0
Research Papers

Sentiment Root Cause Analysis Based on Fuzzy Formal Concept Analysis and Fuzzy Cognitive Map

[+] Author and Article Information
Sang-Min Park

Department of Computer
Science and Engineering,
Korea University,
145 Anam-ro Seonguk-gu,
Seoul 136-701, Korea
e-mail: wiyard@korea.ac.kr

Young-Gab Kim

Department of Computer and
Information Security,
Sejong University,
209, Neungdong-ro, Gwangjin-gu,
Seoul 143-747, Korea
e-mail: alwaysgabi@sejong.ac.kr

Doo-Kwon Baik

Department of Computer
Science and Engineering,
Korea University,
145 Anam-ro Seonguk-gu,
Seoul 136-701, Korea
e-mail: baikdk@korea.ac.kr

1Corresponding authors.

Contributed by the Design Engineering Division of ASME for publication in the JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING. Manuscript received December 14, 2015; final manuscript received June 24, 2016; published online August 19, 2016. Assoc. Editor: Jitesh H. Panchal.

J. Comput. Inf. Sci. Eng 16(3), 031004 (Aug 19, 2016) (11 pages) Paper No: JCISE-15-1411; doi: 10.1115/1.4034033 History: Received December 14, 2015; Revised June 24, 2016

Feature-level sentiment analysis can retrieve the sentimental preferences for the features of products but cannot retrieve the causes of the preferences. Previous sentiment analysis methods used sentiment words to calculate the sentiment polarity for specific features but could not utilize neutral sentiment words, even when they constituted a large proportion of the sentiment words. Fault diagnosis can extract causes and determine the root cause by using factual information and the cause-effect relation, but is not used for sentiment data. For the retrieval of sentiment root causes, we propose a sentiment root cause analysis method for user preferences. We consider sentiment relations based on fuzzy formal concept analysis (FFCA) to extend hierarchical feature-level sentiment analysis. A hierarchical relation of neutral sentiment words and explicit causal relation based on causal conjunctions is utilized to retrieve the cross features of root causes. A sentiment root cause is determined from the extracted causes to explain the preference of a sentiment expression by using a fuzzy cognitive map with a relations method. We demonstrate a factual ontology and sentiment ontology based on a feature ontology for clothing products. We evaluated the proposed sentiment root cause analysis method and verified that it is improved as compared with term frequency-based methods and sentiment score analysis.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Fuzzy formal concept analysis

Grahic Jump Location
Fig. 2

Process of sentiment root cause analysis

Grahic Jump Location
Fig. 3

Merged sentiment ontology and factual ontology based on the feature ontology

Grahic Jump Location
Fig. 4

Merged sentiment ontology and factual ontology

Grahic Jump Location
Fig. 5

Hierarchical triple relation score

Grahic Jump Location
Fig. 6

Fuzzy cognitive map with relations

Grahic Jump Location
Fig. 7

Feature ontology tree based on WordNet similarity

Grahic Jump Location
Fig. 8

Factual ontology tree with feature ontology, product description, and neutral sentiment words

Grahic Jump Location
Fig. 9

Merged sentiment ontology based on the FFCA method and factual ontology based on the feature ontology

Grahic Jump Location
Fig. 10

Ratio of triple for information words, expressive words, and auxiliary words

Grahic Jump Location
Fig. 11

Accuracy of sentiment cause analysis compared with term frequency based analysis and feature based analysis

Grahic Jump Location
Fig. 12

Accuracy of sentiment root cause analysis as compared with term frequency-based analysis, feature-based analysis, and feature/sentiment word-based analysis

Grahic Jump Location
Fig. 13

Accuracy of sentiment root cause analysis as compared with sentiment score analysis, sentiment score analysis on informational sentiment words, and feature/sentiment word-based analysis

Grahic Jump Location
Fig. 14

Sentiment cause ontology with triple node score and triple relation score, which includes the hierarchical structure based on FFCA and the nonhierarchical structure method FCM-R

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In