We adjust sentiment analysis techniques to automatically detect customer emotion in on-line service interactions of multiple business domains. Then we use the adjusted sentiment analysis tool to report insights about the dynamics of emotion in on-line service chats, using a large data set of Telecommunication customer service interactions. Our analyses show customer emotions starting out negative and evolving into positive as the interaction ends. Also, we identify a close relationship between customer emotion dynamicsduring the service interaction and the concepts of service failure and recovery. This connection manifests in customer service quality evaluationsafter the interaction ends. Our study shows the connection between customer emotion and service quality as service interactions unfold, and suggests the use of sentiment analysis tools for real-time monitoring and control of web-based service quality.