Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
This addresses the need for companies to identify potentially churning users in chatbot interactions, though it is incremental by extending existing social media methods to chatbots and adding multilingual data.
The paper tackles the problem of detecting user churn intent in multilingual chatbot conversations and social media, showing that classifiers trained on social media data can detect churn intent in chatbots and that a bilingual approach outperforms monolingual methods.
We propose a new method to detect when users express the intent to leave a service, also known as churn. While previous work focuses solely on social media, we show that this intent can be detected in chatbot conversations. As companies increasingly rely on chatbots they need an overview of potentially churny users. To this end, we crowdsource and publish a dataset of churn intent expressions in chatbot interactions in German and English. We show that classifiers trained on social media data can detect the same intent in the context of chatbots. We introduce a classification architecture that outperforms existing work on churn intent detection in social media. Moreover, we show that, using bilingual word embeddings, a system trained on combined English and German data outperforms monolingual approaches. As the only existing dataset is in English, we crowdsource and publish a novel dataset of German tweets. We thus underline the universal aspect of the problem, as examples of churn intent in English help us identify churn in German tweets and chatbot conversations.