Showing papers on "Chatbot published in 2018"

From Eliza to XiaoIce: challenges and opportunities with social chatbots

Abstract: Conversational systems have come a long way since their inception in the 1960s. After decades of research and development, we have seen progress from Eliza and Parry in the 1960s and 1970s, to task-completion systems as in the Defense Advanced Research Projects Agency (DARPA) communicator program in the 2000s, to intelligent personal assistants such as Siri, in the 2010s, to today’s social chatbots like XiaoIce. Social chatbots’ appeal lies not only in their ability to respond to users’ diverse requests, but also in being able to establish an emotional connection with users. The latter is done by satisfying users’ need for communication, affection, as well as social belonging. To further the advancement and adoption of social chatbots, their design must focus on user engagement and take both intellectual quotient (IQ) and emotional quotient (EQ) into account. Users should want to engage with a social chatbot; as such, we define the success metric for social chatbots as conversation-turns per session (CPS). Using XiaoIce as an illustrative example, we discuss key technologies in building social chatbots from core chat to visual awareness to skills. We also show how XiaoIce can dynamically recognize emotion and engage the user throughout long conversations with appropriate interpersonal responses. As we become the first generation of humans ever living with artificial intelligenc (AI), we have a responsibility to design social chatbots to be both useful and empathetic, so they will become ubiquitous and help society as a whole.

Neural Approaches to Conversational AI

Abstract: This tutorial surveys neural approaches to conversational AI that were developed in the last few years. We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) social bots. For each category, we present a review of state-of-the-art neural approaches, draw the connection between neural approaches and traditional symbolic approaches, and discuss the progress we have made and challenges we are facing, using specific systems and models as case studies.

From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots

Abstract: Conversational systems have come a long way since their inception in the 1960s. After decades of research and development, we've seen progress from Eliza and Parry in the 60's and 70's, to task-completion systems as in the DARPA Communicator program in the 2000s, to intelligent personal assistants such as Siri in the 2010s, to today's social chatbots like XiaoIce. Social chatbots' appeal lies not only in their ability to respond to users' diverse requests, but also in being able to establish an emotional connection with users. The latter is done by satisfying users' need for communication, affection, as well as social belonging. To further the advancement and adoption of social chatbots, their design must focus on user engagement and take both intellectual quotient (IQ) and emotional quotient (EQ) into account. Users should want to engage with a social chatbot; as such, we define the success metric for social chatbots as conversation-turns per session (CPS). Using XiaoIce as an illustrative example, we discuss key technologies in building social chatbots from core chat to visual awareness to skills. We also show how XiaoIce can dynamically recognize emotion and engage the user throughout long conversations with appropriate interpersonal responses. As we become the first generation of humans ever living with AI, we have a responsibility to design social chatbots to be both useful and empathetic, so they will become ubiquitous and help society as a whole.

Psychological, Relational, and Emotional Effects of Self-Disclosure After Conversations With a Chatbot.

Abstract: Disclosing personal information to another person has beneficial emotional, relational, and psychological outcomes. When disclosers believe they are interacting with a computer instead of another person, such as a chatbot that can simulate human-to-human conversation, outcomes may be undermined, enhanced, or equivalent. Our experiment examined downstream effects after emotional versus factual disclosures in conversations with a supposed chatbot or person. The effects of emotional disclosure were equivalent whether participants thought they were disclosing to a chatbot or to a person. This study advances current understanding of disclosure and whether its impact is altered by technology, providing support for media equivalency as a primary mechanism for the consequences of disclosing to a chatbot.

Evaluating and Informing the Design of Chatbots

Abstract: Text messaging-based conversational agents (CAs), popularly called chatbots, received significant attention in the last two years. However, chatbots are still in their nascent stage: They have a low penetration rate as 84% of the Internet users have not used a chatbot yet. Hence, understanding the usage patterns of first-time users can potentially inform and guide the design of future chatbots. In this paper, we report the findings of a study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform. Analysis of chat logs and user interviews revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface. We conclude with implications to evolve the design of chatbots, such as: clarify chatbot capabilities, sustain conversation context, handle dialog failures, and end conversations gracefully.

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Abstract: This paper describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient (IQ) and emotional quotient (EQ) in system design, cast human-machine social chat as decision-making over Markov Decision Processes (MDPs), and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key components including dialogue manager, core chat, skills, and an empathetic computing module. We show how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations. Since her launch in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them. Analysis of large scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.

