Topic Modeling: Perspectives From a Literature Review

Abstract

Topic modeling is a Natural Language Processing technique that has gained popularity over the last ten years, with applications in multiple fields of knowledge. However, there is insufficient empirical evidence to show how this field of study has developed over the years, as well as the main models that have been applied in different contexts. The objective of this paper is to analyze the evolution of the topic modeling technique, the main areas in which it has been applied, and the models that are recommended for specific types of data. The methodology applied is based on bibliometric analysis. First, we searched the Web of Science and the Scopus databases. We then used scientometric techniques and a Tree of Science methodology, which allowed us to analyze the search results from the perspectives of classics, structure, and trends. The results show that the USA and China are among the most productive countries in this field and the applications have been mainly in the identification of sub-topics in short texts, such as social networks and blogs. The main conclusion of this work is that topic modeling is a versatile technique that can complement systematic literature reviews and that has been well-received in different academic and research contexts. The results of this study will help researchers and academics to recognize the importance of these techniques for reviewing large volumes of unstructured information, such as research articles, and in general, for systematic literature reviews.

Water Safety and Water Governance: A Scientometric Review

“…The use of both datasets provides a comprehensive overview of the current state of the research on water safety and governance and facilitates scientometric analysis, including citation and collaboration network analysis. Recent studies have emphasized the importance of combining Scopus and WoS for certain research topics, and this study aligns with these recommendations [9]. Using both datasets allows for a more general and complete understanding of the research on water safety and water governance [10].…”

Tourism and Conservation Empowered by Augmented Reality: A Scientometric Analysis Based on the Science Tree Metaphor

“…These documents are distributed as follows: conference papers (306, or 41.92%), articles (276, or 37.81%), conference reviews (56, or 7.67%), reviews (42, or 5.75%), book chapters (34, 4.66%), notes (5, or 0.68%), early access (3, or 0.41%), books (3, 0.41%), proceedings papers (1, or 0.14%), erratum (1, 0.14%), letters (1, or 0.14%), and meeting abstracts (1, or 0.14%). Even though the percentage of proceedings, errata, letters, and meeting abstracts is small (4, or 0.46%), for some research areas these documents are significant [63]. Additionally, certain algorithms, such as the tree of science algorithm, select the most relevant literature, making it unnecessary to exclude this data from the outset.…”

Pemodelan Topik pada Media Berita Online Menggunakan Latent Dirichlet Allocation (Studi Kasus Merek Somethinc)

“…Topic modeling merupakan salah satu teknik unsupervised machine learning untuk menemukan tema tersembunyi dari kumpulan dokumen teks besar guna mengelompokkan tema-tema tersebut menjadi satu Pemodelan Topik pada Media Berita Online... (Puspita et al, 2024) topik [9], [10]. Pemodelan topik menganggap bahwa setiap dokumen merupakan kombinasi dari sekumpulan topik dan kata [19]. Latent Dirichlet Allocation (LDA) merupakan salah satu metode dari pemodelan topik yang banyak digunakan.…”