Art-bots: Toward Chat-based Conversational Experiences in Museums

The pilot aimed to find new and interesting ways to engage teenagers in visiting these museums through visualising narrative using a convergence of chatbot technology and gamification.

This paper explores how chatbots can offer opportunities for museums and galleries in engaging their audiences through recent developments, and through a case study approach focusing on the design and implementation of an audience development pilot in Milan involving four historic house museums (Case Museo di Milano). The pilot aimed to find new and interesting ways to engage teenagers in visiting these museums through visualising narrative using a convergence of chatbot technology and gamification.

2018

Interactivity in museums and art exhibitions is a relevant topic since museums face issues related to representation, participation, and education to the most diverse publics. Visitors cannot be perceived anymore as passive recipients of knowledge, but as active actors engaged in the process of interpretation and signification. In this scenario, there is an invisible gap between visitors and collections in terms of engagement and information in museums, what opens opportunities in terms of technology adoption in an attempt to compensate understanding and exploration of collections This research paper has the aim to discuss the relations of text-image and artworks in museums as well as the role of technologies in the relationship between visitors and collection, with special focus on chatbots. Based on a discussion involving concepts such as the aura, as defined by Walter Benjamin, anchorage, as defined by Roland Barthes, Umberto Eco's double coding and levels of reading, and museum ways communicate within exhibitions, a reflection is made about technology adoption in museums and the way technology should enhance the visitor experience. Examples of interactive technologies adopted in specific exhibitions or included in the entire museum experience are exemplified, and in combination with the discussion of text-image and technology, an exhibition at the National Gallery of Ireland was chosen as the case study to suggest an approach for chatbot adoption in museums. The relevance of this study relies on the fact that the discussion concerns technology adoption not only as means of entertainment and interactivity but mainly as a tool to highlight the collection and enhance interpretation.

Museums and Digital Culture, Springer Series on Cultural Computing, 2019

This chapter explores the application of artificial intelligence (AI) in museums and galleries in engaging their audiences, specifically through the development and use of chatbot technologies. Through a case study approach, the chapter further provides a practical focus on the design and implementation of an audience development pilot in Milan involving four historic house museums (Case Museo di Milano). The pilot aimed to find new and interesting ways to engage teenagers in visiting these museums through visualizing narrative using a convergence of chatbot and gamification platforms.

Chatbots have caught the headlines recently with businesses starting to adopt them to stimulate conversation with customers. But what are chatbots? How do they work? What can they do for museums and their audiences?

2020

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.

2020

This work addresses the challenges of creating usable and personalized conversational interfaces for broad, yet applicable, domains that require user engagement and learning, such as museum chatbots. Whether the chatbots are standalone or coupled with virtual agents or real-life robots, the functional requirements for interaction that targets specific learning aspects would be expected to be more or less similar. This work reports on experimental semantics-driven conversational interface design for chatbots in museum settings, targeting visitors to converse about exhibits and learn information about their style, the artists, the era, and other aspects related to them. Depending on the semantics (presentation, learning, exploration), chatbot scenarios were designed and evaluated by participants in a formative evaluation. The evaluation show that user requirement perception manifests in expectations on the semantic level, instead of just the technical level. The results between the sc...

Statistics about social media usage show that instant messaging apps are increasingly popular (Kemp 2016). So far only a few museums use instant messaging to get in touch with their public, actual and potential. In 2014 and 2016 for example the Horniman Museum in South London experimented using WhatsApp to communicate with their visitors (Murphy 2016), while the Brooklyn Museum launched in 2015 a proprietary chat app called ASK with a dedicated answering team (Simon 2015). Even if completely different in scale, both experiments share the same goal: to provide real-time answers by human staff to visitors’ questions about the museums and the collections.

Culture and Computing. HCII 2020., Rauterberg M., vol. 12215, Copenhagen, Springer International Publishing, 2020

The paper presents recent work on the design and development of AI chatbots for museums using Knowledge Graphs (KGs). The utilization of KGs as a key technology for implementing chatbots raises not only issues related to the representation and structuring of exhibits' knowledge in suitable formalism and models, but also issues related to the translation of natural language dialogues to and from the selected technology for the formal representation and structuring of information and knowledge. Moreover, such a translation must be as transparent as possible to visitors, towards a realistic human-like question-answering process. The paper reviews and evaluates a number of recent approaches for the use of KGs in developing AI chatbots, as well as key tools that provide solutions for natural language translation and the querying of Knowledge Bases and Linked Open Data sources. This evaluation aims to provide answers to issues that are identified within the proposed MuBot approach for designing and implementing AI chatbots for museums. The paper also presents Cretan MuBot, the first experimental KG/Ontology-based AI chatbot of the MuBot Platform, which is under development in the Heracleum Archaeological Museum.

2006

The use of a PDA with ad-hoc built-in information retrieval functionalities can help people in visiting an historical site in a natural manner instead of traditional audio/visual pre-recorded guides. The aim of this work is to build a versatile virtual-guide system adaptable to the user needs of mobility and therefore usable on different devices (e.g. PDAs, Smartphones). An information retrieval service is included and is easily accessible through a spoken language interaction. The system takes the advantages of chat-bot and speech recognition technologies, allowing a natural interaction with the user. The system has been implemented on a Qtek PDA with Windows Mobile 2003 with the aim of assisting an user during a visit to a cultural heritage institution.