Topic detection of online book reviews: Preliminary results

Yunseon Choi, Soohyung Joo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations


This study is part of a larger research project which aims to investigate whether online reviews on children's books would represent significant factors which are useful for selecting appropriate books for children. This paper presents the preliminary results on topic detection of online book reviews. Topic modeling using Latent Dirichlet Allocation (LDA) generated several topic terms from online reviews, and we categorized those topic terms into eleven categories. Sentiment analysis was applied to examine the emotional aspects of the reviews. We examined that sentiment words which have a powerful effect on polarity values to determine whether those sentiment words appear as topic words extracted by the LDA topic modeling. The results of our study have a significant implication on understanding user behavior in online book reviews.

Original languageEnglish
Title of host publicationProceedings - 2019 ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019
EditorsMaria Bonn, Dan Wu, Stephen J. Downie, Alain Martaus
Number of pages2
ISBN (Electronic)9781728115474
StatePublished - Jun 2019
Event19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019 - Urbana-Champaign, United States
Duration: Jun 2 2019Jun 6 2019

Publication series

NameProceedings of the ACM/IEEE Joint Conference on Digital Libraries
ISSN (Print)1552-5996


Conference19th ACM/IEEE Joint Conference on Digital Libraries, JCDL 2019
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© 2019 IEEE.


  • Online reviews
  • Sentiment analysis
  • Social media
  • Topic modeling

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Topic detection of online book reviews: Preliminary results'. Together they form a unique fingerprint.

Cite this