Design Of Conversational Agents Research Articles

In Conversation with Artificial Intelligence: Aligning language Models with Human Values

Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or values should they be aligned with? And how can this be accomplished? In this paper, we propose a number of steps that help answer these questions. We start by developing a philosophical analysis of the building blocks of linguistic communication between conversational agents and human interlocutors. We then use this analysis to identify and formulate ideal norms of conversation that can govern successful linguistic communication between humans and conversational agents. Furthermore, we explore how these norms can be used to align conversational agents with human values across a range of different discursive domains. We conclude by discussing the practical implications of our proposal for the design of conversational agents that are aligned with these norms and values.

The TRISEC framework for optimizing conversational agent design across search, experience and credence service contexts

PurposeService providers increasingly use conversational agents (CAs), such as chatbots, to effectively communicate with customers while managing interaction costs and providing round-the-clock customer service. Yet, the adoption and implementation of such agents in service contexts remains a hit-and-miss, and firms often struggle to balance their CAs implementation complexities and costs with relation to their service objectives, technology design and customer experiences. The purpose of this paper is to provide guidance on optimizing CA design, therefore, the authors develop a conceptual framework, TRISEC, that integrates service logic, technology design and customer experience to examine the implementation of CA solutions in search, experience and credence (SEC) contexts.Design/methodology/approachThe paper draws on service marketing and communications research, combining the service context classification scheme of search, experience and credence and the technology infused service marketing triangle foci (service, technology and customer) in its conceptual development.FindingsThe authors find that an opportunity exists in recognizing the importance of context when designing CAs and aiming to achieve a balance between service objectives, technology design and customer experiences.Originality/valueThis study contributes to service management and communications research literature by providing interactive service marketing researchers with the highly generalizable TRISEC framework to aid in optimizing CA design and implementation in interactive customer communication technologies. Furthermore, the study provides an array of future research avenues. From a practical perspective, this study aims at providing managers with a means to optimize CA technology design while maintaining a balance between customer centricity and implementation complexity and costs in different service contexts.

Examining spoken words and acoustic features of therapy sessions to understand family caregivers’ anxiety and quality of life

BackgroundSpeech and language cues are considered significant data sources that can reveal insights into one’s behavior and well-being. The goal of this study is to evaluate how different machine learning (ML) classifiers trained both on the spoken word and acoustic features during live conversations between family caregivers and a therapist, correlate to anxiety and quality of life (QoL) as assessed by validated instruments. MethodsThe dataset comprised of 124 audio-recorded and professionally transcribed discussions between family caregivers of hospice patients and a therapist, of challenges they faced in their caregiving role, and standardized assessments of self-reported QoL and anxiety. We custom-built and trained an Automated Speech Recognition (ASR) system on older adult voices and created a logistic regression-based classifier that incorporated audio-based features. The classification process automated the QoL scoring and display of the score in real time, replacing hand-coding for self-reported assessments with a machine learning identified classifier. FindingsOf the 124 audio files and their transcripts, 87 of these transcripts (70%) were selected to serve as the training set, holding the remaining 30% of the data for evaluation. For anxiety, the results of adding the dimension of sound and an automated speech-to-text transcription outperformed the prior classifier trained only on human-rendered transcriptions. Specifically, precision improved from 86% to 92%, accuracy from 81% to 89%, and recall from 78% to 88%. InterpretationClassifiers can be developed through ML techniques which can indicate improvements in QoL measures with a reasonable degree of accuracy. Examining the content, sound of the voice and context of the conversation provides insights into additional factors affecting anxiety and QoL that could be addressed in tailored therapy and the design of conversational agents serving as therapy chatbots.

Are You Flirting, Objectifying or What? a Conversation Analysis of “you’re very sexy” Conversational Turn

Intent identification is one of the most critical components in conversational agent design. Conversational agent “is any dialogue system that not only conducts natural language processing but also responds automatically using human language.” (Conversational Agent, 2019). The crux of designing human-like conversational agent is to mimic how human understands another human and then responds “naturally”. The current study attempts to answer the fundamental question: how to model human processes of understanding another human? In order to answer that question, it starts from exploring some basic concepts relevant to intent identification from Conversation Analysis (CA). CA is a mature field that studies authentic human interaction. The basic concepts from CA are then synthesised into a model that potentially fit to existing framework and paradigm in conversational agent design, i.e. Natural Conversation Framework (NCF) and Intent-Entity-Context-Response (IECR) paradigm. Instead of using a made-up sentence, the model is then tested to an authentic conversational turn seksi sekali dirimu ‘you’re very sexy’. The test shows that the model is able to detect several possible intents contain in this authentic conversational turn. The model is also able to handle Conversational Indonesian and multi-modality. Considering the versatility of Conversation Analysis, in all likelihood the model will be able to handle any language and all kinds of modalities. Future study can be done to analyse more Conversational Indonesian data (to develop library of intent for Conversational Indonesian Language), as well as conversational data from different languages and conversational data containing diverse modalities.

