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.

How do people judge the credibility of algorithmic sources

Abstract: The exponential growth of algorithms has made establishing a trusted relationship between human and artificial intelligence increasingly important. Algorithm systems such as chatbots can play an important role in assessing a user’s credibility on algorithms. Unless users believe the chatbot’s information is credible, they are not likely to be willing to act on the recommendation. This study examines how literacy and user trust influence perceptions of chatbot information credibility. Results confirm that algorithmic literacy and users’ trust play a pivotal role in how users form perceptions of the credibility of chatbot messages and recommendations. Insights on how user trust is related to credibility provide a useful perspective on the conceptualization of algorithmic credibility. Algorithmic information processing that has been identified provides better foundations for algorithm design and development and a stronger basis for the design of sense-making chatbot journalism.

A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots

Abstract: We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system. The challenges of building such a model lie in how to ground conversation contexts with background documents and how to recognize important information in the documents for matching. To overcome the challenges, DGMN fuses information in a document and a context into representations of each other, and dynamically determines if grounding is necessary and importance of different parts of the document and the context through hierarchical interaction with a response at the matching step. Empirical studies on two public data sets indicate that DGMN can significantly improve upon state-of-the-art methods and at the same time enjoys good interpretability.

Future English Learning: Chatbots and Artificial Intelligence

Abstract: Advancements in robotic research have enabled robots to assist humans in many ways. Chatbots have been considered useful in many areas and research has increasingly focused on applying this technology to language education. The purpose of this study is to report on and review different types of intelligent chatbots in terms of language learning. The findings reveal that there are few chatbot programs that allow for direct interaction between chatbots and humans through voice recognition systems or texting for the purpose of learning foreign languages. Researchers have investigated the limited use of AI in education fields, including chatbot applications aimed at improving English teaching and learning. Based on their empirical studies, chatbots have proven to have some positive effects on students’ communication skills largely by their effect on expanding the quantity of their interactions, meaning negotiation, increasing their motivation, and on raising their interest in learning. Thus, this study proposes that chatbots can enrich language inputs and bring opportunities for language learners to raise communicative competence. More studies should be conducted to develop chatbots for learning foreign languages. Based on the findings of this study, suggestions for future research directions concerning chatbots in the realm of language education are presented, and further pedagogical implications are discussed.