Lessons Learned from Modeling the Interaction with Conversational Agents

IF 0.8 Q3 EDUCATION & EDUCATIONAL RESEARCH

Interaction Design and Architectures Pub Date : 2023-02-01 DOI:10.55612/s-5002-055-007

Ulisses da Silva Fernandes, Glívia Angélica Rodrigues Barbosa, Bruno Azevedo Chagas, Gabriel Diniz Junqueira Barbosa, Simone Diniz Junqueira Barbosa, R. Prates

{"title":"Lessons Learned from Modeling the Interaction with Conversational Agents","authors":"Ulisses da Silva Fernandes, Glívia Angélica Rodrigues Barbosa, Bruno Azevedo Chagas, Gabriel Diniz Junqueira Barbosa, Simone Diniz Junqueira Barbosa, R. Prates","doi":"10.55612/s-5002-055-007","DOIUrl":null,"url":null,"abstract":"Intelligent conversational agents have become widespread. Inspired by conversations in natural language, they present different degrees of intelligence and autonomy, bringing challenges for Human-Computer Interaction (HCI). One such challenge concerns design languages for modeling user-agent interaction. We focus here on MoLIC, a design-phase dialogue model based on Semiotic Engineering theory devised to represent user-system interactions as conversations. We performed two case studies with MoLIC interaction diagrams representing two conversational agents – the ANA chatbot and Samsung Bixby. We examined how the interactive aspects of these agents could be expressed in MoLIC. Although it was possible to express the general interaction, our results showed limitations related to the language expressiveness or its inadequacy to represent these systems. We identified limitations in the applicability of MoLIC in modeling and pondered on how to extend or adapt it; directing the HCI community to issues and initiatives that can help design and model these technologies.","PeriodicalId":44247,"journal":{"name":"Interaction Design and Architectures","volume":" ","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Interaction Design and Architectures","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.55612/s-5002-055-007","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}

引用次数: 0

Abstract

Intelligent conversational agents have become widespread. Inspired by conversations in natural language, they present different degrees of intelligence and autonomy, bringing challenges for Human-Computer Interaction (HCI). One such challenge concerns design languages for modeling user-agent interaction. We focus here on MoLIC, a design-phase dialogue model based on Semiotic Engineering theory devised to represent user-system interactions as conversations. We performed two case studies with MoLIC interaction diagrams representing two conversational agents – the ANA chatbot and Samsung Bixby. We examined how the interactive aspects of these agents could be expressed in MoLIC. Although it was possible to express the general interaction, our results showed limitations related to the language expressiveness or its inadequacy to represent these systems. We identified limitations in the applicability of MoLIC in modeling and pondered on how to extend or adapt it; directing the HCI community to issues and initiatives that can help design and model these technologies.

查看原文本刊更多论文

会话代理交互建模的经验教训

智能对话代理已经普及。受自然语言对话的启发，它们表现出不同程度的智能和自主性，给人机交互(HCI)带来了挑战。其中一个挑战涉及用户代理交互建模的设计语言。我们在这里关注MoLIC，这是一种基于符号学工程理论的设计阶段对话模型，旨在将用户-系统交互表示为对话。我们进行了两个案例研究，使用MoLIC交互图表示两个会话代理——ANA聊天机器人和Samsung Bixby。我们研究了这些药物的相互作用方面如何在MoLIC中表达。虽然可以表达一般的交互，但我们的结果显示了与语言表达性相关的局限性，或者它不足以表示这些系统。我们发现了MoLIC在建模中适用性的局限性，并思考了如何扩展或调整它;引导HCI社区关注能够帮助设计和建模这些技术的问题和计划。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Interaction Design and Architectures EDUCATION & EDUCATIONAL RESEARCH-

CiteScore

2.50

自引率

15.40%

发文量

审稿时长

20 weeks

期刊介绍： IxD&A (Interaction Design and Architecture (s)) Journal bases its existence on the following beliefs: - the complexity of today''s society requires the developments of new visions and new tools to address new systemic problems; - one needs at large to promote a deeper understanding of the interaction mechanisms, whatever the scale and the phenomena involved, from which originate the dynamic and static of the systems and all forms of architectures; - within complex systems, processes, architectures and cultural stratifications the focus should be always the individuals and their continuous co-evolution with the place that they populate; - the project and the ability to meta-design are central elements necessary to live consciously experiences, and above all those mediated by the machine. IxD&A aims to offer an interdisciplinary arena where everybody can present top level researches and discuss ideas on the future of technology mediated experiences in the field of communication, learning, working, entertainment, healthcare, etc...) a future that can be made possible by a joint effort in research and education. IxD&A, indeed, offers the ideal forum for meeting among frontier research, education, cutting edge technology development and application. Indeed, there will be no future if research and education will not be able to meet the world of production, or, in other words if we will not be able to transfer the ''lab'' into real life.