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.

Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-Sequence Model

Abstract: We apply sequence-to-sequence model to mitigate the impact of speech recognition errors on open domain end-to-end dialog generation We cast the task as a domain adaptation problem where ASR transcriptions and original text are in two different domains In this paper, our proposed model includes two individual encoders for each domain data and make their hidden states similar to ensure the decoder predict the same dialog text The method shows that the sequence-to-sequence model can learn the ASR transcriptions and original text pair having the same meaning and eliminate the speech recognition errors Experimental results on Cornell movie dialog dataset demonstrate that the domain adaption system help the spoken dialog system generate more similar responses with the original text answers

Customer Service Chatbots: A Qualitative Interview Study into the Communication Journey of Customers

Abstract: The current qualitative interview study describes the communication journey of customers who wish to contact companies, and their evaluation of chatbot communication within this journey. Interviews were conducted with a sample (N = 24) that was varied in terms of gender, age, educational level and household composition. Experiences with nine customer service chatbots were included. The analysis focuses on three stages in the journey: first, customers’ prior expectations when contacting a company; second, their experiences during chatbot conversations, and third, their final conclusions about under which conditions customer service chatbots should be implemented, and the consequences of chatbot communication for customers’ company perceptions. Implications for research and practice are discussed.

Combining Chatbot and Social Media: Enhancing Personal Learning Environment (PLE) in Language Learning

Abstract: Transformation of the global learning landscape in twentyfirst century is shaped by the uptake of digital technology and social network applications, along with students’ alteration of characteristics, needs, and demands. As an attempt to integrate digital technology and social network application, this study aimed to develop a chatbot-based application integrated with social media LINE to enhance language learning, specifically for learning Japanese grammar. The application, namely Gengobot, is a chatbotbased grammar application, consisting of Japanese Language Proficiency Test Level 5 and Level 4 (N5 and N4) grammar materials in three language: Indonesian, English, and Japanese. This study applied design-based research method with Waterfall application development procedure, and a questionnaire to gather feedbacks from fifty-three students regarding Gengobot features and contents. Gengobot application was successfully developed using code igniter framework, MySQL database, and webhook to integrate Gengobot application with LINE messaging API. Application testing confirmed that Gengobot is successfully developed and operated properly. The students agreed that Gengobot materials and features considered to be adequate, useful, user friendly, and suitable to support language learning. Gengobot is also highly accessible since it is integrated to social media LINE, allowing students to adjust its use to their own learning preference and needs, which is suitable to enhance students’ personal learning environment. © 2020Tim Pengembang Jurnal UPI Article History: Received 26 Mar 2020 Revised 15 Sep 2020 Accepted 30 Sep 2020 Available online 2 Oct 2020 ____________________

Potential effects of chatbot technology on customer support: A case study

Abstract: This study analyzed an experiment with using a chatbot for the customer support department at the case company. A modified version of the updated DeLone and McLean information system success model was utilized to evaluate potential effects of the chatbot on the operation of the customer support. Five dimensions of the model were measured before and after the chatbot implementation and then compared to determine if the chatbot can help improve the customer experience with the customer support of the case company. Responses from 60 customers who had used the chatbot were obtained through a web-based survey. Results indicated that the addition of a chatbot to a traditional customer support model can improve customer experience, mainly on responsiveness measure, while maintain a similar level on information quality, system quality and user satisfaction dimensions. Results also suggested that unsuccessful chatbot attempts which require further human involvement may not necessarily worsen customer experience as many expect. Based on the experiment, the study also provided three suggestions for firms when planning to adopt chatbot technology. First, the potential of chatbot should not be overestimated, it cannot replace human agents completely in customer support. Second, chatbot should handle only simple enough tasks and leave the more complex and trickier ones to human. And third, building a chatbot is a continuous process that requires careful resource planning not only for the initial development but also for the later stage of analyzing and turning conversations of the chatbot.

A Study on Conversational Public Administration Service of the Chatbot Based on Artificial Intelligence

Abstract: Artificial intelligence-based services are expanding into a new industrial revolution. There is artificial intelligence technology applied in real life due to the development of big data and deep learning related technology. And data analysis and intelligent assistant services that integrate information from various fields have also been commercialized. Chatbot with interactive artificial intelligence provide shopping, news or information. Chatbot service, which has begun to be adopted by some public institutions, is now just a first step in the steps. This study summarizes the services and technical analysis of chatbot. and the direction of public administration service chatbot was presented.