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
••
01 Jun 2019TL;DR: A unified framework for human evaluation of chatbots that augments existing tools and provides a web-based hub for researchers to share and compare their dialog systems and open-source baseline models and evaluation datasets are introduced.
Abstract: Open-domain dialog systems (i.e. chatbots) are difficult to evaluate. The current best practice for analyzing and comparing these dialog systems is the use of human judgments. However, the lack of standardization in evaluation procedures, and the fact that model parameters and code are rarely published hinder systematic human evaluation experiments. We introduce a unified framework for human evaluation of chatbots that augments existing tools and provides a web-based hub for researchers to share and compare their dialog systems. Researchers can submit their trained models to the ChatEval web interface and obtain comparisons with baselines and prior work. The evaluation code is open-source to ensure standardization and transparency. In addition, we introduce open-source baseline models and evaluation datasets. ChatEval can be found at https://chateval.org.
55 citations
••
07 Nov 2019TL;DR: This work prototyped their chatbot as an interactive question-answering application and analyzed users’ interaction patterns, perceptions, and contexts of use to understand the potential of chatbots for breastfeeding education by conducting an Wizard-of-Oz experiment.
Abstract: Use of chatbots in different spheres of life is continuously increasing since a couple of years. We attempt to understand the potential of chatbots for breastfeeding education by conducting an Wizard-of-Oz experiment with 22 participants. Our participants included breastfeeding mothers and community health workers from the slum areas of Delhi, India. We prototyped our chatbot as an interactive question-answering application and analyzed users' interaction patterns, perceptions, and contexts of use. The chatbot use cases emerged primarily as the first line of support. The participants, especially the mothers, were enthusiastic with the opportunity to ask questions and get reliable answers. We also observed the influencing role of female relative, e.g. mothers-in-law, in breastfeeding practices. Our analysis of user information-seeking suggests that a majority of questions (88%) are of nature that can be answered by a chatbot application. We further observe that the queries are embedded deeply into myths and existing belief systems. Therefore requiring the designers to focus on subtle aspects for providing information such as positive reinforcement and contextual sensitivity. Further, we discuss, different societal and ethical issues associated with Chatbot usage for a public health topic such as breastfeeding education.
55 citations
••
TL;DR: In this article, the authors investigated the effect of different service scripts presented during chatbot service encounters and found that when employing an education script, a significant positive effect occurs for human service agents (compared to chatbots) in terms of both satisfaction and purchase intention.
Abstract: Brands are increasingly considering the use of chatbots to supplement, or even replace, humans in service interactions. Like humans, chatbots can follow certain service scripts in their encounters, which can subsequently determine the customer experience. Service scripts are verbal prescriptions that seek to standardize customer service interactions. However, while the role of service scripts is well documented, despite the increasing use of chatbots as a service mechanism, less is known about the effect, on consumers, of different service scripts presented during chatbot service encounters.,An experimental scenario was developed to test the research hypotheses. Respondents were randomly allocated to scenarios representing a 2 (service interaction: human, chatbot) × 2 (service script: education, entertainment) design. A total of 262 US consumers constituted the final sample for the study.,The findings indicate that when employing an education script, a significant positive effect occurs for human service agents (compared to chatbots) in terms of both satisfaction and purchase intention. These effects are fully mediated by emotion and rapport, showing that the bonds developed through the close proximity to a human service agent elicit emotion and develop rapport, which in turn influence service outcomes. However, this result is present only when an educational script is used.,This paper contributes to the emerging service marketing literature on the use of digital services, in particular chatbots, in service interactions. We show that differences occur in key outcomes dependent on the type of service script employed (education or entertainment). For managers, this study indicates that chatbot interactions can be tailored (in script delivered) in order to maximize emotion and rapport and subsequently consumer purchase intention and satisfaction.
55 citations
••
TL;DR: A pilot at the University of Nebraska‐Lincoln for a chatbot that answers questions about the library and library resources using artificial intelligence mark‐up language metadata and a SQL database to store the question and answers.
Abstract: Purpose – This paper aims to describe a pilot at the University of Nebraska‐Lincoln for a chatbot that answers questions about the library and library resources.Design/methodology/approach – The chatbot was developed using a SQL database to store the question and answers using artificial intelligence mark‐up language metadata. The user interface was built using PHP, adapted from Program‐O. The open source PHP program was modified to support better display and the launching of URLs within the chatbot screen. Database content was created by “mining” library websites for information, and analyzing chat logs.Findings – The chatbot answers questions from a variety of users from around the world. It has attracted an unexpected number of social chatters, which required some additional metadata to accommodate personal chatting and to guide questions back to the intent of the project. The majority of questions are directional or factual questions that Pixel can handle. The database proved to be practical to build ...
55 citations
••
01 Jan 2018TL;DR: An implementation of an intelligent chatbot system in travel domain on Echo platform which would gather user preferences and model collective user knowledge base and recommend using the Restricted Boltzmann Machine (RBM) with Collaborative Filtering.
Abstract: Chatbot is a computer application that interacts with users using natural language in a similar way to imitate a human travel agent. A successful implementation of a chatbot system can analyze user preferences and predict collective intelligence. In most cases, it can provide better user-centric recommendations. Hence, the chatbot is becoming an integral part of the future consumer services. This paper is an implementation of an intelligent chatbot system in travel domain on Echo platform which would gather user preferences and model collective user knowledge base and recommend using the Restricted Boltzmann Machine (RBM) with Collaborative Filtering. With this chatbot based on DNN, we can improve human to machine interaction in the travel domain.
55 citations