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.

Enhancing Conversational Agents with Empathic Abilities

Abstract: Conversational agents are getting increasingly popular and find applications in health and customer services. Conversations in these fields are often emotionally charged. It is, therefore, necessary to handle the conversation with some degree of empathy to be effective. In this work, we leverage advances in the field of natural language processing to create a dialogue system that can convincingly generate empathic responses to text-based messages. To improve the system's ability to converse with empathy, we train the language model on empathic conversations and inject additional emotional information in the response generation. We propose two chatbots: a benchmark bot and an empathic bot. Additionally, we implement an emotion classifier that allows us to predict the emotional state of text-based messages. We evaluate both chatbots in quantitative studies and compare them with human responses in qualitative studies involving human judges. Our evaluation shows that our empathic chatbot outperforms the benchmark bot and even the human-generated responses in terms of perceived empathy. Additionally, we achieve state-of-the-art results in terms of response quality using transformer-based language models. Finally we report that we can double the initial performance of the emotion classifier using undersampling techniques, yielding a final F1-score of 0.81 in six basic emotions.

Towards Designing Conversational Agent Systems

Abstract: Conversation is interactive communication between two and more people which enhances knowledge among these people. It is key to exchange thoughts and ideas while listening to each other. Based on this idea the advances in artificial intelligence started to develop technologies in which computer can communicate with human in a more natural way. A computer program which acts as an automated conversation agent is also called as a Chatbot. Chatbots are useful in many different applications like health care, education, financial marketing, banking, agriculture, etc. This paper presents a survey on different issues in designing conversational agents. The paper discusses the types and applications of Chatbot; it lists research challenges while designing and implementing these systems. The paper presents a study and comparison of different techniques like NLP (Natural Language Processing), Deep Learning and Neural Networks used for designing these systems. The paper also presents various datasets being used by popular Chatbots in the industry. The paper ends by summarizing scope for future work in this domain.

A multimodal guide for the augmented campus

Abstract: The use of Personal Digital Assistants (PDAs) with ad-hoc built-in information retrieval and auto-localization functionalities can help people navigating an environment in a more natural manner compared to traditional audio/visual pre-recorded guides. In this work we propose and discuss a user-friendly, multi-modal guide system for pervasive context-aware service provision within augmented environments. The proposed system is adaptable to the user needs of mobility within a given environment; it is usable on different mobile devices and in particular on PDAs, which are used as advanced adaptive HEI (human-environment interaction) interfaces. An information retrieval service is provided that is easily accessible through spoken language interaction in cooperation with an auto-localization service. The interaction is enabled by speech recognition and synthesis technologies, and by a ChatBot system, endowed with common sense reasoning capabilities to properly interpret user speech and provide him with the requested information. This interaction mode turns to be more natural, and users are required to have only basic skills on the use of PDAs. The auto-localization service relies on a RFID-based framework, which resides partly in the mobile side of the entire system (PDAs), and partly in the environment side. In particular, RFID technology allows the system to provide users with context-related information. An implemented case study is showed that illustrates service provision in an augmented environment within university campus settings (termed "Augmented Campus"). Lastly, a discussion about user experiences while using trial services within the Augmented Campus is given.

Chatbot design issues: building intelligence with the Cartesian paradigm

Abstract: The article discusses the functioning of human-like consciousness and the potential for developing a chatbot based on human-like consciousness. The proposed approach was verified experimentally using a sociological method and by attracting a cohort of student volunteers. The chatbot population was created on the back of our complex neural network architecture design. The volunteers were asked to identify their interlocutor, which was either a human agent or a chatbot. For integrity, the conversations between bots and people were organized randomly so that each volunteer could interact several times with all bots in the population and with all participants in the sample. The article discusses the results of the study, the details of the proposed approach. The article explains the features of the functioning and self-reconfiguration of the neural network that provide high reliability of chatbot replicas and high speed of responses to replicas of human users so that the delay time does not raise suspicion of human users. The main idea of the authors’ approach is an attempt to model human self-awareness and self-reflection. The results prove the proposed neural network architecture design successful in terms of real-time self-learning.

A longitudinal study of human-chatbot relationships

Abstract: Social chatbots have become more advanced, paving the way for human–chatbot relationships (HCRs). Although this phenomenon has already received some research attention, the results have been contradictory, and there is uncertainty regarding how to understand HCR formation. To provide the needed knowledge on this phenomenon, we conducted a qualitative longitudinal study. We interviewed 25 participants over a 12-week period to understand how their HCRs formed with the popular chatbot Replika. We found that the HCRs formed gradually and mostly in line with the assumptions of Social Penetration Theory. Our findings indicate the need to acknowledge substantial variation and nuance in the HCR formation process, plus variation in the onset of self-disclosure and in the subsequent relationship formation. The results show that important drivers pushing the relationship toward attachment and perceived closeness appear to be Replika's ability to participate in a variety of interactions, as well as to support more deep-felt human needs related to social contact and self-reflection. In contrast, unpredictable events and technical difficulties could hinder relationship formation and lead to termination. Finally, we discuss the appropriateness of using a theoretical framework developed for human–human relationships when investigating HCRs, and we suggest directions for future research.