Should Machines Express Sympathy and Empathy? Experiments with a Health Advice Chatbot

Abstract: When we ask a chatbot for advice about a personal problem, should it simply provide informational support and refrain from offering emotional support? Or, should it show sympathy and empat...

What Makes Users Trust a Chatbot for Customer Service? An Exploratory Interview Study

Abstract: Chatbots are increasingly offered as an alternative source of customer service. For users to take up chatbots for this purpose, it is important that users trust chatbots to provide the required support. However, there is currently a lack in knowledge regarding the factors that affect users’ trust in chatbots. We present an interview study addressing this knowledge gap. Thirteen users of chatbots for customer service were interviewed regarding their experience with the chatbots and factors affecting their trust in these. Users’ trust in chatbots for customer service was found to be affected (a) by factors concerning the specific chatbot, specifically the quality of its interpretation of requests and advise, its human-likeness, its self-presentation, and its professional appearance, but also (b) by factors concerning the service context, specifically the brand of the chatbot host, the perceived security and privacy in the chatbot, as well as general risk perceptions concerning the topic of the request. Implications for the design and development of chatbots and directions for future work are suggested.

A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks

Abstract: Nowadays it is the era of intelligent machine. With the advancement of artificial intelligent, machine learning and deep learning, machines have started to impersonate as human. Conversational software agents activated by natural language processing is known as chatbot, are an excellent example of such machine. This paper presents a survey on existing chatbots and techniques applied into it. It discusses the similarities, differences and limitations of the existing chatbots. We compared 11 most popular chatbot application systems along with functionalities and technical specifications. Research showed that nearly 75% of customers have experienced poor customer service and generation of meaningful, long and informative responses remains a challenging task. In the past, methods for developing chatbots have relied on hand-written rules and templates. With the rise of deep learning these models were quickly replaced by end-to-end neural networks. More specifically, Deep Neural Networks is a powerful generative-based model to solve the conversational response generation problems. This paper conducted an in-depth survey of recent literature, examining over 70 publications related to chatbots published in the last 5 years. Based on literature review, this study made a comparison from selected papers according to method adopted. This paper also presented why current chatbot models fails to take into account when generating responses and how this affects the quality conversation.

Chatbot: An Education Support System for Student

Abstract: In the last few years there has been a fast growing up of the use of Chatbots in various fields, such as Health Care, Marketing, Educational, Supporting Systems, Cultural Heritage, Entertainment and many others. This paper presents the realization of a prototype of a Chatbot in educational domain: the purpose has focused on the design of the specific architecture, model to manage communication and furnish the right answers to the student. For this aim, it has been realized a system that can detect the questions and thanks to the use of natural language processing techniques and the ontologies of domain, gives the answers to student. Finally, after the implementation of the designed model, experimental campaign was conducted in order to demonstrate its utility.

Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media

Abstract: Chatbot has become an important solution to rapidly increasing customer care demands on social media in recent years. However, current work on chatbot for customer care ignores a key to impact user experience - tones. In this work, we create a novel tone-aware chatbot that generates toned responses to user requests on social media. We first conduct a formative research, in which the effects of tones are studied. Significant and various influences of different tones on user experience are uncovered in the study. With the knowledge of effects of tones, we design a deep learning based chatbot that takes tone information into account. We train our system on over 1.5 million real customer care conversations collected from Twitter. The evaluation reveals that our tone-aware chatbot generates as appropriate responses to user requests as human agents. More importantly, our chatbot is perceived to be even more empathetic than human agents.

Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce

Abstract: Nowadays, it is a heated topic for many industries to build automatic question-answering (QA) systems. A key solution to these QA systems is to retrieve from a QA knowledge base the most similar question of a given question, which can be reformulated as a paraphrase identification (PI) or a natural language inference (NLI) problem. However, most existing models for PI and NLI have at least two problems: They rely on a large amount of labeled data, which is not always available in real scenarios, and they may not be efficient for industrial applications. In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource-poor target domain. Specifically, since most existing transfer learning methods only focus on learning a shared feature space across domains while ignoring the relationship between the source and target domains, we propose to simultaneously learn shared representations and domain relationships in a unified framework. Furthermore, we propose an efficient and effective hybrid model by combining a sentence encoding-based method and a sentence interaction-based method as our base model. Extensive experiments on both paraphrase identification and natural language inference demonstrate that our base model is efficient and has promising performance compared to the competing models, and our transfer learning method can help to significantly boost the performance. Further analysis shows that the inter-domain and intra-domain relationship captured by our model are insightful. Last but not least, we deploy our transfer learning model for PI into our online chatbot system, which can bring in significant improvements over our existing system. Finally, we launch our new system on the chatbot platform Eva in our E-commerce site AliExpress.

