A Learning Analytics Approach to Address Heterogeneity in the Classroom: The Teachers’ Diagnostic Support System

Kärner, Tobias; Warwas, Julia; Schumann, Stephan

doi:10.1007/s10758-020-09448-4

Cited by 15 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It may be assumed that the algorithm is not only more accurate, but also provides more differentiated results than some teachers are able to do. Considering that teachers are supposed to be experts in many areas, it is not surprising that they can only meet these expectations to a limited extent as previous findings have shown, for example with regard to knowledge gaps in the area of basic language constructs (see Washburn et al, 2016;Aro & Björn, 2016;Corvacho del Toro, 2013) and limited accuracy in their diagnostic judgements (Kärner et al, 2021). Aro and Björn found that teachers' knowledge of morphology was significantly lower than it was for phonology and phonics.…”

Section: Table 11mentioning

confidence: 99%

“…Primary school teachers are challenged to identify the learning needs of students and to provide adaptive learning opportunities for all of them in terms of formative assessment (for the construct, see Black & Wiliam, 2009; for empirical evidence, see Hebbecker & Souvignier, 2018). This not only poses an issue of time, but also requires strong diagnostic skills (Black & Wiliam, 2009; for an overview, see Kärner, Warwas, & Schumann, 2021). International findings show that teachers often lack knowledge of basic language constructs for this purpose (for Canada, England, New Zealand and the USA, see Washburn, Binks-Cantrell, Joshi, Martin-Chang, & Arrow, 2016; for Finland, see Aro & Björn, 2016; for Germany, see Corvacho del Toro, 2013) and that the accuracy of their diagnostic judgments is limited (for an overview, see Kärner et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…This not only poses an issue of time, but also requires strong diagnostic skills (Black & Wiliam, 2009; for an overview, see Kärner, Warwas, & Schumann, 2021). International findings show that teachers often lack knowledge of basic language constructs for this purpose (for Canada, England, New Zealand and the USA, see Washburn, Binks-Cantrell, Joshi, Martin-Chang, & Arrow, 2016; for Finland, see Aro & Björn, 2016; for Germany, see Corvacho del Toro, 2013) and that the accuracy of their diagnostic judgments is limited (for an overview, see Kärner et al, 2021). As a successful start in literacy acquisition has a positive long-term effect on later performance, and early deficits are difficult to make up for later (see longitudinal study by Sparks, Patton, & Murdoch, 2014), it is important to develop procedures that enable a differentiated diagnosis of students' spelling abilities so that appropriate exercises can be provided on this basis (Lee, Chung, Zhang, Abedi, & Warschauer, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning for spelling acquisition - How accurate is the prediction of specific spelling errors in German primary school students?

Böhme¹,

Coors²,

Oster³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: In Germany, 30 % of students demonstrate insufficient spelling skills at the end of primary school – partly owing to the challenge for teachers to manage a variety of student learning needs. Digital tools using machine learning (ML) have already proven to be useful in enabling teachers to individualise students’ learning. However, there are still no suitable approaches for demographics not yet proficient in spelling. Objectives: With an aim to adapt ML for students of all proficiencies, we investigate how accurately spelling errors can be predicted across different literacy skill levels, which specific errors are predicted best (and worst), and the content-related reasons for these errors.Methods: We developed a web application for spelling that was used by N = 685 first and second graders in Bavaria, Germany. With the 18,133 different misspellings made, we trained six ML models and compared their performances.Results and conclusions: Comparing all ML models employed in this work, the random forest performed best on average as a predictor of spelling errors. Errors at the syllable and morpheme level were predicted best, and errors at the basic phoneme-grapheme level were predicted slightly less accurately. Confusions often concerned cases that are considered linguistically ambiguous or occurred in complex error entanglements.Implications: The results show that ML can be a useful tool to investigate specific spelling deficiencies in demographics not yet proficiently literate. ML could assist in individualising spelling acquisition, such as by automatically providing students individualised feedback or by providing teachers with diagnostic information about their students’ learning progress.

show abstract

Section: Table 11mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for spelling acquisition - How accurate is the prediction of specific spelling errors in German primary school students?

