The IEEE Transactions on Affective Computing is a cross-disciplinary and international archive journal aimed at disseminating results of research on the design of systems that can recognize, interpret, and simulate human emotions and related affective phenomena. The journal publishes original research on the principles and theories explaining why and how affective factors condition interaction between humans and technology, on how affective sensing and simulation techniques can inform our understanding of human affective processes, and on the design, implementation and evaluation of systems that carefully consider affect among the factors that influence their usability. Surveys of existing work are considered for publication when they propose a new viewpoint on the history and the perspective on this domain.

The journal covers but is not limited to the following topics:

Sensing & analysis: Algorithms and features for the recognition of affective state from face and body gestures; Analysis of text and spoken language for emotion recognition; Analysis of prosody and voice quality of affective speech; Recognition of auditory and visual affect bursts; Recognition of affective state from central (e.g. fMRI, EEG) and peripheral (e.g. GSR) physiological measures; Methods for multi-modal recognition of affective state; Recognition of group emotion; Methods of data collection with respect to psychological issues as mood induction and elicitation or technical methodology as motion capturing; Tools and methods of annotation for provision of emotional corpora.

(Cyber) psychology & behavior: Clarification of concepts related to ‘affective computing’ (e.g., emotion, mood, personality, attitude) in ways that facilitate their use in computing; Computational models of human emotion processes (e.g., decision-making models that account for the influence of emotion; predictive models of user emotional state); Studies on cross-cultural, group and cross-language differences in emotional expression; Contributions to standards and markup language for affective computing.

Behavior Generation & User Interaction: Computational models of visual, acoustic and textual emotional expression for synthetic and robotic agents; Models of verbal and nonverbal expression of various forms of affect that facilitate machine implementation; Methods to adapt interaction with technology to the affective state of users; Computational methods for influencing the emotional state of people; New methods for defining and evaluating the usability of affective systems and the role of affect in usability; Methods of emotional profiling and adaptation in mid- to long-term interaction; Application of affective computing including education, health care, entertainment, customer service, design, vehicle operation, social agents/robotics, affective ambient intelligence, customer experience measurement, multimedia retrieval, surveillance systems, biometrics, music retrieval and generation.

Special Issue on Can AI Care? Affective LLMs for the Future of Mental Health
提出日: 2025-10-30

Important Dates 

Manuscript Submission Deadline October 30, 2025 
First Review Notification December 1, 2026 
Revised Manuscript Due February 1, 2026 
Final Decision Notification March 1, 2026

Aim and Scope

Mental health has become a critical global concern, with far-reaching implications for individual well-being, societal cohesion, and public healthcare systems. Traditional mental health services face challenges in scalability, personalization, and accessibility. In response, artificial intelligence—particularly systems capable of emotional awareness—offers promising avenues to support mental health interventions at scale. 

The rapid advancement of Large Language Models (LLMs) has transformed the landscape of natural language processing, enabling more sophisticated and human-like interactions. However, these models often lack the affective depth and the genuine empathy that are crucial in emotionally sensitive contexts like mental health. Integrating affective computing principles into LLMs represents a promising direction to address this gap, enabling emotionally intelligent systems that are context-aware, ethically aligned, and capable of building trust in high-stakes interactions. 

This special issue aims to explore interdisciplinary approaches that integrate affective computing, psycho-cognitive disciplines, and LLMs to advance empathetic AI in mental health applications. We welcome contributions that investigate theoretical foundations, novel algorithms, and real-world systems that enhance the emotional awareness and relational intelligence of LLMs. In particular, the issue will emphasize clinical application and deployment strategies, as well as domain-specific customizations that cater to unique healthcare scenarios. Our goal is to foster research that paves the way for emotionally responsive and trustworthy AI agents capable of making meaningful contributions to mental health care. 

Topics of Interest 

We invite original research articles, theoretical contributions, and system-level studies on topics including (but not limited to): 

    Emotion detection and affect modeling in large-scale language models. 
    Affective and empathetic dialogue generation. 
    Personalization and contextual adaptation for emotional support systems. 
    Multimodal affective computing in LLM-integrated systems (text, audio, visual). 
    LLM-based mental health screening and early detection tools. 
    Human-in-the-loop training for empathetic AI.
    Computational models of empathy, compassion, and rapport in language generation.
    Cross-linguistic and cultural generalization of affective LLMs. 
    Evaluation frameworks for empathy, engagement, and emotional appropriateness.
    Ethical, privacy, and fairness considerations in emotionally-sensitive applications. 
    Deployment studies of AI mental health assistants or therapeutic agents. 
    Clinical applications and deployment: Real-world case studies and integration strategies in healthcare settings. 
    Domain-specific customization: Tailored affective LLM solutions for specific patient groups (e.g., elderly, adolescents, chronic disease management).