A Framework for Design of Conversational Agents to Support Health Self-Care for Older Adults.

We examined the potential of conversational agents (CAs) to support older adults' self-care related to chronic illness in light of lessons learned from decades of pedagogical agent research, which investigates the impact and efficacy of CAs for a wide range of learners. The role of CAs in education (i.e., pedagogical agents) has been long studied, but their potential for supporting self-care has received less attention, especially for older adults. We reviewed work on pedagogical agents and considered how it informs the design of CAs for older adults. We propose a framework for designing CAs to support older adult self-care, which organizes a review of work in this area and integration with the pedagogical agent literature. Our review of the pedagogical agent literature revealed an evolution from teaching machines to interactive, social systems that influence student motivational as well as learning outcomes. To integrate this review with work on CAs and self-care, we developed a framework that specifies how self-care goals evolve with stages of an illness, communication goals that support self-care at each stage, patient needs, and requirements for CAs to support these needs. The review identified an agenda for future research on CA functions and features that help older adults accept need for self-care, establish self-care, and sustain self-care over time. Integrating insights from the pedagogical agent literature with research on developing CAs for self-care defines an agenda for developing and evaluating CAs to help older adults manage illness.

Systematic Review: Trust-Building Factors and Implications for Conversational Agent Design

ABSTRACT Off-the-shelf conversational agents are permeating people’s everyday lives. In these artificial intelligence devices, trust plays a key role in users’ initial adoption and successful utilization. Factors enhancing trust toward conversational agents include appearances, voice features, and communication styles. Synthesizing such work will be useful in designing evidence-based, trustworthy conversational agents appropriate for various contexts. We conducted a systematic review of the experimental studies that investigated the effect of conversational agents’ and users’ characteristics on trust. From a full-text review of 29 articles, we identified five agent design-themes affecting trust toward conversational agents: social intelligence of the agent, voice characteristics and communication style, look of the agent, non-verbal communication, and performance quality. We also found that participants’ demographic, personality, or use context moderate the effect of these themes. We discuss implications for designing trustworthy conversational agents and responsibilities around on stereotypes and social norm building through agent design.

How do facilitation interventions foster learning? The role of evaluation and coordination as causal mediators in idea convergence

Teams need to co-construct meaning to establish shared understanding of crowdsourced ideas. This is challenging because team members are often faced with an excessive amount of ideas, they have no access to the ideator to clarify ideas, have limited meeting duration, and do not necessarily share a common working history. Facilitation interventions can aid the co-construction of meaning. However, it is uncertain if facilitation interventions that were successful in traditional convergence settings can be applied to convergence with crowdsourced ideas and what mechanisms can explain the positive association between facilitation interventions and co-creation of meaning. In this study, I tested three facilitation techniques and the mediating role of evaluation and coordination in a laboratory experiment involving 199 participants. The participants were given an IT-supported convergence task with crowdsourced ideas. The findings show that facilitated teams receiving high attention guidance and discussion encouragement outperform non-facilitated teams and that evaluation and coordination are the mechanisms through which these effects come about. The findings are beneficial for the design of conversational agents in convergence settings and for team leaders who want to establish shared understanding in convergence settings with crowdsourced ideas.

Erratum to: Natural language scripting within conversational agent design

Erratum to: Natural language scripting within conversational agent design

Erratum to: An approach to conversational agent design using semantic sentence similarity

Erratum to: An approach to conversational agent design using semantic sentence similarity

Natural language scripting within conversational agent design

This paper presents a novel Semantic-Based Conversational Agent (SCA). Traditional conversational agents (CA) interpret scripts consisting of structural patterns of sentences, which take no conside...

An approach to conversational agent design using semantic sentence similarity

This paper presents a novel framework for constructing a Semantic-Based Conversational Agent (SCAF). Traditional conversational agents (CA) interpret scripts using structural patterns of sentences, which require the script writer to consider every possible permutation that a user may send as input to the CA. This is a time-consuming process, which takes no consideration of semantic content, working solely with the structural form of the sentence. Furthermore, this has proven to be a high maintenance task that can produce some unforeseen consequences when modifying or introducing new patterns into a script. This invariably results in the script writer reassessing the entire script to prevent such occurrences. Different script writers possess differing levels of skill and as such this can prove to be an exasperating task. The proposed SCAF interprets scripts consisting of natural language sentences by means of a semantic sentence similarity measure. User input is measured semantically against the natural language sentences of the context in order to respond with an appropriate output. Such scripting is effortless and alleviates the burden of the traditional pattern-scripted methodologies. Evaluation of the framework has highlighted its potential and shown improvements on traditional CAs.