Yunhan Wu, Martin Porcheron, Philip R. Doyle, Justin Edwards, D. Rough, Orla Cooney, Anna Bleakley, L. Clark, Benjamin R. Cowan
{"title":"Comparing Command Construction in Native and Non-Native Speaker IPA Interaction through Conversation Analysis","authors":"Yunhan Wu, Martin Porcheron, Philip R. Doyle, Justin Edwards, D. Rough, Orla Cooney, Anna Bleakley, L. Clark, Benjamin R. Cowan","doi":"10.1145/3543829.3543839","DOIUrl":"https://doi.org/10.1145/3543829.3543839","url":null,"abstract":"Intelligent Personal Assistants (IPAs) are limited in the languages they support, meaning many people are left to interact using a non-native language. Yet, we know little about how people interact with IPAs in this way. Through a conversation analysis (CA) perspective, we examine native (L1) and non-native (L2) English speaker interactions with Google Assistant, comparing how both user groups produce IPA commands. Our work shows that L1 and L2 speakers similarly used pauses, partial or complete repetition, and hyper-articulation when constructing commands. However, L2 speakers tended to experience issues in lexical access, syntactic construction and pronunciation, resulting in the use of code-mixing, increased pause lengths and off-task rehearsal to help generate commands. We consider reasons for such effects, whilst exploring ways to design IPA interaction to ensure it is sensitive to L2 challenges in command production.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125009685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jaisie Sin, Dongqing Chen, Jalena G. Threatt, Anna Gorham, Cosmin Munteanu
{"title":"Does Alexa Live Up to the Hype? Contrasting Expectations from Mass Media Narratives and Older Adults' Hands-on Experiences of Voice Interfaces","authors":"Jaisie Sin, Dongqing Chen, Jalena G. Threatt, Anna Gorham, Cosmin Munteanu","doi":"10.1145/3543829.3543841","DOIUrl":"https://doi.org/10.1145/3543829.3543841","url":null,"abstract":"Voice user interfaces (VUIs) are advertised as easy to use and beneficial to older adults (OAs). Disparities between expectations and OAs’ hands-on experiences with VUIs may discourage OAs’ further use of VUIs and widen digital divides. To understand such disparities, we conducted two-week in-home field deployments of the Amazon Echo Dot with OAs. We interviewed participants before and after deployment on their perceptions of VUIs in relation to prevailing media-derived expectations about VUIs. Our analysis revealed mismatches between expectation and hands-on experiences with VUIs; namely, VUIs were found to be more primitive than expected, there were more limitations to VUIs than expected, more prerequisites were required to fully make use of VUIs, and the sources that VUIs drew from fell short in earning trust. Our findings contribute aspects to be considered to close the gap between expectations and experiences related to VUIs for older adults.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"570 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123149063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Voice Assistants Have a Plurilingualism Problem","authors":"Amanda Kann","doi":"10.1145/3543829.3544526","DOIUrl":"https://doi.org/10.1145/3543829.3544526","url":null,"abstract":"Intelligent personal assistants (IPAs) using speech interfaces have historically been limited to monolingual use in pre-selected languages. Although recent developments in some IPAs have allowed for increased multilingual flexibility, the plurilingual competence – ability to utilise more than one language in the frame of a single interaction – of state-of-the-art IPAs still falls short. This is demonstrated in a pilot study, where two widely used IPAs are shown to consistently fail in plurilingual interactions across 3 core tasks. This lack of plurilingual competence makes certain IPA functions virtually unusable in various contexts for users who are not native speakers of the official language(s) where they are located, and also speaks to wider problems in the treatment of multilingual use of IPAs by developers. Addressing these issues will not only make IPAs with speech interfaces considerably more functional for a large demographic of current and potential IPA users, but also enable new applications for IPAs in contexts such as self-regulated language learning.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132116284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Pilot Study for Understanding Users’ Attitudes Towards a Conversational Agent for News Recommendation","authors":"Li Chen, Zhirun Zhang, Xinzhi Zhang, Lehong Zhao","doi":"10.1145/3543829.3544530","DOIUrl":"https://doi.org/10.1145/3543829.3544530","url":null,"abstract":"Conversational recommender agents have been rapidly developed and applied in various domains (e.g., amusement, e-commerce, tourism) in recent years, to allow users to easily access information or service through natural communication with the system. However, little attention has been paid to the news domain, though some news organizations (e.g., ABC, BBC) have started to deploy news chatbots to engage with audiences. In this work, we performed a pilot study in form of a semi-structured interview for the purpose of knowing important features of recommendations users expect when they interact with a news conversational agent. In particular, in order to acquire users’ thoughtful feedback, we implemented a prototype system based on a taxonomy that covers all of the major recommendation-seeking and information-searching goals according to related literature. The interview results reveal users’ opinions on various aspects of a conversational agent for news recommendation, including the condition under which they may request/accept the news recommendation by a conversational agent, important features of the conversational news recommendation they expect, and their preferred preference elicitation strategy. Several practical implications are concluded at the end, which might inspire the design and development of effective conversational agents in the news domain.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133949265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shruti Rao, Valeria Resendez, Abdallah El Ali, Pablo César
