AI technologies that sense student attention and emotions to enable more personalised teaching interventions are increasingly promoted, but raise pressing questions about student learning, wellbeing, and ethics. In particular, students’ perspectives about AI sensing-intervention in learning are often overlooked. We conducted an online mixed-method experiment with Australian university students (N=132), presenting video scenarios varying by whether sensing was used (in-use vs. not-in-use), sensing modality (gaze-based attention detection vs. facial-based emotion detection), and intervention (by digital device vs. teacher). Participants also completed pairwise ranking tasks to prioritise six core ethical concerns. Findings revealed that students valued targeted intervention but responded negatively to AI monitoring, regardless of sensing methods. Students preferred system-generated hints over teacher-initiated assistance, citing learning agency and social embarrassment concerns. Students’ ethical considerations prioritised autonomy and privacy, followed by transparency, accuracy, fairness, and learning beneficence. We advocate designing customisable, social-sensitive, non-intrusive systems that preserve student control, agency, and well-being.

Adopting AI in multi-stakeholder contexts often involves complex ethical challenges, particularly when decision-makers are not directly impacted by the technology. Ethical challenges arise not only from the design of the AI technology but also from social factors in its development and deployment which may harm disempowered stakeholders. This paper examines how stakeholder dynamics in AI adoption may help to create or mitigate such harm, using a case study of AI-based student monitoring in K-12 education. These systems analyse students’ emotions, concentration, and classroom performance to inform teaching. We conducted 30 semi-structured interviews with key stakeholders: parents, school representatives, and developers. Our findings identify three key social factors that may create ethical problems in decision-making: limited representation of students’ perspectives during design and adoption; developers’ compromises and pragmatism under organisational pressure; and school governors’ limited technological literacy and failure of ‘due diligence’. These factors arise from power imbalances related to knowledge and authority that may weaken accountability mechanisms for governing AI in Education (AIEd) adoption. We propose addressing these imbalances through improving the AI ethics literacy of key stakeholders to ensure effective oversight and informed decision-making. This work contributes an empirical understanding of how real-world power relations shape ethical vulnerabilities in AIEd adoption. It extends HCI and AI ethics research by revealing how stakeholder asymmetries can marginalise affected users and constrain the practical application of ethical design principles. These insights offer guidance for more inclusive and accountable AI governance and provide insights relevant to other multi-stakeholder AI contexts. CCS CONCEPTS • Human-centred computing -> Empirical studies in HCI; Empirical studies in collaborative and social computing.

AI's integration into education promises to equip teachers with data-driven insights and intervene in student learning. Despite the intended advancements, there is a lack of understanding of interactions and emerging dynamics in classrooms where various stakeholders including teachers, students, and AI, collaborate. This paper aims to understand how students perceive the implications of AI in Education (AIEd) in terms of classroom collaborative dynamics, especially AI used to observe students and notify teachers to provide targeted help. Using the story completion method, we analyzed narratives from 65 participants, highlighting three challenges: AI decontextualizing of the educational context; AI-teacher cooperation with bias concerns and power disparities; AI's impact on student behavior that further challenges AI's effectiveness. We argue that for effective and ethical AI-facilitated cooperative education, future AIEd design must factor in the situated nature of implementation. Designers must consider the broader nuances of the education context, impacts on multiple stakeholders, dynamics involving these stakeholders, and the interplay among potential consequences for AI systems and stakeholders. It is crucial to understand the values in the situated context, the capacity and limitations of both AI and human for effective cooperation, and any implications to the relevant ecosystem.