Understanding the Learners’ Actions when Using Mathematics Learning Tools

Abstract

The use of computer-based mathematics tools is widespread in learning. Depending on the way that these tools assess the learner's solution paths, one can distinguish between automatic assessment tools and semi-automatic assessment tools. Automatic assessment tools directly provide all feedback necessary to the learners, while semi-automatic assessment tools involve the teachers as part the assessment process. They are provided with as much information as possible on the learners' interactions with the tool. How can the teachers know how the learning tools were used and which intermediate steps led to a solution? How can the teachers respond to a learner's question that arises while using a computer tool? Little is available to answer this beyond interacting directly with the computer and performing a few manipulations to understand the tools' state. This paper presents SMALA, a web-based logging architecture that addresses these problems by recording, analyzing and representing user actions. While respecting the learner's privacy, the SMALA architecture supports the teachers by offering fine-grained representations of the learners' activities as well as overviews of the progress of a classroom.

Student's Patterns of Interaction with a Mathematics Intelligent Tutor: Learning Analytics Application

“…Learning management systems (LMS), intelligent tutors and other e-Learning systems generate vast amount of user generated data. Learning analytics can be applied to provide learner feedback and support, and detect early warning systems [20,22]. The objective of learning analytics is to derive information which can reveal how students use the intelligent tutoring or other e-learning systems and identify potential determinants of academic achievement.…”

“…A key feature of these software systems is their ability to record and store details of each learning activity that happens when a student interacts with the system. Such digital data can be analyzed and interpreted which can reveal some useful information regarding students' study habits and their progress [22]. Learning analytics is a research discipline which provides framework for analysis of these system-generated large data logs in order to understand learning activities [17,39,41].…”

“…and interpreted which can reveal some useful information regarding students' study habits and their progress [22]. Learning analytics is a research discipline which provides framework for analysis of these system-generated large data logs in order to understand learning activities [17,39,41].…”

Exploring the benefits and challenges of learning analytics in higher education institutions: a systematic literature review

“…Data analytics have revolutionized different domains including higher education in which e-learning and web-based technologies have generated massive data (Greller and Drachsler, 2012). Learning analytics, an application of data analytics in higher education institutions, has transformed several aspects in higher education including the ability to detect at risk students (Kotsiantis et al, 2013;Kulik et al, 1990), track students' progress (Libbrecht et al, 2012), predicting individual learning needs of each student (Krumm et al, 2014;Arnold and Pistilli, 2012) and revealing potential determinants of students' academic achievement (Greller and Drachsler, 2012) among other merits. However, the potential capabilities and benefits that data analytics can provide are not generically adaptable to all higher education institutions and they are not fully utilized which indicates several areas of improvement towards usage of learning analytics in higher education.…”