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.

A Conversation-Driven Approach for Chatbot Management

Abstract: Managing and evolving a chatbot’s content is a laborious process and there is still a lack of standardization. In this context of standardization, the absence of a management process can lead to bad user experiences with a chatbot. This work proposes the Chatbot Management Process, a methodology for content management on chatbot systems. The proposed methodology is based on the experiences acquired with the development of Evatalk, the chatbot for the Brazilian Virtual School of Government. The focus of this methodology is to evolve the chatbot content through the analysis of user interactions, allowing a cyclic and human-supervised process. We divided the proposed methodology into three distinct phases, namely, manage, build, and analyze. Moreover, the proposed methodology presents a clear definition of the roles of the chatbot team. We validate the proposed methodology along with the creation of the Evatalk chatbot, whose amount of interactions was of 22,771 for the 1,698,957 enrolled attendees in the Brazillian Virtual School of Government in 2020. The application of the methodology on Evatalk’s chatbot brought positive results: we reduced the chatbot’s human hand-off rate from 44.43% to 30.16%, the chatbot’s knowledge base examples increased by 160% whilst maintaining a high percentage of confidence in its responses and keeping the user satisfaction collected in conversations stable.

Engaging Students With a Chatbot-Based Academic Advising System

Abstract: Abstract Advising systems automate aspects of academic advising. Traditionally, advising systems focused on specialized tasks such as course selection. Recently, chatbot-based advising systems have emerged as they emulate scenario-based advising. Nevertheless, the design of most chatbot-based advising systems is not user-centric, potentially causing a lack of adoption. Further, there is a lack of studies reporting findings of usability evaluation of chatbot-based advising systems. In response, we contribute a chatbot-based academic advising system, MyAdvisor, that helps students with prescriptive academic inquiries. The system is based on real advising scenarios and designed with usability principles. The results show that students learn the system fast and find it helpful. This work contributes (1) scenario-based functional requirements and usability requirements of the chatbot-based advising system, (2) the application of usability heuristics in the design of the system, and (3) findings of empirically evaluating the system usability.

Churn Intent Detection in Multilingual Chatbot Conversations and Social Media

Abstract: We propose a new method to detect when users express the intent to leave a service, also known as churn. While previous work focuses solely on social media, we show that this intent can be detected in chatbot conversations. As companies increasingly rely on chatbots they need an overview of potentially churny users. To this end, we crowdsource and publish a dataset of churn intent expressions in chatbot interactions in German and English. We show that classifiers trained on social media data can detect the same intent in the context of chatbots. We introduce a classification architecture that outperforms existing work on churn intent detection in social media. Moreover, we show that, using bilingual word embeddings, a system trained on combined English and German data outperforms monolingual approaches. As the only existing dataset is in English, we crowdsource and publish a novel dataset of German tweets. We thus underline the universal aspect of the problem, as examples of churn intent in English help us identify churn in German tweets and chatbot conversations.

Intelligent Chatbot for Requirements Elicitation and Classification

Abstract: Software Requirements (SR) are considered as the foundation for a supreme quality software development process and each step of the software development process is dependent and is related to the SR. Software requirements elicitation may be the most important area of requirements engineering and possibly of the entire software development process. There is a lot of human work required in the process of software requirements elicitation and software requirements classification and in cases where the requirements are huge in number, this requirements elicitation and classification process becomes tedious and is prone to errors. We propose a novel approach to automate Requirements Elicitation and Classification using an intelligent conversational chatbot. Utilizing Machine Learning and Artificial Intelligence, the chatbot converses with stakeholders in Natural Language and elicits formal system requirements from the interaction, and subsequently classifies the elicited requirements into Functional and Non-functional system requirements.

Testing Chatbots with Charm.

Abstract: Chatbots are software programs with a conversational user interface, typically embedded in webs or messaging systems like Slack, Facebook Messenger or Telegram. Many companies are investing in chatbots to improve their customer support. This has led to a proliferation of chatbot creation platforms (e.g., Dialogflow, Lex, Watson). However, there is currently little support for testing chatbots, which may impact in their final quality.