Similarity-based approach for accurately retrieving similar cases to intelligently handle online complaints

Xiaolan Cui, Shuqin Cai, Yuchu Qin

Research output: Contribution to journalArticle

Abstract

Purpose – The purpose of this paper is to propose a similarity-based approach to accurately retrieve reference solutions for the intelligent handling of online complaints.
Design/methodology/approach – This approach uses a case-based reasoning framework and firstly formalizes existing online complaints and their solutions, new online complaints, and complaint products, problems and content as source cases, target cases and distinctive features of each case, respectively. Then the
process of using existing word-level, sense-level and text-level measures to assess the similarities between complaint products, problems and contents is explained. Based on these similarities, a measure with high accuracy in assessing the overall similarity between cases is designed. The effectiveness of the approach is evaluated by numerical and empirical experiments.
Findings – The evaluation results show that a measure simultaneously considering the features of similarity at word, sense and text levels can obtain higher accuracy than those measures that consider only one level feature of similarity; and that the designed measure is more accurate than all of its linear
combinations.
Practical implications – The approach offers a feasible way to reduce manual intervention in online complaint handling. Complaint products, problems and content should be synthetically considered when handling an online complaint. The designed procedure of the measure with high accuracy can be applied in
other applications that consider multiple similarity features or linguistic levels.
Originality/value – A method for linearly combining the similarities at all linguistic levels to accurately assess the overall similarities between online complaint cases is presented. This method is experimentally verified to be helpful to improve the accuracy of online complaint case retrieval. This is the first study that considers the accuracy of the similarity measures for online complaint case retrieval
LanguageEnglish
Pages1223-1244
Number of pages12
JournalKybernetes
Volume46
Issue number7
DOIs
Publication statusPublished - 7 Aug 2017

Fingerprint

Linguistics
complaint
Case based reasoning
High Accuracy
Experiments
Retrieval
Similarity
Case-based Reasoning
linguistics
Similarity Measure
Design Methodology
Linearly
Target
Evaluation
experiment
methodology
Experiment

Cite this

@article{7607294e94cd40189c5595a5e99e43d2,
title = "Similarity-based approach for accurately retrieving similar cases to intelligently handle online complaints",
abstract = "Purpose – The purpose of this paper is to propose a similarity-based approach to accurately retrieve reference solutions for the intelligent handling of online complaints.Design/methodology/approach – This approach uses a case-based reasoning framework and firstly formalizes existing online complaints and their solutions, new online complaints, and complaint products, problems and content as source cases, target cases and distinctive features of each case, respectively. Then theprocess of using existing word-level, sense-level and text-level measures to assess the similarities between complaint products, problems and contents is explained. Based on these similarities, a measure with high accuracy in assessing the overall similarity between cases is designed. The effectiveness of the approach is evaluated by numerical and empirical experiments.Findings – The evaluation results show that a measure simultaneously considering the features of similarity at word, sense and text levels can obtain higher accuracy than those measures that consider only one level feature of similarity; and that the designed measure is more accurate than all of its linearcombinations.Practical implications – The approach offers a feasible way to reduce manual intervention in online complaint handling. Complaint products, problems and content should be synthetically considered when handling an online complaint. The designed procedure of the measure with high accuracy can be applied inother applications that consider multiple similarity features or linguistic levels.Originality/value – A method for linearly combining the similarities at all linguistic levels to accurately assess the overall similarities between online complaint cases is presented. This method is experimentally verified to be helpful to improve the accuracy of online complaint case retrieval. This is the first study that considers the accuracy of the similarity measures for online complaint case retrieval",
keywords = "Case-based reasoning, accuracy, case retrieval, online complaint handling, similarity measure",
author = "Xiaolan Cui and Shuqin Cai and Yuchu Qin",
year = "2017",
month = "8",
day = "7",
doi = "10.1108/K-10-2016-0271",
language = "English",
volume = "46",
pages = "1223--1244",
journal = "Kybernetes",
issn = "0368-492X",
publisher = "Emerald Group Publishing Ltd.",
number = "7",

}

Similarity-based approach for accurately retrieving similar cases to intelligently handle online complaints. / Cui, Xiaolan; Cai, Shuqin; Qin, Yuchu.

In: Kybernetes, Vol. 46, No. 7, 07.08.2017, p. 1223-1244.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Similarity-based approach for accurately retrieving similar cases to intelligently handle online complaints

AU - Cui, Xiaolan

AU - Cai, Shuqin

AU - Qin, Yuchu

PY - 2017/8/7

Y1 - 2017/8/7

N2 - Purpose – The purpose of this paper is to propose a similarity-based approach to accurately retrieve reference solutions for the intelligent handling of online complaints.Design/methodology/approach – This approach uses a case-based reasoning framework and firstly formalizes existing online complaints and their solutions, new online complaints, and complaint products, problems and content as source cases, target cases and distinctive features of each case, respectively. Then theprocess of using existing word-level, sense-level and text-level measures to assess the similarities between complaint products, problems and contents is explained. Based on these similarities, a measure with high accuracy in assessing the overall similarity between cases is designed. The effectiveness of the approach is evaluated by numerical and empirical experiments.Findings – The evaluation results show that a measure simultaneously considering the features of similarity at word, sense and text levels can obtain higher accuracy than those measures that consider only one level feature of similarity; and that the designed measure is more accurate than all of its linearcombinations.Practical implications – The approach offers a feasible way to reduce manual intervention in online complaint handling. Complaint products, problems and content should be synthetically considered when handling an online complaint. The designed procedure of the measure with high accuracy can be applied inother applications that consider multiple similarity features or linguistic levels.Originality/value – A method for linearly combining the similarities at all linguistic levels to accurately assess the overall similarities between online complaint cases is presented. This method is experimentally verified to be helpful to improve the accuracy of online complaint case retrieval. This is the first study that considers the accuracy of the similarity measures for online complaint case retrieval

AB - Purpose – The purpose of this paper is to propose a similarity-based approach to accurately retrieve reference solutions for the intelligent handling of online complaints.Design/methodology/approach – This approach uses a case-based reasoning framework and firstly formalizes existing online complaints and their solutions, new online complaints, and complaint products, problems and content as source cases, target cases and distinctive features of each case, respectively. Then theprocess of using existing word-level, sense-level and text-level measures to assess the similarities between complaint products, problems and contents is explained. Based on these similarities, a measure with high accuracy in assessing the overall similarity between cases is designed. The effectiveness of the approach is evaluated by numerical and empirical experiments.Findings – The evaluation results show that a measure simultaneously considering the features of similarity at word, sense and text levels can obtain higher accuracy than those measures that consider only one level feature of similarity; and that the designed measure is more accurate than all of its linearcombinations.Practical implications – The approach offers a feasible way to reduce manual intervention in online complaint handling. Complaint products, problems and content should be synthetically considered when handling an online complaint. The designed procedure of the measure with high accuracy can be applied inother applications that consider multiple similarity features or linguistic levels.Originality/value – A method for linearly combining the similarities at all linguistic levels to accurately assess the overall similarities between online complaint cases is presented. This method is experimentally verified to be helpful to improve the accuracy of online complaint case retrieval. This is the first study that considers the accuracy of the similarity measures for online complaint case retrieval

KW - Case-based reasoning

KW - accuracy

KW - case retrieval

KW - online complaint handling

KW - similarity measure

U2 - 10.1108/K-10-2016-0271

DO - 10.1108/K-10-2016-0271

M3 - Article

VL - 46

SP - 1223

EP - 1244

JO - Kybernetes

T2 - Kybernetes

JF - Kybernetes

SN - 0368-492X

IS - 7

ER -