Mindful Expression: AI-Powered Reader-Centric Support for Digital Well-being
Project Description
Digital communication now plays a central role in how people collaborate, learn, and build relationships. However, in many real-world contexts—particularly in workplaces—communication is shaped by power dynamics and uneven social norms. Individuals in positions of authority may express themselves in ways that are brief, ambiguous, or overly direct, while recipients are often expected to interpret and respond appropriately. This asymmetry places a cognitive and emotional burden on readers, who must make sense of messages they cannot control, often leading to stress, negative affect, or misinterpretation.
Existing solutions largely adopt a writer-centric approach, focusing on helping authors refine tone, grammar, or wording. While useful, these approaches rely on the assumption that writers are willing or able to adjust their behavior—an assumption that frequently does not hold in practice, especially in hierarchical or high-pressure environments.
In contrast, this project proposes a reader-centric paradigm for digital well-being. By shifting the focus from expression to perception, this work repositions AI as a personalized mediation layer that empowers individuals to engage with digital communication in a healthier and more constructive way. Ultimately, the project aims to improve comprehension, reduce conflict, and support more balanced and resilient digital interactions.
Existing solutions largely adopt a writer-centric approach, focusing on helping authors refine tone, grammar, or wording. While useful, these approaches rely on the assumption that writers are willing or able to adjust their behavior—an assumption that frequently does not hold in practice, especially in hierarchical or high-pressure environments.
In contrast, this project proposes a reader-centric paradigm for digital well-being. By shifting the focus from expression to perception, this work repositions AI as a personalized mediation layer that empowers individuals to engage with digital communication in a healthier and more constructive way. Ultimately, the project aims to improve comprehension, reduce conflict, and support more balanced and resilient digital interactions.
Supervisor
SHAO, Qijia
Quota
2
Course type
UROP1100
UROP2100
UROP3100
UROP3200
UROP4100
Applicant's Roles
he applicant will be actively involved in the full lifecycle of the project. Primary responsibilities include:
Supporting the implementation of advanced semantic processing techniques for problematic content detection and re-representation.
Participating in the system evaluation on information integrity and stylistic alignment after re-representation.
Contributing to the design of context-aware feedback mechanisms for enhancing digital well-being.
Supporting data collection and analysis, including pilot testing and formal experiments with users while ensuring data quality and privacy.
Collaborating on research synthesis and potential paper writing/submission.
Supporting the implementation of advanced semantic processing techniques for problematic content detection and re-representation.
Participating in the system evaluation on information integrity and stylistic alignment after re-representation.
Contributing to the design of context-aware feedback mechanisms for enhancing digital well-being.
Supporting data collection and analysis, including pilot testing and formal experiments with users while ensuring data quality and privacy.
Collaborating on research synthesis and potential paper writing/submission.
Applicant's Learning Objectives
By participating in this project, the applicant will:
Gain hands-on experience in Human-AI Interaction research and semantic processing techniques.
Understand and apply Human-Centered Design (HCD) principles to address complex social challenges in digital environments.
Develop skills in semantic processing and the application of cutting-edge linguistic models to real-world data.
Acquire expertise in designing and evaluating adaptive user interfaces focused on digital well-being and interpersonal harmony.
Improve communication and collaboration skills through participation in a multidisciplinary research environment.
Gain hands-on experience in Human-AI Interaction research and semantic processing techniques.
Understand and apply Human-Centered Design (HCD) principles to address complex social challenges in digital environments.
Develop skills in semantic processing and the application of cutting-edge linguistic models to real-world data.
Acquire expertise in designing and evaluating adaptive user interfaces focused on digital well-being and interpersonal harmony.
Improve communication and collaboration skills through participation in a multidisciplinary research environment.
Complexity of the project
Moderate