Automatic Inspection of E-Portfolios for Improving Formative and Summative Assessment

Müller, Wolfgang; Rebholz, Sandra; Libbrecht, Paul

doi:10.1007/978-3-319-52836-6_51

Cited by 8 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, the results indicate that the selected text mining techniques, topic modeling and sentiment analysis, lead to insights on the feedback, similar to the results in other research areas [18,19]. However, it is important to view these results as a support for interpretation of feedback rather than a tool for automatic assessment, as also concluded by Müller and Rebholz [20]. In this study we took an important first step towards the delivery of useful and meaningful support and insight in the underlying opinions in narrative feedback to help individual students interpret the longitudinal feedback collected in their e-portfolio, which is a rather unexplored area in education research [21].…”

Section: Sentiment Per Topic Evaluationsupporting

confidence: 82%

See 1 more Smart Citation

Toward Automatic Interpretation of Narrative Feedback in Competency-Based Portfolios

Loon

Govaerts

Donkers

et al. 2022

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

Self-directed learning is generally considered a key competence in higher education. To enable self-directed learning, assessment practices increasingly embrace assessment for learning rather than assessment of learning, shifting the focus from grades and scores to provision of rich, narrative and personalized feedback. Students are expected to collect, interpret and give meaning to this feedback, in order to self-assess their progress and to formulate new, appropriate learning goals and strategies. However, interpretation of aggregated, longitudinal narrative feedback has been proven to be very challenging, cognitively demanding and time consuming. In this study, we therefore explored the applicability of existing, proven text mining techniques to support feedback interpretation. More specifically, we investigated whether it is possible to automatically generate meaningful information about prevailing topics and the emotional load of feedback provided in medical students' competence-based portfolios (N = 1500), taking into account the competence framework and the students' various performance levels. Our findings indicate that the text mining techniques topic modeling and sentiment analysis make it feasible to automatically unveil the two principal aspects of narrative feedback, namely the most relevant topics in the feedback and their sentiment. This study therefore takes a valuable first step towards the automatic, online support of students, who are tasked with meaningful interpretation of complex narrative data in their portfolio as they develop into self-directed life-long learners.

show abstract

Section: Sentiment Per Topic Evaluationsupporting

confidence: 82%

“…However, use of text mining techniques for analysis of narrative data in assessment and e-portfolios in particular seems underexplored. Müller and Rebholz [20] describe an approach for automatic assessment of e-portfolios in Media Education and Management. It uses descriptive statistical tools (e.g.…”

Section: Introductionmentioning

confidence: 99%

Toward Automatic Interpretation of Narrative Feedback in Competency-Based Portfolios

Loon

Govaerts

Donkers

et al. 2022

IEEE Trans. Learning Technol.

View full text Add to dashboard Cite

show abstract

“…Several studies have used custom software and online applications such as employing LMS and MOOCs to collect online classroom activities (Goggins et al 2016;KU et al 2018;Libbrecht et al 2013;Müller et al 2016;Shen et al 2018;Suehiro et al 2017;Xu and Recker 2012). Others have used modern devices including eye-tracker, portable electroencephalogram (EEG), gyroscope, accelerometer and smartphones (Prieto et al 2016;Prieto et al 2018;Saar et al 2017;Saar et al 2018;, and conventional instruments such as video and voice recorders (Barmaki and Hughes 2015;Gauthier 2013;Thomas 2018), to record classroom activities.…”

Section: Data Sources and Toolsmentioning

confidence: 99%

Teaching analytics, value and tools for teacher data literacy: a systematic and tripartite approach

Ndukwe

Daniel

2020

Int J Educ Technol High Educ

View full text Add to dashboard Cite

Teaching Analytics (TA) is a new theoretical approach, which combines teaching expertise, visual analytics and design-based research to support teacher’s diagnostic pedagogical ability to use data and evidence to improve the quality of teaching. TA is now gaining prominence because it offers enormous opportunities to the teachers. It also identifies optimal ways in which teaching performance can be enhanced. Further, TA provides a platform for teachers to use data to reflect on teaching outcome. The outcome of TA can be used to engage teachers in a meaningful dialogue to improve the quality of teaching. Arguably, teachers need to develop their teacher data literacy and data inquiry skills to learn about teaching challenges. These skills are dependent on understanding the connection between TA, LA and Learning Design (LD). Additionally, they need to understand how choices in particular pedagogues and the LD can enhance their teaching experience. In other words, teachers need to equip themselves with the knowledge necessary to understand the complexity of teaching and the learning environment. Providing teachers access to analytics associated with their teaching practice and learning outcome can improve the quality of teaching practice. This research aims to explore current TA related discussions in the literature, to provide a generic conception of the meaning and value of TA. The review was intended to inform the establishment of a framework describing the various aspects of TA and to develop a model that can enable us to gain more insights into how TA can help teachers improve teaching practices and learning outcome. The Tripartite model was adopted to carry out a comprehensive, systematic and critical analysis of the literature of TA. To understand the current state-of-the-art relating to TA, and the implications to the future, we reviewed published articles from the year 2012 to 2019. The results of this review have led to the development of a conceptual framework for TA and established the boundaries between TA and LA. From the analysis the literature, we proposed a Teaching Outcome Model (TOM) as a theoretical lens to guide teachers and researchers to engage with data relating to teaching activities, to improve the quality of teaching.

show abstract

“…A more recent study [16] aimed at devising an LMS-based system to provide an automated assessment of e-portfolios, upon raw statistical features like word count or number of images. A first comparison of human vs. machine grades of 12 e-portfolios yielded promising results (r = .67).…”

Section: Automated Assessment Approaches In Health Carementioning

confidence: 99%

How Well Do Student Nurses Write Case Studies? A Cohesion-Centered Textual Complexity Analysis

Dascălu

Dessus

Thuez

et al. 2017

Data Driven Approaches in Digital Education

View full text Add to dashboard Cite

Abstract.Starting from the presumption that writing style is proven to be a reliable predictor of comprehension, this paper investigates the extent to which textual complexity features of nurse students' essays are related to the scores they were given. Thus, forty essays about case studies on infectious diseases written in French language were analyzed using ReaderBench, a multi-purpose framework relying on advanced Natural Language Processing techniques which provides a wide range of textual complexity indices. While the linear regression model was significant, a Discriminant Function Analysis was capable of classifying students with an 82.5% accuracy into high and low performing groups. Overall, our statistical analysis highlights essay features centered on document cohesion flow and dialogism that are predictive of teachers' scoring processes. As text complexity strongly influences learners' reading and understanding, our approach can be easily extended in future developments to e-portfolios assessment, in order to provide customized feedback to students.

show abstract

Automatic Inspection of E-Portfolios for Improving Formative and Summative Assessment

Cited by 8 publications

References 4 publications

Toward Automatic Interpretation of Narrative Feedback in Competency-Based Portfolios

Toward Automatic Interpretation of Narrative Feedback in Competency-Based Portfolios

Teaching analytics, value and tools for teacher data literacy: a systematic and tripartite approach

How Well Do Student Nurses Write Case Studies? A Cohesion-Centered Textual Complexity Analysis

Contact Info

Product

Resources

About