izpis_h1_title_alt

Učna analitika kombiniranega učenja v visokem šolstvu : doktorska disertacija
ID Keržič, Damijana (Author), ID Škulj, Damjan (Mentor) More about this mentor... This link opens in a new window, ID Dečman, Mitja (Comentor)

.pdfPDF - Presentation file, Download (7,24 MB)
MD5: D3CB917F6E28837E76FF0B3A1CF0E56A

Abstract
Kombinirano učenje, ki predstavlja preplet tradicionalnega poučevanja v predavalnici z izvedbo v spletnem okolju, postaja vse prisotno tudi v visokem šolstvu. Sistemi za upravljanje učenja, v katerih se odvija e-učenje, shranjujejo vsako interakcijo študenta s sistemom v dnevniških datotekah. Hkrati s temi podatki se o študentu vodijo različne zbirke izobraževalnih podatkov v elektronski obliki in tudi ankete so vse pogosteje implementirane v spletnem okolju. Raziskovanje, analiziranje in rudarjenje izobraževalnih podatkov zbranih v različnih podatkovnih zbirkah z namenom razumeti proces učenja in izluščiti informacije, ki bi pomagale pri tehtnih odločitvah za izboljšanje izobraževalnega procesa, predstavljajo znanstveno področje poimenovano učna analitika. Namen pričujoče disertacije je izboljšati razumevanje procesa učenja v kombiniranem učenju v visokošolskem izobraževanju s ciljem opredeliti dejavnike, ki pomembno vplivajo na delo študenta v spletni učilnici, in med aktivnostmi določiti tiste, ki jih lahko povežemo s končno uspešnostjo. V empiričnem delu sta predstavljena dva pogosta pristopa učne analitike. Analitika je bila opravljena s prosto dostopnimi programskimi orodji na raznovrstnih podatkovnih zbirkah študentov Fakultete za upravo. Z rudarjenjem izobraževalnih podatkov je raziskana uspešnost različnih napovednih modelov v napovedovanju končne (ne)uspešnosti študenta na osnovi njegove aktivnosti v spletni učilnici ter predispozicij (učni pristop, predhodna uspešnost). Pri tem so se razkrile nekatere odločilne aktivnosti v spletni učilnici in zaznale razlike med predmeti, medtem ko povezanosti študentovih predispozicij in končne uspešnosti nismo potrdili. Na osnovi modelov sprejemanja informacijskih sistemov ter z vključevanjem učnih teorij je predlagan konceptualni model uspešnosti študenta v kombiniranem učenju, ki je ovrednoten z uporabo modeliranja strukturnih enačb. Ugotovitve konceptualnega modela izpostavljajo ključno vlogo učitelja v učnem procesu, ki z ustvarjanje pozitivne učne klime predstavlja enega pomembnejših faktorjev uspešnosti študenta v kombiniranem študiju. Izsledki raziskave so koristni pri načrtovanju sprememb, ki prispevajo k izboljšanju kakovosti poučevanja tako za Fakulteto za upravo kot tudi širše.

Language:Slovenian
Keywords:kombinirano učenje, učna analitika, dnevniške datoteke, učni pristop, rudarjenje izobraževalnih podatkov, napovedovanje študentove uspešnosti, konceptualni model študentove uspešnosti, modeliranje strukturnih enačb
Work type:Doctoral dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FDV - Faculty of Social Sciences
Place of publishing:Ljubljana
Publisher:[D. Keržič]
Year:2022
Number of pages:300 str.
PID:20.500.12556/RUL-137171 This link opens in a new window
UDC:378:004(043.2)
COBISS.SI-ID:110544131 This link opens in a new window
Publication date in RUL:04.06.2022
Views:2031
Downloads:184
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Learning analytics of blended learning in higher education
Abstract:
Blended learning is becoming ubiquitous in higher education. It combines traditional face-to-face teaching and online learning that typically takes place in learning management systems which store all student interactions with the system in their log files. In addition to this data, education institutions store various electronic student datasets and survey responses. Learning analytics involves collection, analysis and mining of education data to better understand the learning process and obtain information that can inform decision-making with regard to enhancing student success. The purpose of this dissertation is to improve the understanding of the blended learning process in higher education with the aim of identifying the factors that significantly influence student work in the online classroom, and determining activities that are most associated with student final performance. The empirical part presents two frequent learning analytics approaches carried out with open source software. The calculations were based on education data from various data sources of the Faculty of Public Administration. Education data mining examined the predictive effectiveness of various models of predicting student final (non)performance based on their activity in the online classroom and predispositions (learning approach, previous performance). The study revealed some more significant activities and detected some differences between the courses. The connection between student predispositions and their final performance was not confirmed. A conceptual model of student performance in blended learning was proposed based on models of acceptance of technology and theories of learning. The model was evaluated with structural equation modeling. The findings point out the key role of the teacher in the learning process. By creating a positive learning climate the teacher represents a significant factor in student performance in blended learning. The findings contribute to quality enhancement of teaching at the Faculty of Public Administration and also at other education institutions.

Keywords:blended learning, learning analytics, data logfile, students’ approaches to learning, education data mining, predicting student performance, conceptual model of student performance, structural equation modeling

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back