Recommender systems in educational contexts have proven effective to identify learning resources that fit the interests and needs of learners. Their usage has been of special interest in online self-learning scenarios to increase student retention and improve the learning experience. In current recommendation techniques, and in particular, in…

This research connects several data-driven educational data mining approaches to a framework for interaction developed in educational research. In particular, 10 million usage data points collected by a Learning Management System used by students and teachers in 450 online undergraduate courses were analyzed with this framework. A range of…

The present paper contains a research into the issue of employment and legal safeguarding of social protection of young individuals suffering from cognitive disorders in Ukraine. The importance of legislative guarantees of equal rights and possibilities for such category of individuals, in comparison with all other members of the society, in…

This Innovative Practice Category Work In Progress paper presents an application of machine learning and data mining to student performance data in an undergraduate electrical engineering program. We are developing an analytical approach to enhance retention in the program especially among underrepresented groups. Our approach will provide…

An important research problem for Educational Data Mining is to expedite the cycle of data leading to the analysis of student learning processes and the improvement of support for those processes. For this goal in the context of social interaction in learning, we propose a three-part pipeline that includes data infrastructure, learning process…

Completion rates for massive open online classes (MOOCs) are notoriously low, but learner intent is an important factor. By studying students who drop out despite their intent to complete the MOOC, it may be possible to develop interventions to improve retention and learning outcomes. Previous research into predicting MOOC completion has focused…

Many Open and Distance Learning (ODL) providers report that their students are prone to lower rates of retention and completion than campus-based students. Against this background, there is growing interest around distance-specific learning support. The current research investigated the experiences of students during their first semester as…

An underlying theme of this paper is that it can be easier and more efficient to conduct valid and effective research studies in online environments than in traditional classrooms. Taking advantage of the "big data" available in an online university, we conducted a study in which a massive online database was used to predict student…

This paper reports on early findings from a pilot study into student retention beyond Year 10. Located in rural, regional and disadvantaged communities in Tasmania, the research has implications at State, national and international levels. It is being funded by a nationally competitive Australian Research Council Linkage grant and the Tasmanian…

By probing the micro-level interactions and experiences shaping students' thoughts, behaviors, and decisions during college the authors hope to generate a better picture of how individuals enact the intersection of their own agency with their given social context. Such insights may enable a more accurate and meaningful interpretation of the…

This paper reports on research that examined longitudinal data on students entering Tennessee Board of Regents institutions of higher education after the implementation of a state-mandated developmental studies program. The program identifies and helps at-risk students to persist in college to graduation. Data analysis is presented from a 1986…

This study developed a statistical model to identify college students most prone to dropping out, testing the model to predict the retention status of black residential and white commuter students at an historically black institution with an open admissions policy. The model used 25 pre- and early-matriculation variables, including gender, age,…

This paper presents findings on predictive models used to identify student characteristics associated with persistence and success in the Administration of Justice (ADJ) program at Blue Ridge Community College (Virginia). Data mining was used to discover patterns and relationships in the data, and analysis was performed using the SPSS program,…

Most of the literature on student retention focuses on what students do "wrong" that leads to departure from college, but there is much to be learned from studying student success in higher education. This article presents a study designed to uncover the strategies that successful minority students employ to overcome barriers to academic…

This paper on postsecondary outcomes illustrates a technique to determine whether or not mainstream models are appropriate for predicting educational outcomes of American Indians (AIs) and Alaskan Native (ANs). It introduces a prominent statistical procedure to assess models with empirical data and shows how the results can have implications for…