Faster is Not Always Better: Understanding the Effect of Dynamic Response Delays in Human-Chatbot Interaction

Abstract: A key challenge in designing conversational user interfaces is to make the conversation between the user and the system feel natural and human-like. In order to increase perceived humanness, many systems with conversational user interfaces (e.g., chatbots) use response delays to simu-late the time it would take humans to respond to a message. However, delayed responses may also negatively impact user satisfaction, particularly in situations where fast response times are expected, such as in customer service. This paper reports the findings of an online experiment in a customer service context that investigates how user perceptions differ when interacting with a chatbot that sends dynamically delayed responses compared to a chatbot that sends near-instant responses. The dynamic delay length was calculated based on the complexity of the re-sponse and complexity of the previous message. Our results indicate that dynamic response de-lays not only increase users’ perception of humanness and social presence, but also lead to greater satisfaction with the overall chatbot interaction. Building on social response theory, we provide evidence that a chatbot’s response time represents a social cue that triggers social re-sponses shaped by social expectations. Our findings support researchers and practitioners in understanding and designing more natural human-chatbot interactions.

Understanding Chatbot-mediated Task Management

Abstract: Effective task management is essential to successful team collaboration. While the past decade has seen considerable innovation in systems that track and manage group tasks, these innovations have typically been outside of the principal communication channels: email, instant messenger, and group chat. Teams formulate, discuss, refine, assign, and track the progress of their collaborative tasks over electronic communication channels, yet they must leave these channels to update their task-tracking tools, creating a source of friction and inefficiency. To address this problem, we explore how bots might be used to mediate task management for individuals and teams. We deploy a prototype bot to eight different teams of information workers to help them create, assign, and keep track of tasks, all within their main communication channel. We derived seven insights for the design of future bots for coordinating work.

Intelligent Assistants in Higher-Education Environments: The FIT-EBot, a Chatbot for Administrative and Learning Support

Abstract: The purpose of this paper is to discuss about smart learning environments and present the FIT-EBot, a chatbot, which automatically gives a reply to a question of students about the services provided by the education system on behalf of the academic staff. The chatbot can play the role of an intelligent assistant, which provides solutions for higher-education institutions to improve their current services, to reduce labor costs, and to create new innovative services. Various artificial intelligence techniques such as text classification, named entity recognition are used in this work to enhance the system performance.

All Work and No Play

Abstract: Many conversational agents (CAs) are developed to answer users' questions in a specialized domain. In everyday use of CAs, user experience may extend beyond satisfying information needs to the enjoyment of conversations with CAs, some of which represent playful interactions. By studying a field deployment of a Human Resource chatbot, we report on users' interest areas in conversational interactions to inform the development of CAs. Through the lens of statistical modeling, we also highlight rich signals in conversational interactions for inferring user satisfaction with the instrumental usage and playful interactions with the agent. These signals can be utilized to develop agents that adapt functionality and interaction styles. By contrasting these signals, we shed light on the varying functions of conversational interactions. We discuss design implications for CAs, and directions for developing adaptive agents based on users' conversational behaviors.

Single or Multiple Conversational Agents?: An Interactional Coherence Comparison

Abstract: Chatbots focusing on a narrow domain of expertise are in great rise. As several tasks require multiple expertise, a designer may integrate multiple chatbots in the background or include them as interlocutors in a conversation. We investigated both scenarios by means of a Wizard of Oz experiment, in which participants talked to chatbots about visiting a destination. We analyzed the conversation content, users' speech, and reported impressions. We found no significant difference between single- and multi-chatbots scenarios. However, even with equivalent conversation structures, users reported more confusion in multi-chatbots interactions and adopted strategies to organize turn-taking. Our findings indicate that implementing a meta-chatbot may not be necessary, since similar conversation structures occur when interacting to multiple chatbots, but different interactional aspects must be considered for each scenario.

