Summary: Researchers have developed an AI tool called EmoSync that boosts empathy by tailoring emotional analogies to each user’s personality and life experiences. Unlike traditional empathy tech that assumes uniform emotional responses, EmoSync uses a large language model (LLM) to map personal traits and generate custom scenarios that resonate more deeply.
In a study of over 100 participants, those using EmoSync showed significantly better understanding of others’ emotions than with conventional methods. The technology represents a new frontier in emotion-aware AI, aiming to foster authentic interpersonal understanding in complex social environments.
Key Facts:
- Personalized Empathy: EmoSync uses LLMs to create custom emotional analogies based on user personality and values.
- Validated Results: Users demonstrated significantly improved emotional understanding compared to traditional empathy tools.
- Real-World Impact: EmoSync helps bridge emotional gaps in diverse societies by translating others’ feelings into relatable experiences.
Source: POSTECH
A research team at POSTECH (Pohang University of Science and Technology, South Korea) has developed AI technology that helps individuals deeply understand others’ emotions by analyzing individual personality traits and values and generating personalized analogy.
This study was recognized with the “Popular Choice Honorable Mention Award,” given to the top 5% of 74 Interactivity track demonstrations at ACM CHI 2025, the world’s leading international conference in Human-Computer Interaction (HCI).
Society is a complex community where people with different identities and diverse backgrounds live together. While people strive to understand each other, even the concept of “empathy” can sometimes feel overwhelming – because even in the same situation, emotions can differ greatly from person to person.
Until now, computer-based empathy technologies have been operating on the assumption that showing the same experience would evoke similar emotions. However, reality is more complicated: emotional reactions vary widely depending on an individual’s personality, past experiences, and values.
“EmoSync”, an LLM-based agent, embraces and utilizes these individual differences. By meticulously analyzing each user’s psychological traits and emotional response patterns, the LLM generates personalized analogical scenarios that allow people to understand others’ feelings through the lens of their own experiences.
For example, if a user struggles to empathize with subtle discrimination or exclusion in the workplace, EmoSync analyzes the user’s past experiences and creates a relatable connection, such as ‘a moment of feeling excluded by peers during school days.’
This approach helps users understand others’ emotions more vividly and realistically by using the lens of familiar experiences.
The research team conducted experiments involving over 100 participants from diverse backgrounds using this technology. The results showed that participants who used EmoSync demonstrated significantly improved emotional understanding and empathy compared to traditional methods.
This scientifically demonstrates that personalized metaphorical experiences can genuinely enhance empathy.
Hyojin Ju, the first author of the study, said, “Our research demonstrates that AI can be used to facilitate genuine understanding and empathy among people,” and added, “We will continue to develop AI technologies that help foster true understanding and empathy in real-life situations.”
Professor Inseok Hwang of POSTECH commented, “This study is a successful example showing that generative AI can identify each user’s unique emotional structure and generate personalized experiences that induce specific emotions. It represents a novel and meaningful approach-both academically and socially-to fostering empathy in ways that were not possible before.”
This research was conducted by Professor Inseok Hwang and Ph.D. students Hyojin Ju, Jungeun Lee, and Seungwon Yang from POSTECH’s Department of Computer Science and Engineering, in collaboration with Professor Jungseul Ok.
Funding: The project was supported by the National Research Foundation of Korea (NRF) Mid-career Researcher Program, the Future Convergence Technology Pioneer Project funded by the Korean government (MSIT), and the University ICT Research Center Project from the Institute of Information & Communications Technology Planning & Evaluation (IITP), also funded by the Korean government (MSIT).
About this AI and empathy research news
Author: Jinyoung Huh
Source: POSTECH
Contact: Jinyoung Huh – POSTECH
Image: The image is credited to Neuroscience News
Original Research: The findings will be presented at ACM CHI 2025
