Build sentiment classification prediction model for O2O service

Long Sheng Chen; Wan Ting Chien; Hua Nan Chang

doi:10.1145/3133811.3133825

Build sentiment classification prediction model for O2O service

Long Sheng Chen
, Wan Ting Chien
, Hua Nan Chang

Department of Industrial Engineering and Management

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

With the rapid development of information and communication technology, O2O (Online to Offline) business model has attracted lots of attentions for enterprises. In such a fast-growing environment, some studies indicated that lack of trust will bring a great damage to O2O business. Besides, some published works pointed out those negative comments in social communities will decrease the consumer's trust to O2O companies and platforms. So, it is necessary for enterprises to understand the important factors that affect consumers' sentiment of textual reviews. Therefore, this study aims to build prediction models by using Support Vector Machines Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO), respectively. We do not only attempt to build sentiment classification models, but also to find the important factors that affect the sentiments of comments. The findings can be references for O2O market enterprises to carefully answer customers' comments to improve customers' trust and service quality.

Original language	English
Title of host publication	2017 3rd International Conference on Industrial and Business Engineering, ICIBE 2017
Publisher	Association for Computing Machinery
Pages	10-14
Number of pages	5
ISBN (Electronic)	9781450353519
DOIs	https://doi.org/10.1145/3133811.3133825
State	Published - 17 Aug 2017
Event	3rd International Conference on Industrial and Business Engineering, ICIBE 2017 - Sapporo, Japan Duration: 17 Aug 2017 → 19 Aug 2017

Publication series

Name	ACM International Conference Proceeding Series
Volume	Part F130952

Conference

Conference	3rd International Conference on Industrial and Business Engineering, ICIBE 2017
Country/Territory	Japan
City	Sapporo
Period	17/08/17 → 19/08/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computing Machinery.

Keywords

Feature selection
LASSO
O2O
Sentiment classification
SVM-rfe

Access to Document

10.1145/3133811.3133825

Cite this

@inproceedings{9d17f3d9dcd5402382a8a8b936fcdd94,

title = "Build sentiment classification prediction model for O2O service",

abstract = "With the rapid development of information and communication technology, O2O (Online to Offline) business model has attracted lots of attentions for enterprises. In such a fast-growing environment, some studies indicated that lack of trust will bring a great damage to O2O business. Besides, some published works pointed out those negative comments in social communities will decrease the consumer's trust to O2O companies and platforms. So, it is necessary for enterprises to understand the important factors that affect consumers' sentiment of textual reviews. Therefore, this study aims to build prediction models by using Support Vector Machines Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO), respectively. We do not only attempt to build sentiment classification models, but also to find the important factors that affect the sentiments of comments. The findings can be references for O2O market enterprises to carefully answer customers' comments to improve customers' trust and service quality.",

keywords = "Feature selection, LASSO, O2O, Sentiment classification, SVM-rfe",

author = "Chen, \{Long Sheng\} and Chien, \{Wan Ting\} and Chang, \{Hua Nan\}",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computing Machinery.; 3rd International Conference on Industrial and Business Engineering, ICIBE 2017 ; Conference date: 17-08-2017 Through 19-08-2017",

year = "2017",

month = aug,

day = "17",

doi = "10.1145/3133811.3133825",

language = "???core.languages.en\_GB???",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "10--14",

booktitle = "2017 3rd International Conference on Industrial and Business Engineering, ICIBE 2017",

}

Chen, LS, Chien, WT & Chang, HN 2017, Build sentiment classification prediction model for O2O service. in 2017 3rd International Conference on Industrial and Business Engineering, ICIBE 2017. ACM International Conference Proceeding Series, vol. Part F130952, Association for Computing Machinery, pp. 10-14, 3rd International Conference on Industrial and Business Engineering, ICIBE 2017, Sapporo, Japan, 17/08/17. https://doi.org/10.1145/3133811.3133825

Build sentiment classification prediction model for O2O service. / Chen, Long Sheng; Chien, Wan Ting; Chang, Hua Nan.
2017 3rd International Conference on Industrial and Business Engineering, ICIBE 2017. Association for Computing Machinery, 2017. p. 10-14 (ACM International Conference Proceeding Series; Vol. Part F130952).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Build sentiment classification prediction model for O2O service

AU - Chen, Long Sheng

AU - Chien, Wan Ting

AU - Chang, Hua Nan

PY - 2017/8/17

Y1 - 2017/8/17

N2 - With the rapid development of information and communication technology, O2O (Online to Offline) business model has attracted lots of attentions for enterprises. In such a fast-growing environment, some studies indicated that lack of trust will bring a great damage to O2O business. Besides, some published works pointed out those negative comments in social communities will decrease the consumer's trust to O2O companies and platforms. So, it is necessary for enterprises to understand the important factors that affect consumers' sentiment of textual reviews. Therefore, this study aims to build prediction models by using Support Vector Machines Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO), respectively. We do not only attempt to build sentiment classification models, but also to find the important factors that affect the sentiments of comments. The findings can be references for O2O market enterprises to carefully answer customers' comments to improve customers' trust and service quality.

AB - With the rapid development of information and communication technology, O2O (Online to Offline) business model has attracted lots of attentions for enterprises. In such a fast-growing environment, some studies indicated that lack of trust will bring a great damage to O2O business. Besides, some published works pointed out those negative comments in social communities will decrease the consumer's trust to O2O companies and platforms. So, it is necessary for enterprises to understand the important factors that affect consumers' sentiment of textual reviews. Therefore, this study aims to build prediction models by using Support Vector Machines Recursive Feature Elimination (SVM-RFE) and Least Absolute Shrinkage and Selection Operator (LASSO), respectively. We do not only attempt to build sentiment classification models, but also to find the important factors that affect the sentiments of comments. The findings can be references for O2O market enterprises to carefully answer customers' comments to improve customers' trust and service quality.

KW - Feature selection

KW - LASSO

KW - O2O

KW - Sentiment classification

KW - SVM-rfe

UR - https://www.scopus.com/pages/publications/85037721631

U2 - 10.1145/3133811.3133825

DO - 10.1145/3133811.3133825

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85037721631

T3 - ACM International Conference Proceeding Series

SP - 10

EP - 14

BT - 2017 3rd International Conference on Industrial and Business Engineering, ICIBE 2017

PB - Association for Computing Machinery

T2 - 3rd International Conference on Industrial and Business Engineering, ICIBE 2017

Y2 - 17 August 2017 through 19 August 2017

ER -

Build sentiment classification prediction model for O2O service

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this