Topic
Chatbot
About: Chatbot is a research topic. Over the lifetime, 2415 publications have been published within this topic receiving 24372 citations. The topic is also known as: IM bot & AI chatbot.
Papers published on a yearly basis
Papers
More filters
23 Jan 2020
TL;DR: 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.
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.
12 citations
01 Mar 2018
TL;DR: Users were shown to rate their relationships with the banking chatbot as more helpful and self-validating when they communicate with it by a voice- input modality than by a text-input modality.
Abstract: The use of chatbots is more common in our everyday lives than ever before. However, few studies have been conducted comparing the differences between text- and voice-input modalities of chatbots in the banking industry. In this study, through empirical and survey-based research, users were shown to rate their relationships with the banking chatbot as more helpful and self-validating when they communicate with it by a voice-input modality than by a text-input modality.
12 citations
01 Jan 2018
TL;DR: This chapter provides UX designers with some of the linguistic resources necessary to build more engaging chatbots and virtual agents and applies linguistic research as a design tool for creating conversational interfaces that have style and strategically align to users’ needs according to the social goal at hand.
Abstract: This chapter provides UX designers with some of the linguistic resources necessary to build more engaging chatbots and virtual agents. Conversation Analysis teaches us the foundational mechanics of conversation—how participants initiate and terminate an interaction, how they take turns in talk, how they negotiate understanding, etc. Interactional Sociolinguistics and the study of conversational style show us how humans leverage these structures to convey style and accomplish social goals in talk, such as building rapport or showing respect. If Conversation Analysis is the key to designing conversation that flows, Interactional Sociolinguistics and conversational style are the keys to designing conversation that has what some might call personality. Here, linguistic research is applied as a design tool for creating conversational interfaces that have style and strategically align to users’ needs according to the social goal at hand. If designers seek to make a chatbot enthusiastic or considerate, this chapter has the tools needed to design conversations that achieve that with users.
12 citations
21 Sep 2021
TL;DR: In this paper, the authors present a chatbot that engages in dialogues with users who do not want to get vaccinated, with the goal to persuade them to change their stance and get a vaccine.
Abstract: Chatbots have the potential of being used as dialogical argumentation systems for behaviour change applications. They thereby offer a cost-effective and scalable alternative to in-person consultations with health professionals that users could engage in from the comfort of their own home. During events like the global COVID-19 pandemic, it is even more important than usual that people are well informed and make conscious decisions that benefit themselves. Getting a COVID-19 vaccine is a prime example of a behaviour that benefits the individual, as well as society as a whole. In this paper, we present a chatbot that engages in dialogues with users who do not want to get vaccinated, with the goal to persuade them to change their stance and get a vaccine. The chatbot is equipped with a small repository of arguments that it uses to counter user arguments on why the user is reluctant to get a vaccine. We evaluate our chatbot in a study with participants.
12 citations
TL;DR: A review of the literature on Arabic chatbots is presented in this article , where the authors search eight bibliographic databases and conduct backward and forward reference checking to identify relevant studies, and two reviewers independently performed study selection and data extraction.
Abstract: Chatbots have been widely used in many spheres of life from customer services to mental health companions. Despite the breakthroughs in achieving human-like conversations, Arabic language chatbots driven by AI and NLP are relatively scarce due to the complex nature of the Arabic language. We aim to review published literature on Arabic chatbots to gain insight into the technologies used highlighting the gap in this emerging field. To identify relevant studies, we searched eight bibliographic databases and conducted backward and forward reference checking. Two reviewers independently performed study selection and data extraction. The extracted data was synthesized using a narrative approach. We included 18 of 1755 retrieved publications. Thirteen unique chatbots were identified from the 18 studies. ArabChat was the most common chatbot in the included studies (n=5). The type of Arabic language in most chatbots (n=13) was Modern Standard Arabic. The input and output modalities used in 17 chatbots were only text. Most chatbots (n=14) were able to have long conversations. The majority of the chatbots (n=14) were developed to serve a specific purpose (Closed domain). A retrieval-based model was used for developing most chatbots (n=17). Despite a large number of chatbots worldwide, there is relatively a small number of Arabic language chatbots. Furthermore, the available Arabic language chatbots are less advanced than other language chatbots. Researchers should develop more Arabic language chatbots that are based on more advanced input and output modalities, generative-based models, and natural language processing (NLP).
12 citations