Topic Modelling using Latent Dirichlet Allocation (LDA) to Investigate the Latent Topics of Mathematical Creative Thinking Research in Indonesia

In mathematics education, there is increasing interest in Mathematical Creative Thinking (MCT), and numerous scientific documents on this topic have been published in Indonesia. The availability of publication databases has made it easier to access these documents and collect large amounts of data r...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of Intelligent Computing & Health Informatics Ročník 3; číslo 2; s. 35
Hlavný autor: Maulidiya, Della
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: 22.02.2023
ISSN:2715-6923, 2721-9186
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In mathematics education, there is increasing interest in Mathematical Creative Thinking (MCT), and numerous scientific documents on this topic have been published in Indonesia. The availability of publication databases has made it easier to access these documents and collect large amounts of data related to MCT. This data has the potential to uncover latent topics within MCT research articles published in Indonesian journals. This study analyzed a dataset of 102 articles obtained from Garuda (Digital Reference Garda) published between 2010 and 2022 in six proceedings and 49 journals. The study applied text processing techniques and used topic modeling with Latent Dirichlet Allocation (LDA) and variational expectation maximization algorithm (VEM) to produce 23 topics. Each topic consisted of general and special words from the beta probability value. The study found 30 unique words from topic modeling, including learning, abilities, problems, skills, mathematics, tests, levels, answers, approaches, assessments, basics, classes, developing, values, ideas, instruments, materials, mathematics, moderate, models, motivation, open-ended, processes, questions, reasons, solving, styles, subjects, teaching, and worksheets. The study also used LDA to classify documents into discovered themes and found that the five MCT research focuses were learning approaches, student competencies, teacher competencies, assessments, and learning resources. The study's findings revealed a research gap, specifically, the need for more MCT studies that concentrate on enhancing teacher competency.
ISSN:2715-6923
2721-9186
DOI:10.26714/jichi.v3i2.11428