Joint multi-grain topic sentiment: Modeling semantic aspects for online reviews

Md Hijbul Alam; Woo Jong Ryu; Sang-Geun Lee

doi:10.1016/j.ins.2016.01.013

Joint multi-grain topic sentiment: Modeling semantic aspects for online reviews

Md Hijbul Alam, Woo Jong Ryu, Sang-Geun Lee

Center for Artificial Intelligence Research

Research output: Contribution to journal › Article › peer-review

70 Citations (Scopus)

Abstract

The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.

Original language	English
Pages (from-to)	206-223
Number of pages	18
Journal	Information Sciences
Volume	339
DOIs	https://doi.org/10.1016/j.ins.2016.01.013
Publication status	Published - 2016 Apr 20

Bibliographical note

Funding Information:
This research was supported by Basic Science Research Program through the National Research Foundation of Kore a (NRF) funded by the Ministry of Science, ICT and Future Planning (numbers 2015R1A2A1A10052665 and 2015R1A2A1A15052701 ).

Publisher Copyright:
© 2016 Elsevier Inc. All rights reserved.

Keywords

Aspect discovery
Opinion mining
Sentiment analysis
Topic model

ASJC Scopus subject areas

Software
Control and Systems Engineering
Theoretical Computer Science
Computer Science Applications
Information Systems and Management
Artificial Intelligence

Access to Document

10.1016/j.ins.2016.01.013

Cite this

@article{27f84129c4d2455bbc2607c9e4dd16d2,

title = "Joint multi-grain topic sentiment: Modeling semantic aspects for online reviews",

abstract = "The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.",

keywords = "Aspect discovery, Opinion mining, Sentiment analysis, Topic model",

author = "Alam, {Md Hijbul} and Ryu, {Woo Jong} and Sang-Geun Lee",

note = "Funding Information: This research was supported by Basic Science Research Program through the National Research Foundation of Kore a (NRF) funded by the Ministry of Science, ICT and Future Planning (numbers 2015R1A2A1A10052665 and 2015R1A2A1A15052701 ). Publisher Copyright: {\textcopyright} 2016 Elsevier Inc. All rights reserved.",

year = "2016",

month = apr,

day = "20",

doi = "10.1016/j.ins.2016.01.013",

language = "English",

volume = "339",

pages = "206--223",

journal = "Information Sciences",

issn = "0020-0255",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Joint multi-grain topic sentiment

T2 - Modeling semantic aspects for online reviews

AU - Alam, Md Hijbul

AU - Ryu, Woo Jong

AU - Lee, Sang-Geun

N1 - Funding Information: This research was supported by Basic Science Research Program through the National Research Foundation of Kore a (NRF) funded by the Ministry of Science, ICT and Future Planning (numbers 2015R1A2A1A10052665 and 2015R1A2A1A15052701 ). Publisher Copyright: © 2016 Elsevier Inc. All rights reserved.

PY - 2016/4/20

Y1 - 2016/4/20

N2 - The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.

AB - The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.

KW - Aspect discovery

KW - Opinion mining

KW - Sentiment analysis

KW - Topic model

UR - http://www.scopus.com/inward/record.url?scp=84963820824&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2016.01.013

DO - 10.1016/j.ins.2016.01.013

M3 - Article

AN - SCOPUS:84963820824

SN - 0020-0255

VL - 339

SP - 206

EP - 223

JO - Information Sciences

JF - Information Sciences

ER -

Joint multi-grain topic sentiment: Modeling semantic aspects for online reviews

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this