Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 1

A Systematic Literature Review of Topic Modeling Techniques in User Reviews

Journal of Information Systems Engineering and Business Intelligence · Vol. 11 No. 2 (2025) · pp. 238–253

DOI
10.20473/jisebi.11.2.238-253
ISSN
2443-2555, 2598-6333
Published
2025-07-22
Publisher
Universitas Airlangga
Language
eng
License
creativecommons.org/licenses/by/4.0

Abstract

Background: The escalating volume of user review data is necessitating automated methods for extracting valuable insights. Topic modeling was a vital method for understanding key discussions and user opinions. However, there was no comprehensive analysis of the scientific work specifically on topic modeling applied to user review datasets, including its main applications and a comparative analysis of the strengths and limitations of identified methods. This study addressed the gap by characterizing the scientific discussion, identifying potential directions, and exploring currently underutilized application areas within the context of user review analysis. Objective: This study aimed to recognize the implementation trend of topic modeling in various areas and to comprehend the methodology that could be applied to the user review dataset. Methods: A systematic literature review (SLR) was adopted by implementing Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines within six-year spans, narrowing 1746 to 28 selected primary studies. Results: The underlying insight was that user reviews had been critical as the primary data for topic modeling in analyzing various applications. Digital banking and transportation applications were the sectors that received the greatest attention. In this context, Latent Dirichlet Allocation (LDA) was the most extensively used method, with a focus on overcoming its limitations by incorporating additional strategies into LDA-based models. Conclusion: The bibliometric analysis and mapping study practically contributed as a reference when assessing the dominant topic in similar app categories and topic modeling algorithms. Furthermore, this study comprehensively analyzed various topic modeling algorithms, presenting both the strengths and weaknesses of informed selection in relevant applications. Considering the keywords cluster analysis, service quality could be adopted based on the output of the topic modeling. Keywords: Topic modeling, User review, Systematic literature review, Bibliometric analysis

Collaboration network of the authors

9 authors · 15 co-authorship links · 6 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • University of Indonesia
  • Universitas Teknokrat Indonesia
  • Universitas Islam Negeri Raden Intan Lampung
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Dana Indra SensuseUniversity of Indonesia2
Ahmad Ari AldinoUniversitas Teknokrat Indonesia1
Riyama AmbarwatiUniversitas Islam Negeri Raden Intan Lampung1
Rias Kumalasari DeviUniversity of Indonesia1
KautsarinaAffiliation unknown1
Muhamad Adhytia Wana Putra RahmadhanUniversity of Indonesia1
Kautsarina KautsarinaAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://e-journal.unair.ac.id/JISEBI/oai, first harvested 29 Okt 2026, last seen 1 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">A Systematic Literature Review of Topic Modeling Techniques in User Reviews</dc:title>
	<dc:creator>Mustaqim, Ilham Zharif</dc:creator>
	<dc:creator>Suryono, Ryan Randy</dc:creator>
	<dc:description xml:lang="en-US">Background: The escalating volume of user review data is necessitating automated methods for extracting valuable insights. Topic modeling was a vital method for understanding key discussions and user opinions. However, there was no comprehensive analysis of the scientific work specifically on topic modeling applied to user review datasets, including its main applications and a comparative analysis of the strengths and limitations of identified methods. This study addressed the gap by characterizing the scientific discussion, identifying potential directions, and exploring currently underutilized application areas within the context of user review analysis. 
Objective: This study aimed to recognize the implementation trend of topic modeling in various areas and to comprehend the methodology that could be applied to the user review dataset. 
Methods: A systematic literature review (SLR) was adopted by implementing Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines within six-year spans, narrowing 1746 to 28 selected primary studies. 
Results: The underlying insight was that user reviews had been critical as the primary data for topic modeling in analyzing various applications. Digital banking and transportation applications were the sectors that received the greatest attention. In this context, Latent Dirichlet Allocation (LDA) was the most extensively used method, with a focus on overcoming its limitations by incorporating additional strategies into LDA-based models. 
Conclusion: The bibliometric analysis and mapping study practically contributed as a reference when assessing the dominant topic in similar app categories and topic modeling algorithms. Furthermore, this study comprehensively analyzed various topic modeling algorithms, presenting both the strengths and weaknesses of informed selection in relevant applications. Considering the keywords cluster analysis, service quality could be adopted based on the output of the topic modeling. 
Keywords: Topic modeling, User review, Systematic literature review, Bibliometric analysis</dc:description>
	<dc:publisher xml:lang="en-US">Universitas Airlangga</dc:publisher>
	<dc:date>2025-07-22</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>text/xml</dc:format>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://e-journal.unair.ac.id/JISEBI/article/view/70728</dc:identifier>
	<dc:identifier>10.20473/jisebi.11.2.238-253</dc:identifier>
	<dc:source xml:lang="en-US">Journal of Information Systems Engineering and Business Intelligence; Vol. 11 No. 2 (2025): June; 238-253</dc:source>
	<dc:source>2443-2555</dc:source>
	<dc:source>2598-6333</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://e-journal.unair.ac.id/JISEBI/article/view/70728/33590</dc:relation>
	<dc:relation>https://e-journal.unair.ac.id/JISEBI/article/view/70728/33440</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 The Authors. Published by Universitas Airlangga.</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by/4.0</dc:rights>
</oai_dc:dc>