Applying Text Mining, Clustering Analysis, and Latent Dirichlet Allocation Techniques for Topic Classification of Environmental Education Journals

I-Cheng Chang,Yu-Jie Chang,Tai-Kuei Yu,Tai-Yi Yu

doi:10.3390/su131910856

Abstract

Facing the big data wave, this study applied artificial intelligence to cite knowledge and find a feasible process to play a crucial role in supplying innovative value in environmental education. Intelligence agents of artificial intelligence and natural language processing (NLP) are two key areas leading the trend in artificial intelligence; this research adopted NLP to analyze the research topics of environmental education research journals in the Web of Science (WoS) database during 2011–2020 and interpret the categories and characteristics of abstracts for environmental education papers. The corpus data were selected from abstracts and keywords of research journal papers, which were analyzed with text mining, cluster analysis, latent Dirichlet allocation (LDA), and co-word analysis methods. The decisions regarding the classification of feature words were determined and reviewed by domain experts, and the associated TF-IDF weights were calculated for the following cluster analysis, which involved a combination of hierarchical clustering and K-means analysis. The hierarchical clustering and LDA decided the number of required categories as seven, and the K-means cluster analysis classified the overall documents into seven categories. This study utilized co-word analysis to check the suitability of the K-means classification, analyzed the terms with high TF-IDF wights for distinct K-means groups, and examined the terms for different topics with the LDA technique. A comparison of the results demonstrated that most categories that were recognized with K-means and LDA methods were the same and shared similar words; however, two categories had slight differences. The involvement of field experts assisted with the consistency and correctness of the classified topics and documents.

Highlights

Introduction iationsThe booming development of Internet technology and the digital economy has pushed today’s society into the tide of the big data era
This study focused on environmental education and applied text mining and multivariate technologies to classify topics of journal papers, compare the categorized results with two different techniques, and perform auditing procedures with domain experts to confirm the consistency of topic classification on environmental education papers
The top fifteen feature words with high TF-IDF weights for the third cluster (K3), termed as “environmental education focused on education for students, teachers, and schools,” were student, teacher, school, environmental education, learn, program, knowledge, environment, course, experience, attitude, model, science, eco, and relation

Summary

Introduction

The booming development of Internet technology and the digital economy has pushed today’s society into the tide of the big data era. Facing the big data wave, the usage of applying artificial intelligence techniques to extract knowledge and wisdom and analyzing the massive and messy data provide the key technologies for innovative business value and business models. Combining the big data and environmental education issues, most scholars are committed to educational learning issues, such as “e-classrooms,” “learning models,” “smart learning environments,” and “distance cooperative learning” [1,2]. Two key areas of intelligent agents and natural language processing (NLP) lead the way [3,4]. Intelligent agents automatically process huge amounts of data through computer programs, assist with sorting and filtering data streams, and automatically organize them into manageable high-value information.

Objectives

Methods

Results

Conclusion