Chatbots in Museums: This article explores how chatbots can offer opportunities for Museums and Institutes in engaging their audiences through recent developments.
Chatbot in the museum and institutes develops a practicable technical solution for the use of chatbots in the museum and institute environment.
The paper outlines conceptual work conducted so far, including the comprehension of some important research topics explored in chatbot in the museum and institutes.
Introduction – Chatbots in Museums
A chatbot is a computer program that attempts to simulate the conversation of a human being via text or voice interactions. In the museum, context chatbots offer great potential, as existing “pain points” can be eliminated: in contrast to personal tours (“takes place in an hour”, “is canceled today”), chatbots are always available.
Today’s digital visitor guidance systems offer only “oneway communication” and are not able to respond to questions from the visitor. Chatbots have the potential to respond meaningfully to the user’s input if the input is processed properly.
Chatbot in the Museum – Chatbots in Museums
Conversations with museum visitors showed that they often have specific questions about certain objects. Classical audioguides can not answer specific questions. In the museum, a chatbot could be the expert you can take with you, answer questions, and provide further information.
Chim aims to explore the usability of a chatbot as an interactive system for knowledge and learning, as well as for effective access and the comprehensible presentation of museum information.
A central question is therefore how the existing information must be structured to relate to the visitors’ questions.
Chim develops new solutions for providing information and explores how the latest research results in the field of intention detection and dialog management can be utilized for chatbots in the museum context. Specifically, the following research fields of human-technology interaction are to be investigated:
2. Related Work
Current research in the field of interactive museum guides covers a wide range of approaches, from beacons controlling the presentation, over agent-based techniques, to robotic museum guides.
In the museum field, still, no elaborate technologies can be found that essentially utilize conversational digital systems such as chatbots.
Providers such as helloguide3 so far only carry over the paradigm of entering numbers from a classical audio guide to chatbots. It is not possible to engage in dialog or ask questions with such museum chatbots.
Chatbot/dialog platforms such as Alexa (Amazon), Dialogflow (Google), Wit.ai (Facebook), or Watson (IBM) enable intention detection for many domains (eg. for ordering a pizza, weather report, flight booking, shopping, etc.).
However, most of these platforms only offer limited customization to their domains and are limited in the choice of input and output modalities. Also, they are not able to manage a dialog with extensive knowledge bases.
Therefore, for special domains such as a tour through an exhibition, own solutions for intent detection and dialog management have to be implemented. In many conversational systems, domain-specific knowledge is mapped by dialog grammars and state machines.
3. The Chim approach
Chim investigates hybrid methods for intention detection and dialog management for the museum sector. A newly developed chatbot-based museum guide usually represents a new knowledge domain for which training data is not yet available.
During the process of creating audio and multimedia guides, many data are generated, which can also be used as training data if appropriate transcription and indexing methods are applied.
Chim’s approach is to combine the development of a hybrid approach for intention detection and dialog management with the creation process of museum tours, using the data generated by authors and editors as training material for a statistical model.
4. Dialog management for museum tours
The individual steps from intention detection over the retrieval of the information to the provision of information are continuously carried out in a dialog between the user and the chatbot.
As the core of the chatbot, intelligent dialog management will process the multimodal intention and determine the system reaction to offer personalized information. The dialog should always be effective, intuitive, and continued with the best possible user experience.
The input/output modalities will be adapted to the situation using text, speech, or multimedia elements. More specifically, the information presented to the users is decided from the intention, the dialog history, the knowledge model from the information processing, and the general context.
The processing of the dialog management will be hybrid: from historical data typical museum guide sequences are learned. At the same time, dialog rules will be created and the two approaches combined.
5. Conclusion and Future Work
The development of a practical technical solution for the use of chatbots in the museum environment represents a challenging task: the editing process for audio and media guides is a highly specialized process, and the extension to knowledge-based approaches for the realization of a chatbot for museums has to be carried out.
The interplay of existing approaches for intention detection and dialog management opens up several research questions, including how chatbots can be used in complex environments such as museums.
Chatbots in Institutes
Chatbots are getting a ubiquitous trend in many fields like medicine, the product and repair industry, and education. Chatbots are computer programs wont to conduct auditory or textual conversations.
In recent decades, the number of students per lecturer has constantly risen. Large-scale lectures at universities with more than 100 students per lecturer and massive open online courses are increasingly becoming the default learning scenario.
Consequently, individualized support provided by lecturers is nearly impossible and students are unable to engage in effective learning.
Several studies have revealed that this lack of individualized support leads to weak learning outcomes, high drop out rates, and dissatisfaction. The best solution would be to possess one teacher per student. Obviously,
this is not possible due to financial and organizational restrictions.
what Google’s vision for an AI?
The first institution looks like we’ll talk most of the time you’ll be hearing from people just like yourselves at institutions who have implemented some of this technology and what that was like what that experience was like for them and in some of these cases that came out of that and potentially even some of the roadmap opportunities that exist for those institutions.
So, I think a lot of us here know that the path for a student from a perspective to employed professional is not one step and so, Google took this to heart and we think of it and translate it into a student life cycle.
what that mean is? there are so many places along a student journey that we can interject with technology.
– Dialog Flow
Dialog flow is the agent that enables this very simple dialogue flow is a conversation building tool and it does so in a very powerful way by using natural language process saying to take the way that a student or a professor or a teacher or someone would speak naturally and translate that into something that you might have heard before called intense and you can think of that by imagining all the different ways that someone might ask about the weather so you know you can say:
- how hot is it today?
- will it rain today?
- what’s the temperature going to be this week?
and traditionally it may have been very rigid and difficult for people to interact with an agent because it required a very specific input and it’s also very difficult for developers to create that agent by hard coding very rigid language in context into that agent and so what dialogue flow does is remove that meaning that your user, your student, your staff, a member can interact the way that we talk very naturally.
And all of the natural language processing that is built into dialogue flow translates that for you into something actionable in your body.
Chatbots have a growing presence in modern society
Becoming integral parts of everything from personal assistants on mobile devices to technical support help over telephone lines, and even getting used for health interventions. In 2016, it is estimated that about 75% of all smartphone users used some sort of messaging apps.
Moreover, analysts predict that by 2020, 30% of all web browsing sessions will be done without a screen, 50% of all searches will be by voice commands, and customers will manage 85% of their enterprise relationships without interacting with a person’s being.
Benefits of chatbots in general education
chatbots can play a serious role in management education also. Several managerial competency frameworks suggest that creating judgments and decisions, providing and receiving feedback, analytical thinking and technological awareness are crucial competencies for future managers.
Chatbots can help to develop each of these skills. Firstly, chatbots can deliver future managers the right information at the right time to make the right judgments and decisions. Secondly, chatbots are promising tools to provide continuous feedback to lecturers and students.
Thirdly, using chatbots as learning partners improve the power of scholars to gather and analyze relevant data by empowering students to research a drag first then getting the knowledge quickly. Last but not least, future managers get trained to figure hand in hand with digital assistants, which becomes standard in future management activities.
We focused on outcomes of chatbot research studies and their underlying theories and practical applications because the main goal of the review is to point out the potential of chatbots for increasing learning outcomes.