Reaching Higher
Featured A Theory-driven Learning Analytic Model for Detecting Students-at-risk in Higher Education
Paper Presentation in a Themed Session
Sonwabo Jongile,
Eunice Ivala
Business intelligence (BI) and analytic solutions originated from learning analytics (LA), which has emerged in the education sector due to the success of data mining models in businesses. However, the application of BI models in analytics for at-risk students (those failing academically or facing challenges that may hinder their completion of studies) is currently unclear in the global higher education context. LA is being tested and implemented in some higher education institutions (HEI) worldwide to enhance learning and teaching through monitoring students’ interactions and success in fully online and blended courses. Furthermore, most studies on LA are data-driven and lack theoretical foundations. This study, from which the findings in this article are derived, is based on Tinto’s longitudinal model of dropout. This model is used to select dropout conditions and extract data from institutional information systems and student learning data, with the goal of improving the identification of at-risk students and providing real-time interventions. Through an inductive analysis of literature, this article explores how theoretical frameworks can be applied in analytics for at-risk students, with a focus on predictive modeling. As a result, a modified theoretical model based on Tinto’s longitudinal model of dropout is presented. This modified model aims to demonstrate the potential of information systems and student learning data in indigenous HEI, providing a learning analytic approach that universities can use to identify students at risk of dropping out.
Attention and Electroencephalogram Signal Analysis: Attention Processes in L2 English Interactions
Paper Presentation in a Themed Session
Rosa Munoz-Luna
This study explores the relationship between electroencephalogram (EEG)-detected attention spikes and linguistic stimuli, particularly in English as a Second Language (L2) for native Spanish speakers. We investigate how linguistic input affects brain activity and how this is interpreted as specific emotions (pleasant or unpleasant). To examine this, we analyzed EEG responses from subjects watching short English videos with varying emotional content and lexical complexity. The videos were selected based on their emotional intensity (ranging from neutral to highly emotional) and lexical features (high- vs. low-frequency words). They were categorized into short clips (a few seconds) and longer segments (one to two minutes) to assess consistency in emotional and cognitive responses. Our approach minimizes the influence of non-linguistic audiovisual elements, ensuring a focus on language. Using a specialized EEG preprocessing application, we extracted key features from the brain signals of 10 young adult university students (aged 20-30, without neurodivergence) who also completed questionnaires about their emotional and attentional experiences. The findings reveal a direct correlation between attention levels and sudden shifts in discourse dynamics, particularly with discursive markers linked to emotional arousal and speech pauses. Additionally, EEG signals varied with the difficulty of discourse comprehension, particularly with low-frequency words and complex content. These results, framed within arousal theory, highlight the impact of language on emotional response, contributing to our understanding of the interaction between linguistic input and emotional processing.
The Communication Paradox: Knowledge Integration and the Negotiation of Meaning
Paper Presentation in a Themed Session
Mary Griffith
Make no mistake AI is learning. Many authors have documented that ‘people’ are already learning in different ways, but seem to underestimate the ability of generative AI to solve problems in unexpected ways. The research project is framed by an interdepartmental collaboration is led by English studies and Telecommunications and deals with speech analysis and machine learning. This project explored the effects of online platforms and attention. The present study focuses on beta brain waves using bioelectrical measurements (electroencephalogram, EEG), as these signals can correlate to attention in subjects when listening to a second language. The objective was to see if online discourse can cause the same attention response as live face-to-face speech and then use the results for machine learning. The student engineers worked closely with undergraduate and postgraduate students in English studies who oversaw the mapping of the texts and identifying stimuli for the research design. The students effectively created an interface between natural language stimuli and machine coding, so that the data could be interpreted statistically and verified as viable for machine learning and text interpretation. This reinforced the connection between natural language and technology with the emerging research. This student led project has allowed us visualize key correlations between EEG data and linguistic features as related to emotion and attention. How to define what happens in the brain as related to attention and emotion has far-reaching influence on teaching, on communication, as well as in training artificial intelligence using human data.
