Paper Info
Title
Topic Detection of Online Book Reviews - Preliminary Results.
Abstract
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.
Year
DOI
Venue
2019
10.1109/JCDL.2019.00098
JCDL
Keywords
Field
DocType
Online reviews, social media, topic modeling, sentiment analysis
Latent Dirichlet allocation,Social media,Information retrieval,Computer science,Sentiment analysis,Topic model
Conference
ISSN
ISBN
Citations 
2575-7865
978-1-7281-1547-4
0
PageRank 
References 
Authors
0.34
4
2
Name
Order
Citations
PageRank
Yunseon Choi100.34
Soohyung Joo215816.00