Towards implementing an AI chatbot platform for museums

Abstract

Recently, understanding their unique role in storytelling and aiming to attract more visitors, several museums have integrated modern ICT technologies. The problem with these technologies however is that gradually tend to be of no real interest to visitors, lack of significant interaction, cannot be continuously updated, and eventually distract visitors from experiencing the exhibits. Museum visitors do not need to be impressed by a technological application but need to learn about the stories of the exhibits in a creative, human-centered and interactive manner. This paper presents an ongoing work towards implementing a new interactive technological trend for museums, i.e., a museum chatbot platform, namely MuBot. The MuBot platform aims to provide museums the opportunity to create simple, interactive and human-friendly apps for their visitors. Such apps will integrate an intelligent chatbot that uses some of the most advanced AI technologies of Machine Learning, Natural Language Processing/Generation, and the Semantic Web. Museum visitors will be able to use a chatbot application that will be created through the MuBot platform, to chat with a ‘smart’ exhibit. They will be able to ask questions through text or voice (in natural language) and receive audible or written answers. The more the visitors ask, the more MuBot will learn and store new knowledge in its knowledge base. The paper presents a preliminary design of the proposed MuBot platform, experimenting with first prototype implementations using the well-known Dialogflow framework, as well as using a Knowledge Graph-based approach.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 36 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.