Title:	Towards an understanding of knowledge bases of chatbot systems
Authors:	Hausdorf, Alrik Müller, Lydia Scheuermann, Gerik Niekler, Andreas Wiegreffe, Daniel
Citation:	WSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 76-85.
Issue Date:	2022
Publisher:	Václav Skala - UNION Agency
Document type:	conferenceObject
URI:	http://hdl.handle.net/11025/49581
ISBN:	978-80-86943-33-6
ISSN:	2464-4617
Keywords:	aplikace motivovaná vizualizace;chatbot;znalostní báze chatbotů;údržba chatbota;rozhodovací strom
Keywords in different language:	application motivated visualization;chatbot;chatbot knowledge base;chatbot maintenance;decision tree
Abstract in different language:	A chatbot can automatically process a user’s request, e.g. to provide a requested information. In doing so, the user starts a conversation with the chatbot and can specify the request by further inquiry. Due to the developments in the field of NLP in recent years, algorithmic text comprehension has been significantly improved. As a result, chatbots are increasingly used by companies and other institutions for various tasks such as order processes or service requests. Knowledge bases are often used to answer users queries, but these are usually curated manually in various text files, prone to errors. Visual methods can help the expert to identify common problems in the knowledge base and can provide an overview of the chatbot system. In this paper, we present Chatbot Explorer, a system to visually assist the expert to understand, explore, and manage a knowledge base of different chatbot systems. For this purpose, we provide a tree-based visualization of the knowledge base as an overview. For a detailed analysis, the expert can use appropriate visualizations to drill down the analysis to the level of individual elements of a specific story to identify problems within the knowledge base. We support the expert with automatic detection of possible problems, which can be visually highlighted. Additionally, the expert can also change the order of the queries to optimize the conversation lengths and it is possible to add new content. To develop our solution, we have conducted an iterative design process with domain experts and performed two user evaluations. The evaluations and the feedback from our domain experts have shown that our solution can significantly improve the maintainability of chatbot knowledge bases.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	WSCG 2022: Full Papers Proceedings

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.