the team focused on the dynamics of the response, that is, how quickly the conductance curve peaks after some stimulus and how it returns to normal.

In the experiment, volunteers were asked to place probes on their skin and watch videos that were either scary scenes from horror films, emotional scenes of family bonding, or funny acts performed by comedians. It is important to note that in each of the scenes there were clearly defined points at which a specific emotional stimulus was sought. By analyzing the traces, the team discovered many interesting and significant trends. For example, they found that the fear response lasted the longest. This may be a biologically evolved trait, as long-term perception of danger is beneficial. Comparing reactions to humor and emotional scenes of family ties, they found that reactions to family ties increased more slowly. The emotions elicited were most likely a mixture of sadness and happiness, so perhaps they interfered with each other, resulting in slower change.

Importantly, the team’s statistical analysis showed that different numbers extracted from the trace’s dynamics could be used to discern a person’s emotional state. While they can’t yet accurately differentiate between emotions, the data could, for example, be used to make statistically significant predictions about whether a subject experiences fear or feels the warmth of family ties. Combined with other signals, the team believes we are one step closer to devices learning how we feel and being able to better understand human emotions. (ANI)

This report is automatically generated by ANI News Service. ThePrint is not responsible for its content.