To improve AI interactions, Finnish researchers have developed a technology that allows computers to understand human emotions, potentially allowing machines to adjust their behavior to improve interaction with the user.
Using principles of mathematical psychology, researchers from the University of Jyväskylä in Finland have created a model that allows computers to recognize and understand human emotions. This breakthrough could improve the interaction between humans and smart technologies, such as artificial intelligence systems, by making them more attuned and responsive to users’ emotions.
According to Jussi Jokinen, associate professor of cognitive science, the model could be used in the future by a computer to predict, for example, when a user will become angry or anxious. In such cases, the computer may, for example, provide additional instructions to the user or redirect the interaction.
Users often experience emotions such as joy, distress, and boredom during their daily interactions with computers. Despite the increasing prevalence of artificial intelligence, modern technologies often do not recognize these emotions of users. The model developed in Jyväskylä can currently predict whether the user has emotions such as happiness, boredom, irritation, anger, despair and anxiety.
“Humans naturally interpret and respond to each other’s emotions, a capability that machines fundamentally lack,” explains Jokinen. “This inconsistency can lead to frustrating interactions with computers, especially if the machine is unaware of the user’s emotional state.”
A research project led by Jokinen uses mathematical psychology to address the problem of incompatibility between intelligent computer systems and their users.
“Our model can be integrated into artificial intelligence systems, allowing them to psychologically understand emotions and thus communicate better with their users,” says Jokinen.
The research is based on affective theory; the next step is to influence the user’s emotions
The study is based on a theory that suggests emotions arise when human cognition evaluates events from different perspectives.
Jokinen explains: “Consider a computer error that occurs during a critical task. This event is considered unproductive by the user’s cognition. A novice user may react with anxiety and fear due to uncertainty about how to fix the error, while an experienced user may feel annoyed and annoyed by having to spend time fixing the problem. “Our model simulates this cognitive evaluation process, predicting the user’s emotional response.”
The next phase of this project will explore potential applications of this emotional understanding.
“Thanks to our model, the computer can anticipate the user’s distress and try to alleviate negative emotions,” says Jokinen.
“This proactive approach can be used in a variety of environments, from office environments to social media platforms, and can increase user engagement by carefully managing emotional dynamics.”
The implications of this type of technology are profound, opening up the possibility of a glimpse into a future where computers will not just be tools, but empathetic partners interacting with the user.
Source: Port Altele
