Analysing structured learning behaviour in Massive Open Online Courses (MOOCs): An approach based on process mining and clustering

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

3 Citaties (Scopus)

Uittreksel

The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students' activities in a MOOC from the perspective of personal constructivism, which we operationalized as a combination of learning behaviour and learning progress. This study considers students' data analyzed as per the MOOC Process Mining: Data Science in Action. We explore the relation between learning behaviour and learning progress in MOOCs, with the purpose to gain insight into how passing and failing students distribute their activities differently along the course weeks, rather than predict students' grades from their activities. Commonly-studied aggregated counts of activities, specific course item counts, and order of activities were examined with cluster analyses, means analyses, and process mining techniques. We found four meaningful clusters of students, each representing specific behaviour ranging from only starting to fully completing the course. Process mining techniques show that successful students exhibit a more steady learning behaviour. However, this behaviour is much more related to actually watching videos than to the timing of activities. The results offer guidance for teachers.

TaalEngels
Pagina's38-60
Aantal pagina's23
TijdschriftInternational Review of Research in Open and Distance Learning
Volume19
Nummer van het tijdschrift5
DOI's
StatusGepubliceerd - 1 jan 2018

Vingerafdruk

learning behavior
learning success
student
constructivism
learning
learning process
video
teacher
science

Trefwoorden

    Citeer dit

    @article{f519175f5ae040a8a7299d49028ab2fb,
    title = "Analysing structured learning behaviour in Massive Open Online Courses (MOOCs): An approach based on process mining and clustering",
    abstract = "The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students' activities in a MOOC from the perspective of personal constructivism, which we operationalized as a combination of learning behaviour and learning progress. This study considers students' data analyzed as per the MOOC Process Mining: Data Science in Action. We explore the relation between learning behaviour and learning progress in MOOCs, with the purpose to gain insight into how passing and failing students distribute their activities differently along the course weeks, rather than predict students' grades from their activities. Commonly-studied aggregated counts of activities, specific course item counts, and order of activities were examined with cluster analyses, means analyses, and process mining techniques. We found four meaningful clusters of students, each representing specific behaviour ranging from only starting to fully completing the course. Process mining techniques show that successful students exhibit a more steady learning behaviour. However, this behaviour is much more related to actually watching videos than to the timing of activities. The results offer guidance for teachers.",
    keywords = "Constructivism, Educational data mining, Learning analytics, Learning behavior, Process mining, Social learning analytics",
    author = "{van den Beemt}, A.A.J. and J.C.A.M. Buijs and {van der Aalst}, W.M.P.",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.19173/irrodl.v19i5.3748",
    language = "English",
    volume = "19",
    pages = "38--60",
    journal = "International Review of Research in Open and Distance Learning",
    issn = "1492-3831",
    publisher = "Athabasca University",
    number = "5",

    }

    Analysing structured learning behaviour in Massive Open Online Courses (MOOCs) : An approach based on process mining and clustering. / van den Beemt, A.A.J.; Buijs, J.C.A.M.; van der Aalst, W.M.P.

    In: International Review of Research in Open and Distance Learning, Vol. 19, Nr. 5, 01.01.2018, blz. 38-60.

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    TY - JOUR

    T1 - Analysing structured learning behaviour in Massive Open Online Courses (MOOCs)

    T2 - International Review of Research in Open and Distance Learning

    AU - van den Beemt,A.A.J.

    AU - Buijs,J.C.A.M.

    AU - van der Aalst,W.M.P.

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students' activities in a MOOC from the perspective of personal constructivism, which we operationalized as a combination of learning behaviour and learning progress. This study considers students' data analyzed as per the MOOC Process Mining: Data Science in Action. We explore the relation between learning behaviour and learning progress in MOOCs, with the purpose to gain insight into how passing and failing students distribute their activities differently along the course weeks, rather than predict students' grades from their activities. Commonly-studied aggregated counts of activities, specific course item counts, and order of activities were examined with cluster analyses, means analyses, and process mining techniques. We found four meaningful clusters of students, each representing specific behaviour ranging from only starting to fully completing the course. Process mining techniques show that successful students exhibit a more steady learning behaviour. However, this behaviour is much more related to actually watching videos than to the timing of activities. The results offer guidance for teachers.

    AB - The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students' activities in a MOOC from the perspective of personal constructivism, which we operationalized as a combination of learning behaviour and learning progress. This study considers students' data analyzed as per the MOOC Process Mining: Data Science in Action. We explore the relation between learning behaviour and learning progress in MOOCs, with the purpose to gain insight into how passing and failing students distribute their activities differently along the course weeks, rather than predict students' grades from their activities. Commonly-studied aggregated counts of activities, specific course item counts, and order of activities were examined with cluster analyses, means analyses, and process mining techniques. We found four meaningful clusters of students, each representing specific behaviour ranging from only starting to fully completing the course. Process mining techniques show that successful students exhibit a more steady learning behaviour. However, this behaviour is much more related to actually watching videos than to the timing of activities. The results offer guidance for teachers.

    KW - Constructivism

    KW - Educational data mining

    KW - Learning analytics

    KW - Learning behavior

    KW - Process mining

    KW - Social learning analytics

    UR - http://www.scopus.com/inward/record.url?scp=85057419187&partnerID=8YFLogxK

    U2 - 10.19173/irrodl.v19i5.3748

    DO - 10.19173/irrodl.v19i5.3748

    M3 - Article

    VL - 19

    SP - 38

    EP - 60

    JO - International Review of Research in Open and Distance Learning

    JF - International Review of Research in Open and Distance Learning

    SN - 1492-3831

    IS - 5

    ER -