A bibliometric analysis of the trends, topics, and findings of research publications on asynchronous and synchronous online language learning over three decades

Since the first study on computer-mediated communication tools in support of language learning was published in 1992, asynchronous and synchronous tools have been widely adopted;however, few reviews have been conducted to explore the research status in this field. As COVID-19 has increased the use of online tools in education, the need to understand how asynchronous and synchronous tools are being used in language education has grown. In this bibliometric analysis, we reviewed asynchronous and synchronous online language learning (ASOLL) by analyzing the trends, topics, and findings of 319 articles on ASOLL. The results indicate that interest in ASOLL has increased over the past three decades with ASOLL for oral proficiency development and collaborative ASOLL being the two main research issues. Interest in three topics collaborative ASOLL, emotions, and corrective feedback - was especially apparent. The review contributes to the understanding of ASOLL while providing practical implications for using information communication technologies to enhance language learning.

Data Analytics on Online Student Engagement Data for Academic Performance Modeling

In large MOOC cohorts, the sheer variance and volume of discussion forum posts can make it difficult for instructors to distinguish nuanced emotion in students, such as engagement levels or stress, purely from textual data. Sentiment analysis has been used to build student behavioral models to understand emotion, however, more recent research suggests that separating sentiment and stress into different measures could improve approaches. Detecting stress in a MOOC corpus is challenging as students may use language that does not conform to standard definitions, but new techniques like TensiStrength provide more nuanced measures of stress by considering it as a spectrum. In this work, we introduce an ensemble method that extracts feature categories of engagement, semantics and sentiment from an AdelaideX student dataset. Stacked and voting methods are used to compare performance measures on how accurately these features can predict student grades. The stacked method performed best across all measures, with our Random Forest baseline further demonstrating that negative sentiment and stress had little impact on academic results. As a secondary analysis, we explored whether stress among student posts increased in 2020 compared to 2019 due to COVID-19, but found no significant change. Importantly, our model indicates that there may be a relationship between features, which warrants future research.