Identifying individual expectations in service recovery through natural language processing and machine learning

作者：

Highlights：

• A method to identify individual expectations for service recovery is proposed.

• New expectation classification is presented based on extant literature.

• Word2vec and machine learning algorithms are used to detect expectations.

• SVMs and Naïve Bayesian classifiers are selected in the method.

摘要

•A method to identify individual expectations for service recovery is proposed.•New expectation classification is presented based on extant literature.•Word2vec and machine learning algorithms are used to detect expectations.•SVMs and Naïve Bayesian classifiers are selected in the method.

论文关键词：Service recovery,Service recovery expectations,Machine learning,Natural language processing,Customer expectation detection method

论文评审过程：Received 4 October 2018, Revised 28 April 2019, Accepted 28 April 2019, Available online 29 April 2019, Version of Record 4 May 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.04.063