Association Rule Mining from an Intelligent Tutor

Doğan, Buket; Camurcu, Ali Yilmaz

doi:10.2190/et.36.4.f

Cited by 10 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The factor of Learning Data is retrieved in the SCI. Some researchers indicated that smart classroom can give adaptive learning support to the student by detecting, recording, and analyzing the students' entire learning statuses (Dogan and Camurcu 2007;Zhang et al 2009;Latham et al 2012). Students' learning data is the basis for constructing learning model and giving the individualized learning diagnosis.…”

Section: Discussionmentioning

confidence: 99%

Development and validation of the smart classroom inventory

Kong

Guang

2015

Smart Learn. Environ.

View full text Add to dashboard Cite

This paper discusses the development and validation of the Smart Classroom Inventory (SCI). The SCI is derived from existing technology integration learning environment instruments, including TROFLEI, TICI and CCEI (ergonomic). To accurately describe the features of smart classroom, the factors of flexibility, learning data, learning experience are added to SCI, and the description of information technology usage of some items are also altered to fit the smart classroom environment. More than 640 11 to 15 years old students validated the instrument, revealing ten scales: Physical Design, Flexibility, Technology Usage, Learning Data, Differentiation, Investigation, Cooperation, Students Cohesiveness, Equity, and Learning Experience. Cronbach's alpha coefficient is 0.92 and 0.94 for the entire questionnaire in Actual and Preferred forms respectively. The results of EFA and CFA prove SCI to be a parsimonious instrument for assessing the smart classroom learning environment. In assessing Actual and Preferred learning environments, SCI results indicated that there are significant differences in all of the ten factors. Students' perception of factors of Differentiation, Flexibility, Technology Usage, and Learning Data are the largest four actual-preferred discrepancies within the smart classroom learning environment. These suggest the importance of innovative application of the current information equipment, and schools should pay more attention to satisfying the students' personalized learning demands. The differences between the gender and between the school settings indicate that smart classroom should integrate both the technology and the humanities factors into the design and application of smart classroom, as well as design multi-level learning activities to satisfy the choices of different age students.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and validation of the smart classroom inventory

Kong

Guang

2015

Smart Learn. Environ.

View full text Add to dashboard Cite

show abstract

“…It also refers to knowledge discovery process within huge datasets, which makes it different from more traditional statistical approaches since it does not rely on predefined hypotheses. Data mining methods do not assume a particular model, rather they automatically extract hidden patterns in data (Dogan & Camurcu, 2008). Moreover, recent years have witnessed the growing body of research regarding application of data mining in educational settings (Aldowah et al, 2019;Kıray et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Exploring Relations Among Pre-Service Science Teachers’ Motivational Beliefs, Learning Strategies and Constructivist Learning Environment Perceptions Through Unsupervised Data Mining

Kıngır

Gök

Bozkır

2020

JBSE

View full text Add to dashboard Cite

Educational data mining is a developing research trend for exploring hidden patterns and natural associations among a set of student, teacher or school related variables. Discovering profiles of preservice science teachers using data mining methods would give important information about quality of teacher education programs and future science teachers’ performance. The aim of this research was to describe characteristics of preservice science teachers and to explore the relations among their motivational beliefs, learning strategy use, and constructivist learning environment perceptions. Participants included 480 preservice science teachers in their final semester of the teacher education program. Data were gathered using Demographic Questionnaire, Motivated Strategies for Learning Questionnaire, Achievement Goal Questionnaire and Constructivist Learning Environment Scale. Findings of clustering analysis revealed gender as a discriminating factor between the obtained two natural groups. Preservice science teachers’ characteristics including background characteristics, motivational beliefs, strategy use and constructivist learning environment perceptions were grouped into two clusters, namely males and females. Moreover, the association rules mining analysis revealed strong relations among preservice science teachers’ motivational beliefs, learning strategy use, and constructivist learning environment perceptions. This research provided many important findings that can be useful for further decision-making strategies. Keywords: constructivist learning environment, data mining, learning strategies, motivational belief, pre-service science teacher

show abstract

“…Some of these applications include students' classification based on their learning performance; detection of irregular learning behaviours; e-learning system navigation and interaction optimization; clustering according to e-learning system usage; systems' adaptability to students' requirements and capacities [5] - [9]. In studies [10], [11] data mining techniques have been used to discover the common factors affecting the learners' performance and students' behaviour patterns.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Students’ Grades in Mathematics, English, and Programming Courses: A KDD Approach

Anwar¹,

Ahmed²,

Khan³

2012

IJFCC

View full text Add to dashboard Cite

Abstract-There are several statistical tools being used for information extraction and knowledge discovery from the students' performance analysis. This paper presents data mining approach applied to discover students' performance patterns in mathematics, English, and programming courses taught in an undergraduate engineering degree program. The interesting patterns emerging from this analysis promise to offer some helpful and constructive guidance to educational administrators and decision makers in higher education sector for the improvement and revision of teaching methodology, restructuring of curriculum, and modifying the prerequisites requirements of various courses.

show abstract

Association Rule Mining from an Intelligent Tutor

Cited by 10 publications

References 10 publications

Development and validation of the smart classroom inventory

Development and validation of the smart classroom inventory

Exploring Relations Among Pre-Service Science Teachers’ Motivational Beliefs, Learning Strategies and Constructivist Learning Environment Perceptions Through Unsupervised Data Mining

Analysis of Students’ Grades in Mathematics, English, and Programming Courses: A KDD Approach

Contact Info

Product

Resources

About