AI Tool EmoSync Boosts Empathy by Creating Personalized Emotional Analogies

Researchers Develop AI Tool to Enhance Empathy

Researchers at POSTECH (Pohang University of Science and Technology) have created an AI tool named EmoSync that improves empathy by generating emotional analogies based on each user's personality and life experiences. Unlike traditional empathy technologies that assume uniform emotional reactions, EmoSync leverages a large language model (LLM) to map individual traits and produce personalized scenarios that resonate more deeply.

In a study involving over 100 participants, those who used EmoSync demonstrated a notably higher ability to understand others' emotions compared to conventional methods. This technology marks a significant advancement in emotion-aware AI, with the goal of promoting genuine interpersonal understanding in diverse social settings.

Key Facts

• Personalized Empathy: EmoSync uses LLMs to craft custom emotional analogies based on personality and values.
• Validated Results: Users showed significantly improved emotional comprehension versus traditional empathy tools.
• Real-World Impact: The tool bridges emotional gaps in diverse societies by translating feelings into relatable experiences.

Introduction

The research team at POSTECH designed AI that analyzes individual personality traits and values to create personalized analogies, helping users grasp others' emotions with greater clarity. Their work was recognized with the “Popular Choice Honorable Mention Award” at ACM CHI 2025, a leading conference in Human-Computer Interaction (HCI). By presenting emotions through familiar experiences, EmoSync enables users to connect with feelings more vividly and realistically.

The Challenge of Empathy

In diverse societies, understanding others' emotions is challenging because emotional responses vary widely among individuals. Traditional empathy tools often assume that similar experiences trigger similar emotions, but this overlooks personal backgrounds, personality differences, and past experiences that shape emotional reactions.

The EmoSync Approach

EmoSync addresses this by incorporating individual differences into its empathy model. The LLM assesses each user's psychological traits and emotional patterns, then generates personalized analogical scenarios. For instance, if a user finds it difficult to relate to subtle workplace discrimination, EmoSync might draw parallels with feelings of exclusion during school days. This method helps users interpret others' emotions through their own familiar experiences, enhancing emotional connection.

Research Findings

The study included over 100 participants from varied backgrounds. Results showed that EmoSync users had significantly improved emotional understanding compared to those using traditional empathy tools. This demonstrates that personalized metaphorical experiences can effectively strengthen empathy.

Hyojin Ju, the study's first author, stated, “Our research shows AI's potential to facilitate genuine empathy among people.” Professor Inseok Hwang added, “This study illustrates how generative AI can identify unique emotional structures in users and produce personalized experiences that evoke specific emotions. It offers a new approach to fostering empathy that wasn’t achievable before.”

Conclusion

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 received support from the National Research Foundation of Korea (NRF) Mid-career Researcher Program, the Future Convergence Technology Pioneer Project funded by the Korean Ministry of Science and ICT (MSIT), and the University ICT Research Center Project from the Institute of Information & Communications Technology Planning & Evaluation (IITP), also funded by MSIT.

For those interested in advancing AI skills, Complete AI Training offers courses covering large language models and emotion-aware AI development.