Learning analytics (LA) has emerged as a powerful approach to improving student success, personalizing

learning, and guiding institutional decision-making. Despite the availability of rich learner data from learning

Innovations (DOI), to propose the Integrated Learning Analytics Adoption Framework (ILAAF). The

framework emphasizes five strategic pillars - vision and governance, capacity building, technology integration,

pedagogical alignment, and continuous evaluation, supported by an operational workflow that transforms raw

data into actionable insights. The findings highlight that adopting ILAAF can shift LA from passive reporting

to active, learner-centered practice. The paper recommends strategic institutional adoption, capacity

development, and ethical governance to ensure LA becomes a dynamic driver of engagement, equity, and long-

term student success.

Driven Teaching

retention, and achievement.

Learning analytics (LA) has emerged as a strategic approach to harnessing this wealth of information. Defined

as the measurement, collection, analysis, and reporting of data about learners and their contexts, LA aims to

understand and optimize learning processes and the environments in which they occur. By applying LA

effectively, institutions can identify at-risk students early, deliver targeted support, and create adaptive learning

pathways that cater to diverse needs. In addition, LA can inform instructional design by highlighting which

resources and activities are most effective in promoting learning, enabling continuous improvement of teaching

practices and course structures.

Despite its transformative potential, evidence indicates that LA remains underutilized in many educational

contexts. While basic descriptive reporting, such as tracking attendance or measuring completion rates, has

Learning analytics (LA) has emerged as a rapidly growing field in educational technology, driven by the

increased adoption of digital learning platforms and the availability of large datasets on learner behaviours.

and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning

and the environments in which it occurs” (SoLAR, 2022). The evolution of LA can be traced from early

descriptive reporting within learning management systems (LMS) to more sophisticated predictive and

prescriptive models that aim to provide real-time and personalized feedback (Márquez et al., 2024). In higher

education, LA plays a strategic role in both academic and administrative decision-making, offering tools to

A core advantage of LA is its capacity to identify at-risk learners early in the academic cycle, enabling timely

interventions that can prevent dropout or failure. Studies demonstrate that predictive models using variables

based on such models have reported measurable improvements in retention rates and student satisfaction.

Another significant benefit of LA lies in its potential to support adaptive learning. By analyzing individual

learning behaviours and performance data, LA systems can recommend tailored learning activities, resources,

and pacing. This adaptive approach can be further enhanced through integration with microlearning strategies,

delivering short, focused learning modules in response to identified gaps (Price et al., 2025). Personalized

learning pathways increase engagement and motivation, particularly in online and blended environments where

learner autonomy is critical.

LA also offers powerful insights for curriculum development. Analysis of aggregated learner data can highlight

the effectiveness of specific resources, pinpoint challenging content areas, and reveal correlations between

intervention are missed.

A significant barrier to effective LA adoption is the limited data literacy among educators and decision-makers.

Without adequate training, staff may struggle to interpret analytics outputs or translate them into actionable

strategies (Márquez et al., 2024). Professional development and institutional support structures are essential to

bridge this gap.

Ethical considerations around data privacy, consent, and transparency are another key limitation. Regulations

Regulation (GDPR) require strict handling of personal information. Failure to address these concerns can erode

The adoption and effective use of LA can be understood through established technology adoption theories. The

Technology Acceptance Model (TAM) posits that perceived usefulness and perceived ease of use are primary

determinants of technology adoption (Davis, 1989; Almaiah et al., 2022). In the LA context, educators are

more likely to engage with analytics tools if they believe these tools will improve teaching effectiveness and

are straightforward to operate. Complementing TAM, the Diffusion of Innovations (DOI) theory explains

adoption at the organizational level. DOI highlights five key attributes influencing adoption: relative

advantage, compatibility, complexity, trialability, and observability (Rogers, 2003). For LA, relative advantage

is demonstrated when analytics lead to tangible improvements in learning outcomes; compatibility is reflected

in alignment with existing pedagogical practices; and trialability is supported by pilot programs before full-

While the literature affirms the benefits of LA, there remains a clear gap in systematic strategies for shifting

from passive reporting to active, intervention-oriented use. Few studies have examined the integration of LA

with microlearning, multimodal analytics, and structured early-warning protocols in a cohesive framework.

Additionally, limited research exists on the contextualization of LA adoption within Malaysian higher

education, particularly in aligning ethical governance with capacity building and pedagogical integration.

Addressing these gaps presents an opportunity to develop a context-specific framework that can maximize the

impact of LA on student engagement, equity, and success.

Despite the increasing availability of learning analytics (LA) tools, many institutions fail to leverage their full

potential. While digital platforms and LMS environments generate vast amounts of learner data, much of this

information remains underused, serving primarily as static reports rather than catalysts for meaningful

educational change. In many cases, analytics functions are limited to tracking basic activity metrics, without

learners well before critical assessments. This allows for timely outreach, academic support, and tailored

interventions that improve retention (Shen et al., 2023; Song et al., 2024). Without such proactive

systems, students who might have been helped often remain unnoticed until it is too late.

content, pace, and difficulty based on individual learner needs. However, these remain rare in practice

due to technological, pedagogical, and resource-related constraints.

enhance self-monitoring and self-regulated learning. Unfortunately, many dashboards are designed

primarily for administrators or instructors, limiting their impact on learners.

Why It Happens The underutilization of LA stems from a combination of technical, cultural, and policy-related

challenges:

translate insights into effective teaching strategies (Márquez et al., 2024).

in implementing advanced analytics systems (Karimov et al., 2024; Misiejuk et al., 2025).

which embeds LA insights into course design and interventions; and Evaluation and Continuous Improvement,

which uses feedback loops to refine tools, data quality, and teaching practices.

Supporting these pillars is an operational workflow that ensures LA moves beyond static reporting into

actionable practice. This workflow follows a five-step sequence: Data Collection from multiple learning

By integrating foundational enablers with a clear process cycle, ILAAF moves LA adoption beyond static,

and academic success. The framework ensures that analytics use is both technically robust and pedagogically

The authors would like to express their sincere gratitude to University Technology MARA (UiTM) Cawangan

4. Ifenthaler, D., & Yau, J. Y. K. (2020). Utilising learning analytics to support study success in higher

education: A systematic review. British Journal of Educational Technology, 51(4), 1045–1068.