Different Chatbots for Different Purposes: Towards a Typology of Chatbots to Understand Interaction Design

Abstract: Chatbots are emerging as interactive systems. However, we lack knowledge on how to classify chatbots and how such classification can be brought to bear in analysis of chatbot interaction design. In this workshop paper, we propose a typology of chatbots to support such classification and analysis. The typology dimensions address key characteristics that differentiate current chatbots: the duration of the user’s relation with the chatbot (short-term and long-term), and the locus of control for user’s interaction with the chatbot (user-driven and chatbot-driven). To explore the usefulness of the typology, we present four example chatbot purposes for which the typology may support analysis of high-level chatbot interaction design. Furthermore, we analyse a sample of 57 chatbots according to the typology dimensions. The relevance and application of the typology for developers and service providers are discussed.

Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time

Abstract: Crowd-powered conversational assistants have been shown to be more robust than automated systems, but do so at the cost of higher response latency and monetary costs. A promising direction is to combine the two approaches for high quality, low latency, and low cost solutions. In this paper, we introduce Evorus, a crowd-powered conversational assistant built to automate itself over time by (i) allowing new chatbots to be easily integrated to automate more scenarios, (ii) reusing prior crowd answers, and (iii) learning to automatically approve response candidates. Our 5-month-long deployment with 80 participants and 281 conversations shows that Evorus can automate itself without compromising conversation quality. Crowd-AI architectures have long been proposed as a way to reduce cost and latency for crowd-powered systems; Evorus demonstrates how automation can be introduced successfully in a deployed system. Its architecture allows future researchers to make further innovation on the underlying automated components in the context of a deployed open domain dialog system.

Chatbot for e-learning: A case of study

Abstract: Nowadays the use of Chatbots is very popular in a large scale of applications especially in systems that provide an intelligence support to the user. In fact, to speed up the assistance, in many cases, these systems are equipped with Chatbots that can interpret the user questions and provide the right answers, in a fast and correct way. This paper presents the realization of a prototype of a Chatbot in educational domain: it has been developed a system to provide support to university students on some courses. The initial purpose has focused on the design of the specific architecture, model to manage communication and furnish the right answers to the student. For this aim, it has been realized a system that can detect the questions and thanks to the use of natural language processing techniques and the ontologies of domain, gives the answers to student. Finally, after the implementation of the designed model, experimental campaign was conducted in order to demonstrate its enforceability and efficiency.

Convey: Exploring the Use of a Context View for Chatbots

Abstract: Text messaging-based conversational systems, popularly called chatbots, have seen massive growth lately. Recent work on evaluating chatbots has found that there exists a mismatch between the chatbot's state of understanding (also called context) and the user's perception of the chatbot's understanding. Users found it difficult to use chatbots for complex tasks as the users were uncertain of the chatbots' intelligence level and contextual state. In this work, we propose Convey (CONtext View), a window added to the chatbot interface, displaying the conversational context and providing interactions with the context values. We conducted a usability evaluation of Convey with 16 participants. Participants preferred using chatbot with Convey and found it to be easier to use, less mentally demanding, faster, and more intuitive compared to a default chatbot without Convey. The paper concludes with a discussion of the design implications offered by Convey.

Intelligent travel chatbot for predictive recommendation in echo platform

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.

Chatbot in a Campus Environment: Design of LiSA, a Virtual Assistant to Help Students in Their University Life

Abstract: This work presents some initial results of our research about the design and implementation of “LiSA” (Link Student Assistant), a chatbot intended to help students in their campus life, through information and services. The focus of our research is to understand which kind of information and services are better accessed through this kind of touch point, how the chatbot personality influences the user experience and the interaction and which level of intelligence should be implemented. After an analysis of the state of the art in the considered application domain we investigated, through a survey, the users’ needs and their inclination to the use of a chatbot for this specific purpose. A chatbot was created to deliver the survey, allowing to understand both the users’ needs and their behaviour while using the tool.

