An adaptable fine-grained sentiment analysis for summarization of multiple short online reviews

Reinald Kim Amplayo, Min Song

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this study, we present a novel method in generating summaries of multiple online reviews using a fine-grained sentiment extraction model for short texts, which is adaptable to different domains and languages. Adaptability of a model is defined as its ability to be easily modified and be usable on different domains and languages. This is important because of the diversity of domains and languages available. The fine-grained sentiment extraction model is divided into two methods: sentiment classification and aspect extraction. The sentiment classifier is built using a three-level classification approach, while the aspect extractor is built using extended biterm topic model (eBTM), an extension of LDA topic model for short texts. Overall, results show that the sentiment classifier outperforms baseline models and industry-standard classifiers while the aspect extractor outperforms other topic models in terms of aspect diversity and aspect extracting power. In addition, using the Naver movies dataset, we show that online review summarization can be effectively constructed using the proposed methods by comparing the results of our method and the results of a movie awards ceremony.

Original languageEnglish
Pages (from-to)54-67
Number of pages14
JournalData and Knowledge Engineering
Volume110
DOIs
Publication statusPublished - 2017 Jul 1

Fingerprint

Sentiment
Sentiment analysis
Summarization
Online reviews
Classifier
Topic model
Language
Movies
Adaptability
Sentiment classification
Industry standards

All Science Journal Classification (ASJC) codes

  • Information Systems and Management

Cite this

@article{3fb9c60065a84877a886767aae0f071c,
title = "An adaptable fine-grained sentiment analysis for summarization of multiple short online reviews",
abstract = "In this study, we present a novel method in generating summaries of multiple online reviews using a fine-grained sentiment extraction model for short texts, which is adaptable to different domains and languages. Adaptability of a model is defined as its ability to be easily modified and be usable on different domains and languages. This is important because of the diversity of domains and languages available. The fine-grained sentiment extraction model is divided into two methods: sentiment classification and aspect extraction. The sentiment classifier is built using a three-level classification approach, while the aspect extractor is built using extended biterm topic model (eBTM), an extension of LDA topic model for short texts. Overall, results show that the sentiment classifier outperforms baseline models and industry-standard classifiers while the aspect extractor outperforms other topic models in terms of aspect diversity and aspect extracting power. In addition, using the Naver movies dataset, we show that online review summarization can be effectively constructed using the proposed methods by comparing the results of our method and the results of a movie awards ceremony.",
author = "Amplayo, {Reinald Kim} and Min Song",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.datak.2017.03.009",
language = "English",
volume = "110",
pages = "54--67",
journal = "Data and Knowledge Engineering",
issn = "0169-023X",
publisher = "Elsevier",

}

An adaptable fine-grained sentiment analysis for summarization of multiple short online reviews. / Amplayo, Reinald Kim; Song, Min.

In: Data and Knowledge Engineering, Vol. 110, 01.07.2017, p. 54-67.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An adaptable fine-grained sentiment analysis for summarization of multiple short online reviews

AU - Amplayo, Reinald Kim

AU - Song, Min

PY - 2017/7/1

Y1 - 2017/7/1

N2 - In this study, we present a novel method in generating summaries of multiple online reviews using a fine-grained sentiment extraction model for short texts, which is adaptable to different domains and languages. Adaptability of a model is defined as its ability to be easily modified and be usable on different domains and languages. This is important because of the diversity of domains and languages available. The fine-grained sentiment extraction model is divided into two methods: sentiment classification and aspect extraction. The sentiment classifier is built using a three-level classification approach, while the aspect extractor is built using extended biterm topic model (eBTM), an extension of LDA topic model for short texts. Overall, results show that the sentiment classifier outperforms baseline models and industry-standard classifiers while the aspect extractor outperforms other topic models in terms of aspect diversity and aspect extracting power. In addition, using the Naver movies dataset, we show that online review summarization can be effectively constructed using the proposed methods by comparing the results of our method and the results of a movie awards ceremony.

AB - In this study, we present a novel method in generating summaries of multiple online reviews using a fine-grained sentiment extraction model for short texts, which is adaptable to different domains and languages. Adaptability of a model is defined as its ability to be easily modified and be usable on different domains and languages. This is important because of the diversity of domains and languages available. The fine-grained sentiment extraction model is divided into two methods: sentiment classification and aspect extraction. The sentiment classifier is built using a three-level classification approach, while the aspect extractor is built using extended biterm topic model (eBTM), an extension of LDA topic model for short texts. Overall, results show that the sentiment classifier outperforms baseline models and industry-standard classifiers while the aspect extractor outperforms other topic models in terms of aspect diversity and aspect extracting power. In addition, using the Naver movies dataset, we show that online review summarization can be effectively constructed using the proposed methods by comparing the results of our method and the results of a movie awards ceremony.

UR - http://www.scopus.com/inward/record.url?scp=85018382785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018382785&partnerID=8YFLogxK

U2 - 10.1016/j.datak.2017.03.009

DO - 10.1016/j.datak.2017.03.009

M3 - Article

AN - SCOPUS:85018382785

VL - 110

SP - 54

EP - 67

JO - Data and Knowledge Engineering

JF - Data and Knowledge Engineering

SN - 0169-023X

ER -