Discourse Centric Learning Analytics: Mapping the Terrain

Knight, Simon; Littleton, Karen

doi:10.18608/jla.2015.21.9

Cited by 27 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Students can then be advised to re-assess their participation, or simply to reflect on their position in the network. The text exchanged by students in discussion forums is also a valuable data source for more recent techniques known as discourse-centric analytics that seek to detect evidence of learning, and language usage patterns that are associated with positive academic outcomes (Ferguson and Buckingham Shum 2011;De Liddo et al 2011;Knight and Littleton 2015). The characterization of these discussions offers the possibility to provide highly detailed and potentially effective feedback for students to increase their performance.…”

Section: The State Of Data-driven Student Supportmentioning

confidence: 99%

Data-Driven Personalization of Student Learning Support in Higher Education

Liu

Bartimote-Aufflick

Pardo

et al. 2017

Learning Analytics: Fundaments, Applications, and Trends

View full text Add to dashboard Cite

Abstract. Despite the explosion of interest in big data in higher education and the ensuing rush for catch-all predictive algorithms, there has been relatively little focus on the pedagogical and pastoral contexts of learning. The provision of personalized feedback and support to students is often generalized and decontextualized, and examples of systems that enable contextualized support are notably absent from the learning analytics landscape. In this chapter we discuss the design and deployment of the Student Relationship Engagement System (SRES), a learning analytics system that is grounded primarily within the unique contexts of individual courses. The SRES, currently in use by teachers from 19 departments, takes a holistic and more human-centric view of data -one that puts the relationship between teacher and student at the center. Our approach means that teachers' pedagogical expertise in recognizing meaningful data, identifying subgroups of students for a range of support actions, and designing and deploying these actions, is facilitated by a customizable technology platform. We describe a case study of the application of this human-centric approach to learning analytics, including its impacts on improving student engagement and outcomes, and debate the cultural, pedagogical, and technical aspects of learning analytics implementation.Keywords: actionable intelligence, implementation, intelligence amplification, learning analytics, personalization, student engagement. Abbreviations EDMEducational data mining EWS Early warning system LA Learning analytics LMS Learning management system SRES Student Relationship Engagement System 2 Introduction The state of data-driven student supportThe rise in use of technology mediation in learning scenarios is providing unprecedented amounts of data about how educational institutions work and how students participate in learning experiences. At the same time, learning scenarios are becoming increasingly diverse and complex. The areas of educational data mining (EDM) and learning analytics (LA) have emerged to address the issue of how to use data to improve our understanding of learning, and enhance the overall quality of the learning experience for the student. Although EDM and LA researchers and practitioners maintain a similar focus (Baker and Siemens 2014), they differ in their approach to data generated in educational settings. Researchers in EDM frequently focus their analyses on the formulation or improvement of data mining algorithms designed to detect and predict important factors in a learning scenario. LA, on the other hand, focuses on how these algorithms can be deployed and integrated in learning designs, used by teachers, and provide tangible improvements for students. However, in their initial stages, both disciplines placed their emphasis mostly on how data can be collected and used by algorithms and not so much on how these data can then lead to actions that have a positive effect on students.Prior to the availability of massive amounts of data, the area...

show abstract

Section: The State Of Data-driven Student Supportmentioning

confidence: 99%

Data-Driven Personalization of Student Learning Support in Higher Education

Liu

Bartimote-Aufflick

Pardo

et al. 2017

Learning Analytics: Fundaments, Applications, and Trends

View full text Add to dashboard Cite

show abstract

“…Relying on students' self-tagging of critical lenses and critical talk types leads to large variations in accuracy and may be of limited validity. For a start, we see potential to incorporate semi-automated tagging using existing dictionaries to identify students' EL learning and critical thinking skills at the individual level (Knight & Littleton, 2015). More time and scaffolding are needed to help students gain greater benefits from the interpretation of learning behaviour based on LA dashboard data.…”

