Abstract
This article describes the design and implementation of a non-intrusive method of assessing customer satisfaction in a voice-enabled electronic commerce environment. After recording a customer's speech voice during his or her interaction with a voice-enabled Web system (VWS), a subsequent questionnaire survey was immediately administered to identify the satisfaction level of the customer. Afterward, a collection of recorded customer voice files and the corresponding values of customer satisfaction were used to construct an artificial neural network-based expert system, the satisfaction level assessment system (SLAS), which was thereafter integrated into VWS for automatically detecting the satisfaction level of VWS users. Experiments were performed to test the feasibility and applicability of the proposed method, and good preliminary results were derived. Instead of using the conventional questionnaire-based approach, SLAS is non-intrusive because it does not require users to fill out any questionnaire. The proposed method can be used by various voice-based business applications, such as call centers and customer relationship management, to achieve the business objective of improving customer satisfaction, enforcing customer loyalty, increasing re-purchase rate, and enhancing enterprise's benefits. The proposed SLAS (including method and system) that was filed for patent application was recently approved by the Taiwan Intellectual Property Office under Patent No. I268478.
ACKNOWLEDGEMENT
The editor and anonymous reviewers are highly appreciated for their invaluable comments and suggestions. This research was supported by a grant from the National Science Council, Taiwan, under contract numbers NSC-96-2221-E-005-088-MY2.