Böhme¹,

Coors²,

Oster³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To comprehend the aforementioned issue, limitations experienced by teachers should be contemplated when undertaking judgments through differentiated instruction. It is imperative that this knowledge is studied, since there are developing digital technologies such as machine learning (ML), educational data mining (EDM), and learning analytics (LA) [27,28] as potential teachers' support systems that can assist them in overcoming obstacles using data-driven decision systems. EDM and LA are the emergent educational fields most developed by computer scientists to explore the large volume of potential data within learning environments [28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Physics Teachers’ Perceptions about Their Judgments within Differentiated Learning Environments: A Case for the Implementation of Technology

2022

View full text Add to dashboard Cite

There is a national shift in the new Indonesian curriculum towards employing differentiated learning approaches in addressing the diversity of students’ needs and abilities. A teachers’ judgment evidently corresponds to the duty required of physics teachers to monitor their students at an individual level. Within the context of Indonesian physics education research (PER), empirical study addressing this subject is still lacking. To fill this gap, eight Indonesian physics teachers’ experiences and limitations about their judgments within differentiated learning environments have been investigated through phenomenological study. Physics teachers were voluntarily recruited after they declared their endorsement and personal consent to participate in the study. Our participants were distributed over several teaching experiences, geographic regions, and information and communication technology (ICT) experiences. The latter experience might be taken into account since, through this study, upcoming developmental research will be projected on engaging recent technological approaches to address the limitations of teachers’ judgments. Online semi-structured interviews (~50 min) were conducted by the first author to all physics teachers involved. Other authors contributed in reviewing the interview protocol and training the first author’s pilot interview. The model of teachers’ thought and action, from Clark and Peterson, was implemented to uncover physics teachers’ experiences and limitations in making judgments within a diverse group of students. The findings revealed that physics teachers have conceded that they should dynamically adapt the learning process in order to meet heterogeneous students’ performances. Personal observation has mainly informed teachers in identifying students’ differences. After students have been identified, the teachers creatively designed learning transformations to accommodate the wide spectrum of students’ abilities. Nevertheless, several limitations were discovered as being encountered by physics teachers, particularly in terms of judgments’ equity and accuracy, as well as the teachers’ workloads. To overcome this, the teachers indicated various and supportive attitudes about technological implementations that would assist their judgments. Ideas for technological development were provided to address identified obstacles during the teachers’ judgments.

show abstract

“…To comprehend our understanding about the aforementioned issue, we should contemplate limitations experienced by teachers when undertaking judgments to individual students. This knowledge is imperative to be studied since there are developing digital technologies such as machine learning, educational data mining, and learning analytics [27,28] as teachers' support systems that can assist them to overcome the obstacles.…”

Section: Introductionmentioning

confidence: 99%

Physics Teachers’ Perceptions about their Judgment within Differentiated Learning Environment: An Implication for Technology Implementation

Santoso¹,

Istiyono²,

Haryanto³

2022

Preprint

View full text Add to dashboard Cite

There is a national shift in the new Indonesian curriculum to employ differentiated learning approach in addressing diversity of students’ needs and abilities. Teachers’ judgment obviously corresponds to the duty that takes physics teachers to monitor their students at individual level. Within Indonesian physics education research (PER) context, empirical study that has addressed this subject is still lacking. To fill this gap, eight Indonesian physics teachers’ experiences and limitations about their judgment within differentiated learning environment has been investigated through phenomenological study. Physics teachers were voluntarily recruited after they have declared their endorsement and personal consent to participate in the study. Our participants were distributed over several teaching experiences, geographic regions, and ICT experiences. The latter experience might be taken into account since, through this study, we would project upcoming developmental research about engaging recent technological approaches to cope limitations of teachers’ judgment. Online semi-structured interviews (~ 50 min) were conducted by the first author (P.H.S.) to all physics teachers. Other authors contributed in reviewing the interview protocol (E.I. and H) and training the first author’s pilot interview (H.R.). Model of teachers’ thought and action was implemented to uncover physics teachers’ experiences and limitations in making judgment within diverse students. Findings revealed that physics teachers have conceded that they should adapt learning process in order to meet heterogeneous students’ needs. Personal observation has mainly informed teachers to identify students’ differences. After students have been identified, they creatively designed learning transformations to accommodate spectrum of students’ abilities. Nevertheless, we discovered several limitations encountered by teachers particularly in terms of judgments’ equity, accuracy, and their workload. To overcome this, teachers indicated various and supportive attitudes about technology implementation to assist their judgment. Implications for technological development was provided to address obstacles during the teachers’ judgment.

show abstract

A Learning Analytics Approach to Address Heterogeneity in the Classroom: The Teachers’ Diagnostic Support System

Cited by 15 publications

References 59 publications

Machine learning for spelling acquisition - How accurate is the prediction of specific spelling errors in German primary school students?

Machine learning for spelling acquisition - How accurate is the prediction of specific spelling errors in German primary school students?

Physics Teachers’ Perceptions about Their Judgments within Differentiated Learning Environments: A Case for the Implementation of Technology

Physics Teachers’ Perceptions about their Judgment within Differentiated Learning Environment: An Implication for Technology Implementation

Contact Info

Product

Resources

About