How Angry are Your Customers? Sentiment Analysis of Support Tickets that Escalate

Abstract

Software support ticket escalations can be an extremely costly burden for software organizations all over the world. Consequently, there exists an interest in researching how to better enable support analysts to handle such escalations. In order to do so, we need to develop tools to reliably predict if, and when, a support ticket becomes a candidate for escalation. This paper explores the use of sentiment analysis tools on customer-support analyst conversations to find indicators of when a particular support ticket may be escalated. The results of this research indicate a considerable difference in the sentiment between escalated support tickets and non-escalated support tickets. Thus, this preliminary research provides us with the necessary information to further investigate how we can reliably predict support ticket escalations, and subsequently to provide insight to support analysts to better enable them to handle support tickets that may be escalated.

Assessment of off-the-shelf SE-specific sentiment analysis tools: An extended replication study

“…In particular, researchers investigated the role of affect in social software engineering by applying sentiment analysis to the content available in collaborative software development platforms such as GitHub (Guzman et al 2014;Sinha et al 2016) and Jira (Ortu et al 2016;Mäntylä et al 2016;Murgia et al 2018). In the scope of requirements engineering research, sentiment analysis has been also leveraged to mine users' opinions about software products from their reviews in the app stores (Panichella et al 2015;Kurtanovic and Maalej 2018), from user-generated contents in microblogging platforms (Guzman et al 2016) and customers' tickets (Werner et al 2018).…”

Development and Application of Sentiment Analysis Tools in Software Engineering: A Systematic Literature Review

“…In the application domain alone, from 𝑛 = 52 papers, mostly unique (37 out of 38) data sources are used to apply a sentiment analysis tool to them. Other data sources include chat data from Amazon MTurk [74], Amazon product review [17], android bug reports [71], or support tickets from IBM [73].…”

Topic Modeling for Support Ticket using Latent Dirichlet Allocation

“…The advantages of support tickets are that all communications between customers and the support team can be recorded [2]. Increasing number of customers will allow an overflow of support tickets to be received by the support team.…”