Aligning Learners' Expectations and Performance by Learning Analytics Systemwith a Predictive Model

Learning analytics (LA) is data collection, analysis, and representation of data about learners in order to improve their learning and performance. Furthermore, LA opens the door to opportunities for self-regulated learning in higher education, a circular process in which learners activate and sustain behaviors that are systematically oriented toward their personal learning goals. The potentials of LA and self-regulated learning are huge; however, they are not yet widely applied in higher education institutions. Slovenian higher education institutions have lagged behind other European countries in LA adoption. Our research aims to fill this gap by using a qualitatively and quantitatively led workflow for building requirement-oriented LA solution, consisting of empirically gathering the students’ expectations of LA and presenting a dashboard solution. Translated Student Expectations of Learning Analytics Questionnaire (SELAQ) and focus groups were used to gather expectations from learners. Based on this data, a user interface utilizing learning analytics and grade prediction with an artificial intelligence model was implemented for a selected course. The interface includes early grade prediction, peer comparison, and historical data overview. Early grade prediction is based on a machine learning model built on users’ interaction in the virtual learning environment, demographic data and their lab grades. First, classification is used to determine students at risk of failing - its precision is reaching 98% after the first month of the course. Second, the exact grade is predicted with the Decision Tree Regressor, which reaches a mean absolute error of 11.2grade points (on a 100 points scale) after the first month. The proposed system is designed for students - its main benefit is the support for self-regulation of the learning process during the semester, possibly motivating students to adjust their learning strategies to prevent failing the course. Initial student evaluation of the system showed positive results. The main stakeholders in learning analytics (LA) solutions are teachers and learners; this work is focused on expectations and solutions for the latter. This study builds on previous research about students’ expectations and attitudes in Europe [ ? ][23][15] and contributes to the recognized importance of including students as key stakeholders in the design and implementation of LA [19]. We focus on the context of Slovenian higher engineering education, which has not been explored in this context before. We contribute to the current body of research with a LA solution based on student requirements, gathered with quantitative and qualitative methods. Such an approach has seldom been combined in existing work; studies mostly gather stakeholders’ expectations [18][5][23] or provide finalized LA solutions; [2], furthermore, a systematic review of work on LA dashboards calls for more empirical user-centered LA system development [13]. This study was guided by two questions: i) What are key learners’ expectations from learning analytics? and ii) How can we implement these expectations in learning analytics-based solution with a focus on self-regulated learning? An emphasis on a user-centered approach to LA