Section: Resultsmentioning

confidence: 99%

Learner Dashboards a Double-Edged Sword? Students’ Sense-Making of a Collaborative Critical Reading and Learning Analytics Environment for Fostering 21st Century Literacies

et al. 2017

View full text Add to dashboard Cite

strategies and outcomes. However, use cases and empirical understandings of student experience, especially in the K-12 schooling sector and in Asian education contexts, remain relatively scarce in the field. Our paper addresses this knowledge gap in two ways. First, we present a first iteration design of a computer-supported collaborative critical reading and LA environment, WiREAD, and its 16-week implementation in a Singapore high school. Second, we foreground students' evaluative accounts of the benefits and drawbacks associated with WiREAD's LA dashboard, which pointed to a number of potentialities and perils. Positives included 1) fostering greater self-awareness, reflective, and self-regulatory learning dispositions, 2) enhancing learning motivation and engagement, and 3) nurturing connective literacy among students. The motivational value of peer-referenced LA dashboard visualizations for stimulating healthy competition and game-like learning was identified alongside the perils of these serving to demoralize, pressurize, and trigger complacency in learners. This paper aims to shed light on the pedagogical complexities of designing LA that considers learners as a critical stakeholder group.

show abstract

“…In fact, with multiple sources of data and features to choose from, researchers are focusing on specific types of context, data, and instruments to determine various impacts towards teaching and learning. When dealing with discourse data, learning analytics are often used, such as statistical discourse analysis (SDA; Chiu & Fujita, 2014b) and discourse-centric learning analytics (DCLA; Knight & Littleton, 2015). Researchers have also used semantics in identifying topic specificity in online discussion forums, through probabilistic topic modelling with semantic visual analytics (Sun, Zhang, Jin, & Lyu, 2014;Hsiao & Awasthi, 2015).…”

Section: Introductionmentioning

confidence: 99%

Promising Ideas for Collective Advancement of Communal Knowledge Using Temporal Analytics and Cluster Analysis

Lee

Tan

2017

Learning Analytics

View full text Add to dashboard Cite

Understanding ideas in a discourse is challenging, especially in textual discourse analysis. We propose using temporal analytics with unsupervised machine learning techniques to investigate promising ideas for the collective advancement of communal knowledge in an online knowledge building discourse. A discourse unit network was constructed and temporal analysis was carried out to identify promising ideas, which are improvable perceptions of significant relevance that aid in the understanding of discourse context and content. With the aid of a degree centrality-betweenness centrality (DC-BC) graph, more promising ideas were discovered. An additional analysis using multiple DC-BC graph snapshots at different discourse junctures illustrates the transition of these promising ideas over time. Machine learning in the form of kmeans clustering further categorized promising ideas. Cluster centroids were calculated and represented the foci of discussions, while the movement of discourse units about cluster centroids reflected how ideas affected learning behaviours among the participants. Discourse units containing promising ideas were qualitatively verified. Overall, the results showed that the implementation of temporal analytics and clustering provided insights and feedback to users about idea-related processes in the discourse. The findings have implications for teachers, students, and researchers.Keywords: Temporal analytics, machine learning, cluster analysis, promising ideas, idea analysis, knowledge building discourse NOTES FOR PRACTICE• Analysis of ideas and related processes is critical for collective knowledge advancement in knowledge building discourse but is challenging due to large and complex discourse data.• This paper contributes to the field of learning analytics by proposing a method that combines temporal analytics and unsupervised machine learning to analyze promising ideas and investigate idea mobility in discourse.• Findings show that temporal analysis bridges the gap between individual analyses of discrete events to provide a broader picture of online discourse that is complementary to machine learning techniques and provides insights into idea-centric discourse.

show abstract

Discourse Centric Learning Analytics: Mapping the Terrain

Cited by 27 publications

References 59 publications

Data-Driven Personalization of Student Learning Support in Higher Education

Data-Driven Personalization of Student Learning Support in Higher Education

Learner Dashboards a Double-Edged Sword? Students’ Sense-Making of a Collaborative Critical Reading and Learning Analytics Environment for Fostering 21st Century Literacies

Promising Ideas for Collective Advancement of Communal Knowledge Using Temporal Analytics and Cluster Analysis

Contact Info

Product

Resources

About