{"title":"Ethical Self-Disclosing Voice User Interfaces for Delivery of News","authors":"Shruti Rao, Valeria Resendez, Abdallah El Ali, Pablo César","doi":"10.1145/3543829.3544532","DOIUrl":"https://doi.org/10.1145/3543829.3544532","url":null,"abstract":"Voice User Interfaces (VUIs) such as Alexa and Google Home that use human-like design cues are an increasingly popular means for accessing news. Self-disclosure in particular may be used to build relationships of trust with users who may reveal intimate details about themselves. This information can be (mis)used by algorithms to tailor and deliver partisan, critical news at the cost of journalistic ethics. In this position paper, we argue that self-disclosing VUIs may be beneficial to build trust with users and deliver news. We explain how a self-disclosing relationship may not only be a step towards human-like voice assistants but also aid in acceptance of, and exposure to different news events. We caution against obvious pitfalls from both a system and journalistic perspective and provide measures to address such concerns.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132006095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Papr Readr Bot: A Conversational Agent to Read Research Papers","authors":"M. X. Foo, Luca Della Libera, Ilhan Aslan","doi":"10.1145/3543829.3544536","DOIUrl":"https://doi.org/10.1145/3543829.3544536","url":null,"abstract":"Reading research papers can be a tedious and lonely task. We present Papr Readr Bot, a (chat)bot which aims to assist researchers in reading papers more effectively and with less cognitive effort by providing paper summaries, answering questions about the paper, extracting figures from the paper, taking notes, and generate citation. Papr Readr Bot demonstrates and provides hands-on experiences of various deep learning-based skills that can be integrated in useful and social conversational assistants for reading related contexts. We open-sourced Papr Readr Bot at https://github.com/michellefxl/papreadr","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heloisa Candello, Marcelo Grave, Emilio Brazil, Marina Ito, Adinan Alves de Brito Filho, R. Paula
{"title":"How can AI leverage alternative criteria and suggest a better way to measure credit worthiness and economic growth?","authors":"Heloisa Candello, Marcelo Grave, Emilio Brazil, Marina Ito, Adinan Alves de Brito Filho, R. Paula","doi":"10.1145/3543829.3544537","DOIUrl":"https://doi.org/10.1145/3543829.3544537","url":null,"abstract":"Small business owners (SBOs) in low-income communities face several challenges when asking for micro-credit loans from financial institutions. Usual difficulties include low credit scores, unbaked situations, outstanding debts, informal employment situations, and the inability to showcase their payable capacity. We interviewed bank credit agents, financial analysts, financial educators, and small business owners to understand the main challenges to accessing credit and the main alternative criteria used to assess creditworthiness. From our research, we sensed that SBOs are not knowledgeable enough and aware of the health of their business. The lack of knowledge about their own business can impact their communication skills to show the documentation and convince credit agents of the necessity of a microloan. This demo showcases a voice-based conversational system that helps unveil SBOs of their business situation, informing a Health Business Index (HBI). The HBI can also be used as collateral by bank agents in financial institutions.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"3463 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127508516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Juan Carlos Farah, Basile Spaenlehauer, Sandy Ingram, D. Gillet
{"title":"A Blueprint for Integrating Task-Oriented Conversational Agents in Education","authors":"Juan Carlos Farah, Basile Spaenlehauer, Sandy Ingram, D. Gillet","doi":"10.1145/3543829.3544525","DOIUrl":"https://doi.org/10.1145/3543829.3544525","url":null,"abstract":"Over the past few years, there has been an increase in the use of chatbots for educational purposes. Nevertheless, the chatbot technologies and architectures that are often applied to educational contexts are not necessarily designed for such contexts. While general-purpose chatbot technologies can be used in educational contexts, there are some challenges specific to these contexts that need to be taken into consideration. Namely, chatbot technologies intended for education should, by design, integrate directly within online learning applications and focus on achieving learning goals by supporting learners with the task at hand. In this paper, we propose a blueprint for an architecture specifically aimed at integrating task-oriented chatbots to support learners in educational contexts. We then present a proof-of-concept implementation of our blueprint as a part of a code review application designed to teach programming best practices. Our blueprint could serve as a starting point for developers in education looking to build chatbot technologies targeting educational contexts and is a first step toward an open chatbot architecture explicitly tailored for learning applications.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125414455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Is Alexa like a computer? A search engine? A friend? A silly child? Yes.","authors":"Smit Desai, M. Twidale","doi":"10.1145/3543829.3544535","DOIUrl":"https://doi.org/10.1145/3543829.3544535","url":null,"abstract":"In this provocation, we analyze metaphors used by 14 end-users in semi-structured interviews to describe their interactions with Voice User Interfaces (VUIs). We identified four key metaphor groups—computer, search engine, friend, and silly child—that can help us understand how individual end-users perceive VUIs differently based on the conversational context. A consideration of these four groups draws attention to the issues with reductionist implementations of system personas and role-based performances and the problems of fixating on humanness as a metaphor. Fortunately, using metaphor analysis can also help in ideating solutions to these issues.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129526057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cross-Modal Repair: Gaze and Speech Interaction for List Advancement","authors":"Razan N. Jaber, Donald Mcmillan","doi":"10.1145/3543829.3543833","DOIUrl":"https://doi.org/10.1145/3543829.3543833","url":null,"abstract":"Interacting with long lists of instructions or ingredients continues to be a challenge for conversational interaction. In this paper, we conducted a user study to experiment with the use of ‘cued-gaze’ – waiting for the user’s visual attention – to manage the delivery of instructions with a voice agent. In a Wizard-of-Oz setting, 12 participants were instructed to build a simple Lego tower by a conversational agent and were able to advance in the list using either speech interaction, or gaze interaction. The increasing use of speech agents in real-world cause users to encounter failures in interactions, so in this task the agent was designed to fail when providing the list of instruction to explore how the participants proceeded to recover from common failures. This showed that, for this use case, cross-modality repair was more effective than reformulation of speech.","PeriodicalId":138046,"journal":{"name":"Proceedings of the 4th Conference on Conversational User Interfaces","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120955231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}