Web Chat Conversations from Contact Centers: a Descriptive Study

Web Chat Conversations from Contact Centers: a Descriptive Study Géraldine Damnati, Aleksandra Guerraz, Delphine Charlet Orange Labs 2 avenue Pierre Marzin, 22307 Lannion Cedex, France E-mail: {geraldine.damnati,aleksandra.guerraz,delphine.charlet}@orange.com Abstract In this article we propose a descriptive study of a chat conversations corpus from an assistance contact center. Conversations are described from several view points, including interaction analysis, language deviation analysis and typographic expressivity marks analysis. We provide in particular a detailed analysis of language deviations that are encountered in our corpus of 230 conversations, corresponding to 6879 messages and 76839 words. These deviations may be challenging for further syntactic and semantic parsing. Analysis is performed with a distinction between Customer messages and Agent messages. On the overall only 4% of the observed words are misspelled but 26% of the messages contain at least one erroneous word (rising to 40% when focused on Customer messages). Transcriptions of telephone conversations from an assistance call center are also studied, allowing comparisons between these two interaction modes to be drawn. The study reveals significant differences in terms of conversation flow, with an increased efficiency for chat conversations in spite of longer temporal span. Keywords: chat conversations, contact center, interaction, language deviation, typographic expressivity marks 1. Introduction Even if phone remains the predominant contact channel in companies’ interactions with their customers, interaction modes are much more diverse nowadays and Customer Relationship Management has to integrate multi-canality in their analytics measurements. In particular, chat conversations are growing very fast and are appreciated by both customers and agents who consider it as a way to remain in direct contact with customers while preserving a certain distance and avoiding disrespectful exchanges. From a company’s point of view, these conversations, easily available through massive logs, constitute a considerable wealth of information in order to better understand customers’ needs. From a language processing perspective, they constitute a new area of study which has been only very little explored. In this article we propose a descriptive analysis of such a chat conversation corpus. Some aspects are described through a contrastive analysis with a phone call-center conversation corpus. Most studies in the literature refer to multiparty chat conversations from chatrooms. (Falaise, 2005) constituted a corpus in French. (Martel & al., 2007) and (Shaikh & al. 2010) describe similar corpora in English. (Cadilhac et al., 2013) have studied the relational structure of such conversations through a deep discursive analysis of chat sessions in an online video game. Among the few works that have been published on contact centers chat conversations, (Dickey et al., 2007) propose a study from the perspective of the strategies adopted by agents in favor of mutual comprehension, with a focus on discontinuity phenomena, trying to understand the reasons why miscomprehension can arise. (Wu et al., 2012) propose a typography of communication modes between customers and agents through a study on a conversation interface. The media cannot be the only prism through which these conversations are studied. The domains, as well as the degree of familiarity between interlocutors are dimensions that …

Content truncated to 500 words