Speaking in a foreign language is considered challenging to both teach and learn. Virtual humans (VHs), as conversational agents (CAs), provide opportunities to practise speaking skills. Lower secondary school students (N = 25) engaged in an AI-based spoken dialogue system (SDS) and interacted verbally with VHs in simulated everyday-life scenarios…

The purpose of the present study was to investigate if following data-driven learning (DDL) to raise the learners' awareness of discourse organizers through concordancing improves their comprehension of English academic lectures. To address this issue, the current study adopted a quasi-experimental (comparison group, pretest-posttest) design. 96…

Social Learning Analytics (SLA) seeks to obtain hidden information in large amounts of data, usually of an educational nature. SLA focuses mainly on the analysis of social networks (Social Network Analysis, SNA) and the Web, to discover patterns of interaction and behavior of educational social actors. This paper incorporates the SLA in a smart…

Current writing support tools tend to focus on assessing final or intermediate products, rather than the writing process. However, sensing technologies, such as keystroke logging, can enable provision of automated feedback during, and on aspects of, the writing process. Despite this potential, little is known about the critical indicators that can…

Recommender systems in educational contexts have proven to be effective in identifying 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 this article, we present the design of a hybrid…

Aim/Purpose: This paper focuses on designing and implementing the rubric for objective JAVA programming assessments. An unsupervised learning approach was used to group learners based on their performance in the results obtained from the rubric, reflecting their learning ability. Background: Students' learning outcomes have been evaluated…

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…

Knowing insights as to why learners from diverse social and demographic profile choose to enroll in distance education can be a useful tool for Open and Distance Learning (ODL) Institutions to understand the requirements of their target segment, help in fine-tuning service offerings for attracting potential students and finally retaining them…

Contemporary students have a varied set of needs--the "lifecycle" of a typical student may no longer be 4 years of continuous enrollment between the ages of 18 and 22, and many students bring rich and varied experiences with them to college. As institutions strive to allocate resources in ways that provide the most benefit to student…

Learning analytics research has used both knowledge engineering and machine learning methods to model student behaviors within the context of digital learning environments. In this paper, we compare these two approaches, as well as a hybrid approach combining the two types of methods. We illustrate the strengths of each approach in the context of…

The growing practice of students as partners (SaP) has sparked numerous conversations in higher education about the roles students do and should play in shaping the future. SaP scholars contend that by engaging with students in meaningful partnership, underpinned by values such reciprocity, students can have deeper and more meaningful learning…

Interdisciplinary research from the learning sciences has helped us understand a great deal about the way that humans learn, and as a result we now have an improved understanding about how best to teach and train people. This same body of research must now be used to better inform the development of Artificial Intelligence (AI) technologies for…

Using data to understand learning and improve education has great promise. However, the promise will not be achieved simply by AI and Machine Learning researchers developing innovative models that more accurately predict labeled data. As AI advances, modeling techniques and the models they produce are getting increasingly complex, often involving…

Writing is a challenge and a potential obstacle for students in U.S. 4-year postsecondary institutions lacking prerequisite writing skills. This study aims to address the research question: Is there a relationship between specific features (analytics) in coursework writing and broader success predictors? Knowledge about this relationship could…

Success prediction in Massive Open Online Courses (MOOCs) is now tackled in numerous works, but still needs new case studies to compare the solutions proposed. We study here a specific dataset from a French MOOC provided by the OpenClassrooms company, featuring 12 courses. We exploit various features present in the literature and test several…