KIT | KIT-Bibliothek | Impressum | Datenschutz

Conversation Mining for Customer Service Chatbots

Schloß, Daniel ORCID iD icon 1; Gnewuch, Ulrich 1
1 Institut für Wirtschaftsinformatik und Marketing (IISM), Karlsruher Institut für Technologie (KIT)


More and more companies are using chatbots in customer service. The large number of chatbots and their interactions with customers produce a huge amount of data, which is useful to track the usage and performance of the chatbot. However, many established performance metrics (e.g., intent scores, conversa-tions per day) could be considered too intuitive to be helpful and are either at a very high level or at the level of single question-answer pairs. Our research aims to address this challenge by presenting a novel approach and system for conver-sation analysis of customer service chatbots. More specifically, we extend estab-lished metrics and concepts with ideas from process mining since every conver-sation with customer service chatbots can be interpreted as a sequence of discrete steps. This paper presents the methodological foundations for our approach, which we call conversation mining, and demonstrates its potential with first in-sights into our prototype. Ultimately, we aim to draw the attention of chatbot researchers and practitioners to the value of conversation data by describing a novel approach for automatically processing and analyzing at a process level.

Verlagsausgabe §
DOI: 10.5445/IR/1000156162
Veröffentlicht am 21.02.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Wirtschaftsinformatik und Marketing (IISM)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator KITopen-ID: 1000156162
Erschienen in 6th International Workshop, CONVERSATIONS 2022, Amsterdam, The Netherlands, November 22–23, 2022
Veranstaltung 6th International Workshop on Chatbot Research, Applications and Design (2022 2022), Amsterdam, Niederlande, 22.11.2022 – 23.11.2022
Bemerkung zur Veröffentlichung position paper
Schlagwörter Chatbots, Customer Service, Data Analytics, Conversation Mining
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page