Emotions are vital to learning success, especially in online learning environments. They make the difference between learning success and failure. Unfortunately, learners' emotional state is still rarely considered in online learning and teaching, although it is an important driver of learning success. This paper reports a work-in-progress…

In the wake of the COVID-19 pandemic, educators and policymakers have scrambled to assess the impact on student learning. Popular metrics that have gained traction are the notions of "years of learning lost" or "months behind," which attempt to quantify the educational setbacks caused by the pandemic. The allure of these…

Learning Analytics (LA) captures the digital footprint of students' online learning activity. This study describes students' navigational behavior in an e-learning setting by processing the LA data obtained from Blackboard LMS. This is an attempt to understand the navigational behavior of students and the relationship with learning performance.…

Within digitally-supported learning environments, learners need to observe themselves so that they can reflect on their strengths and weaknesses and take a step toward autonomous learning. Within the scope of this research, a technology and analytics enhanced assessment environment in which students can assess themselves was implemented and…

In this paper, we propose a novel approach to combine domain modelling and student modelling techniques in a single, automated pipeline which does not require expert knowledge and can be used to predict future student performance. Domain modelling techniques map questions to concepts and student modelling techniques generate a mastery score for a…

Academic advising plays an important role in students' decision-making in higher education. Data-driven methods provide useful recommendations to students to help them with degree completion. Several course recommendation models have been proposed in the literature to recommend courses for the next semester. One aspect of the data that has yet to…

A significant amount of research has gone into predicting student performance and many studies have been conducted to predict why students drop out. A variety of data including digital footprints, socio-economic data, financial data, and psychological aspects have been used to predict student performance at the test, course, or program level.…

Classifying educational forum posts is a longstanding task in the research of Learning Analytics and Educational Data Mining. Though this task has been tackled by applying both traditional Machine Learning (ML) approaches (e.g., Logistics Regression and Random Forest) and up-to-date Deep Learning (DL) approaches, there lacks a systematic…

During the COVID-19 pandemic, an adult noncredit program in the California Community College system partnered with Ease Learning to help convert face-to-face courses to an online modality. Subsequent data revealed a misalignment in the courses' Student Learning Outcomes and Instructional Objectives which became a barrier to student success. Wile's…

Student grade prediction is a popular task for learning analytics, given grades are the traditional form of student performance. However, no matter the learning environment, student background, or domain content, there are things in common across most experiences in learning. In most previous machine learning models, previous grades are considered…

Early predictors of student success are becoming a key tool in flipped and online courses to ensure that no student is left behind along course activities. However, with an increased interest in this area, it has become hard to keep track of what the state of the art in early success prediction is. Moreover, prior work on early success prediction…

This paper studies the use of Reinforcement Learning (RL) policies for optimizing the sequencing of online learning materials to students. Our approach provides an end to end pipeline for automatically deriving and evaluating robust representations of students' interactions and policies for content sequencing in online educational settings. We…

The search for rigor in learning analytics applications has placed survey data in the suspect's corner, favoring more objective trace data. A potential lack of objectivity in survey data is the existence of response styles, the tendency of respondents to answer survey items in a particular biased manner, such as yeah saying or always disagreeing.…

Academic grades in assessments are predicted to determine if a student is at risk of failing a course. Sequential models or graph neural networks that have been employed for grade prediction do not consider relationships between course descriptions. We propose the use of text mining to extract semantic, syntactic, and frequency-based features from…

Metacognition is a valuable tool for learning, since it is closely related to self-regulation and awareness of one's own affect. However, methods for automatically detecting and studying metacognition are scarce. Thus, in this paper we describe an algorithm for automatic detection of metacognitive language in writing. We analyzed text from the…