Chatbots are often designed to mimic social roles attributed to humans. However, little is known about the impact of using language that fails to conform to the associated social role. Our research draws on sociolinguistic to investigate how a chatbot’s language choices can adhere to the expected social role the agent performs within a context. We seek to understand whether chatbots design should account for linguistic register. This research analyzes how register differences play a role in shaping the user’s perception of the human-chatbot interaction. We produced parallel corpora of conversations in the tourism domain with similar content and varying register characteristics and evaluated users’ preferences of chatbot’s linguistic choices in terms of appropriateness, credibility, and user experience. Our results show that register characteristics are strong predictors of user’s preferences, which points to the needs of designing chatbots with register-appropriate language to improve acceptance and users’ perceptions of chatbot interactions.
The increasing globalization of corporate economies has changed the face of engineering practice. In addition to core engineering skills, modern engineers must possess cross-cultural communication skills, team management skills, and the ability to perform on geographicallydistributed teams. In a 2003 ASEE paper 5 , we described a novel curricular paradigm called the Global Engineering College (GEC), based on the idea of seamlessly combining the curricula and educational opportunities of several internationally-distributed engineering institutions to create a virtual engineering college spanning multiple countries and cultures. In this paper, we report on our experiences piloting the key elements of this model under an NSF planning grant, focusing on the obstacles encountered, and solutions developed to address them.
Purpose and Approach Women in recovery describe stigma, negative treatment, and limited support as barriers to achieving their health and parenting goals. Mobile health technologies carefully tailored to support the unique needs of recovery communities can provide less burdensome alternatives to in-person services for women transitioning out of substance use treatment. An iterative design process integrated women’s interests into the structure, content, and interaction flow of a mobile health (mHealth) app. Setting and Participants Participants included women in recovery from opioid, alcohol, and polysubstance use disorders in a comprehensive housing program in urban Arizona. Methods Five focus groups with 3–7 participants each (n = 27 total) informed creation of the mHealth app. Informed by theoretical models of usability and person-centered design, development involved an iterative series of focus groups in which we asked women to comment on interest in using each feature. This provided a qualitative priority framework for feature development. We then modified the app and repeated the process to gauge consensus and continually refine our prototype. Results Women were interested in access to resources, such as housing, counseling, and parenting advice in settings known to treat women in recovery with respect. They also asked for positive messages, chatting with peers, and access to expert answers. They were less interested in points-based learning modules and “scored” activities, leading us to develop a “daily challenges” concept that builds good habits, but does not feel like “classwork”. Women’s recommendations shaped an mHealth app tailored to maximize utility, access, and safety for this at-risk population. Conclusion Integration of user-centered design with applied ethnographic techniques guided the development of a custom-tailored mHealth app responsive to lived experiences and needs of women in recovery. Future research should evaluate the potential for user-centered apps to increase self-efficacy, perceived social support, and to reduce risk of relapse.
Chatbots are often designed to mimic social roles attributed to humans. However, little is known about the impact on user's perceptions of using language that fails to conform to the associated social role. Our research draws on sociolinguistic theory to investigate how a chatbot's language choices can adhere to the expected social role the agent performs within a given context. In doing so, we seek to understand whether chatbots design should account for linguistic register. This research analyzes how register differences play a role in shaping the user's perception of the human-chatbot interaction. Ultimately, we want to determine whether register-specific language influences users' perceptions and experiences with chatbots. We produced parallel corpora of conversations in the tourism domain with similar content and varying register characteristics and evaluated users' preferences of chatbot's linguistic choices in terms of appropriateness, credibility, and user experience. Our results show that register characteristics are strong predictors of user's preferences, which points to the needs of designing chatbots with register-appropriate language to improve acceptance and users' perceptions of chatbot interactions.CCS Concepts: • Human-centered computing → Human computer interaction (HCI); Empirical studies in HCI; Natural language interfaces.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.