메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Hanyang University) (Hanyang University) (Hanyang University)
저널정보
한국HCI학회 한국HCI학회 학술대회 PROCEEDINGS OF HCI KOREA 2026 학술대회 발표 논문집
오류 신고하기

피인용 0

검색

    초록·키워드

    LLM-based AI companions offer continuous availability and support, yet interactions relying solely on uncritical empathy may inadvertently reinforce dysfunctional thoughts or emotional dependence. Attempts to address these risks through regulation often overlook fundamental interaction design, while existing mental health chatbots prioritize clinical objectives that diverge from the friend-like relationship users expect. Meanwhile, research in clinical psychology has consistently demonstrated that everyday cognitive strategies serve as critical protective factors that buffer stress and predict long-term well-being. To operationalize this, we propose a system that naturally embeds implicit cognitive reframing into daily interactions, aiming to foster users' resilience and emotional regulation capabilities. By estimating relationship stages based on Social Penetration Theory (SPT) and a Relationship Health Index (RHI), the architecture dynamically balances the ratio of empathy to perspective-taking. This framework presents a preventive design approach, suggesting structural possibilities for Human-AI interactions that transition from temporary relief to long-term psychological resilience.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-26-02-096524902