Human-Centred Learning Analytics and AI in Education: a Systematic Literature Review

TL;DR

A systematic literature review of human-centred LA/AIED research suggests carefully balancing stakeholders' involvement in designing and deploying LA/AIED systems throughout all design phases, and actively involving target end-users to delineate the balance between human control and automation.

Abstract

The rapid expansion of Learning Analytics (LA) and Artificial Intelligence in Education (AIED) offers new scalable, data-intensive systems but also raises concerns about data privacy and agency. Excluding stakeholders -- like students and teachers -- from the design process can potentially lead to mistrust and inadequately aligned tools. Despite a shift towards human-centred design in recent LA and AIED research, there remain gaps in our understanding of the importance of human control, safety, reliability, and trustworthiness in the design and implementation of these systems. We conducted a systematic literature review to explore these concerns and gaps. We analysed 108 papers to provide insights about i) the current state of human-centred LA/AIED research; ii) the extent to which educational stakeholders have contributed to the design process of human-centred LA/AIED systems; iii) the current balance between human control and computer automation of such systems; and iv) the extent to which safety, reliability and trustworthiness have been considered in the literature. Results indicate some consideration of human control in LA/AIED system design, but limited end-user involvement in actual design. Based on these findings, we recommend: 1) carefully balancing stakeholders' involvement in designing and deploying LA/AIED systems throughout all design phases, 2) actively involving target end-users, especially students, to delineate the balance between human control and automation, and 3) exploring safety, reliability, and trustworthiness as principles in future human-centred LA/AIED systems.

Figures (6)

• Figure 1: The PRISMA protocol as applied in the current systematic literature review
• Figure 2: The distribution of key characteristics in the current research state of human-centred LA/AIED systems, depicted through a Sankey diagram. Categories are sorted by frequency. The diagram illustrates the distribution of education levels, the utilisation of research methodologies (qualitative, quantitative, or mixed), the progression through five multifaceted design phases, and the application of HCD techniques. The varying thickness of the flow path represents the significance of each transition.
• Figure 3: Distribution of stakeholder involvement varies across various design phases. The data demonstrates shifts in passive (black) and active (green) involvement throughout design phases, with more passive stakeholders in Phase 4.
• Figure 4: Distribution of stakeholder involvement in the design of human-centred LA/AIED systems. The green bar represents the percentage of stakeholders actively contributing to and influencing the design. In contrast, the black bar represents the percentage of stakeholders participating in the study with limited influence on design outcomes.
• Figure 5: Distribution of human-centred LA/AIED systems categorised into the human control and computer automation quadrants of the HCAI framework (Q1-Q4, see definitions in Section \ref{['sec:hcai-quadrant']}). The green bars represent studies where the stakeholders actively engaged and contributed to the design of the tools. The black bars represent studies where stakeholders merely participated as test subjects, offering limited input during the design phase of LA/AIED systems.