A Tool for Introducing Computer Science with Automatic Formative Assessment

Abstract: In this paper we present a software platform called Chatbot designed to introduce high school students to Computer Science (CS) concepts in an innovative way: by programming chatbots. A chatbot is a bot that can be programmed to have a conversation with a human or robotic partner in some natural language such as English or Spanish. While programming their chatbots, students use fundamental CS constructs such as variables, conditionals, and finite state automata, among others. Chatbot uses pattern matching, state of the art lemmatization techniques, and finite state automata in order to provide automatic formative assessment to the students. When an error is found, the formative feedback generated is immediate and task-level. We evaluated Chatbot in two observational studies. An online nation-wide competition where more than 10,000 students participated. And, a mandatory in-class 15-lesson pilot course in three high schools. We measured indicators of student engagement (task completion, participation, self reported interest, etc.) and found that girls’ engagement with Chatbot was higher than boys’ for most indicators. Also, in the online competition, the task completion rate for the students that decided to use Chatbot was five times higher than for the students that chose to use the renowned animation and game programming tool Alice. Our results suggest that the availability of automatic formative assessment may have an impact on task completion and other engagement indicators among high school students.

A Self-Diagnosis Medical Chatbot Using Artificial Intelligence

Abstract: To lead a good life healthcare is very much important. But it is very difficult to obtain the consultation with the doctor in case of any health issues. The proposed idea is to create a medical chatbot using Artificial Intelligence that can diagnose the disease and provide basic details about the disease before consulting a doctor .To reduce the healthcare costs and improve accessibility to medical knowledge the medical chatbot is built. Certain chatbots acts as a medical reference books, which helps the patient know more about their disease and helps to improve their health. The user can achieve the real benefit of a chatbot only when it can diagnose all kind of disease and provide necessary information. A text-to-text diagnosis bot engages patients in conversation about their medical issues and provides a personalized diagnosis based on their symptoms. Hence, people will have an idea about their health and have the right protection.

An overview of artificial intelligence based chatbots and an example chatbot application

Abstract: ChatBot can be described as software that can chat with people using artificial intelligence. These software are used to perform tasks such as quickly responding to users, informing them, helping to purchase products and providing better service to customers. In this paper, we present the general working principle and the basic concepts of artificial intelligence based chatbots and related concepts as well as their applications in various sectors such as telecommunication, banking, health, customer call centers and e-commerce. Additionally, the results of an example chabbot for donation service developed for telecommunication service provider are presented using the proposed architecture.

Assessing the Usability of a Chatbot for Mental Health Care

Abstract: The aim of this paper is to assess the usability of a chatbot for mental health care within a social enterprise. Chatbots are becoming more prevalent in our daily lives, as we can now use them to book flights, manage savings, and check the weather. Chatbots are increasingly being used in mental health care, with the emergence of “virtual therapists”. In this study, the usability of a chatbot named iHelpr has been assessed. iHelpr has been developed to provide guided self-assessment, and tips for the following areas: stress, anxiety, depression, sleep, and self esteem. This study used a questionnaire developed by Chatbottest, and the System Usability Scale to assess the usability of iHelpr. The participants in this study enjoyed interacting with the chatbot, and found it easy to use. However, the study highlighted areas that need major improvements, such as Error Management and Intelligence. A list of recommendations has been developed to improve the usability of the iHelpr chatbot.

Chatbot as an Intelligent Personal Assistant for Mobile Language Learning

Abstract: The application of automatic conversational system (chatbot) in learning foreign language is still limited. In this study, we built a chatbot dedicated to English learners. The system is named English Practice is installed on the mobile devices to interact with users through a window chat. Chatbot is able to automatically remind learners to study and suggest some answers to multiple choice questions. It also has the ability to help users in learning vocabulary and new lessons. The result shows that most of the basic functions of the system are used by the users and this this promises to be applied widely in the future.

Quro: Facilitating User Symptom Check Using a Personalised Chatbot-Oriented Dialogue System.

Abstract: Automated conversational agents built with medical applications in mind, have the potential to reduce healthcare readmissions and improve accessibility to medical knowledge. In this work, we demonstrate the development and evaluation of an automated chatbot for triage and conditions assessment, based on user inputs in natural language. The implemented bot engages patients in conversation about symptoms experienced and provides a personalized pre-synopsis based on their symptoms and profile. Our chatbot system was able to predict user conditions correctly based on two sets of patient test cases with an average precision of 0.82. Our implementation demonstrates that a medical chatbot can help with automatic triage and pre-assessment of patients with simple symptom analysis and a conversational approach without the use of cumbersome form-based data entry.