Designing Personalities of Conversational Agents

Kim, Hankyung; Koh, Dong Yoon; Lee, Ga Eun; Park, Jung-Mi; Lim, Youn-kyung

doi:10.1145/3290607.3312887

Cited by 16 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a chatbot can address cultural compatibility and linguistic barriers by providing multilingual options and culturally-sensitive dialogues. 39 In the context of current practices to adequately address social needs, 40 chatbots can act as supportive adjuncts, supplementing and enhancing these efforts. Furthermore, chatbots can play an educational role in assisting families in understanding and accessing resources, steering them through self-referral processes, eligibility assessments, and online resource navigation.…”

Section: Discussionmentioning

confidence: 99%

Chatbot for social needs screening and resource sharing with vulnerable families: Iterative design and evaluation study

Sezgin,

Kocaballi,

Dolce

et al. 2023

Preprint

View full text Add to dashboard Cite

Health outcomes are significantly influenced by unmet social needs. Although screening for unmet social needs has become common in healthcare settings, there is often poor linkage to resources after needs are identified. The structural barriers (e.g., staffing, time, space) to helping address social needs could be overcome by a technology-based solution. This study presents the design and evaluation of a chatbot, DAPHNE©, that screens for social needs and links patients to resources. This study used a two-step approach: (1) iterative design with interdisciplinary stakeholder groups and (2) feasibility and usability assessment. Virtual sessions were held with an interdisciplinary group of stakeholders (n=10) using thematic and content analysis to inform the chatbot's design and development. Evaluation included an online survey, focus group interviews, and scenario-based usability testing with community health workers (family advocates) (n=4) and social workers (n=9). The stakeholders emphasized the importance of provider-technology collaboration, inclusive conversational design, and user education. Users found the chatbot's capabilities met expectations and the chatbot was easy to use (System Usability Scale score=72). The stakeholders raised concerns about accuracy of suggested resources, electronic health record integration, and trust with a chatbot. Future research should examine effectiveness, cost- effectiveness, and scalability of chatbot interventions to address social needs.

show abstract

Section: Discussionmentioning

confidence: 99%

Chatbot for social needs screening and resource sharing with vulnerable families: Iterative design and evaluation study

Sezgin,

Kocaballi,

Dolce

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In addition, a chatbot can address cultural compatibility and linguistic barriers by providing multilingual options and culturally-sensitive dialogues. [47] In the context of current practices to adequately address social needs, [48] chatbots can act as supportive adjuncts, supplementing and enhancing these efforts. Furthermore, chatbots can play an educational role in assisting families in understanding and accessing resources, steering them through self-referral processes, eligibility assessments, and online resource navigation.…”

Section: Principal Findingsmentioning

confidence: 99%

Chatbot for Social Need Screening and Resource Sharing With Vulnerable Families: Iterative Design and Evaluation Study

Sezgin,

Kocaballi,

Dolce

et al. 2024

JMIR Hum Factors

View full text Add to dashboard Cite

Background: Health outcomes are significantly influenced by unmet social needs. Although screening for unmet social needs has become common in healthcare settings, there is often poor linkage to resources after needs are identified. The structural barriers (e.g., staffing, time, space) to helping address social needs could be overcome by a technology-based solution.Objective: This study presents the design and evaluation of a chatbot, DAPHNE©, that screens for social needs and links patients to resources. Methods:This study used a two-step approach: (1) iterative design with interdisciplinary stakeholder groups and (2) feasibility and usability assessment. Virtual sessions were held with an interdisciplinary group of stakeholders (n=10) using thematic and content analysis to inform the chatbot's design and development. Evaluation included an online survey, focus group interviews, and scenario-based usability testing with community health workers (family advocates) (n=4) and social workers (n=9). Results:The stakeholders emphasized the importance of provider-technology collaboration, inclusive conversational design, and user education. Users found the chatbot's capabilities met expectations and the chatbot was easy to use (System Usability Scale score=72). The stakeholders raised concerns about accuracy of suggested resources, electronic health record integration, and trust with a chatbot. Conclusions:Chatbots can provide personalized feedback platforms for families to identify and meet social needs. Our study highlights the importance of user-centered iterative design and development of chatbots for social needs. Future research should examine efficacy, cost-effectiveness, and scalability of chatbot interventions to address social needs.

show abstract

“…Chatbot personality is defined as the stable pattern that dictates the behaviour of a CA [13,70,62], playing a crucial role in its perception by users and its level of acceptability [58], even possibly determining whether users will wish to interact with the chatbot again. [13] Personality can be embedded into a CA by using different channels [33], e.g. what contents it provides and how it speaks, and expressed by different linguistic styles [48].…”

Section: Chatbot Gender and Personalitymentioning

confidence: 99%

The Impact of Gender and Personality in Human-AI Teaming: The Case of Collaborative Question Answering

Milella,

Natali,

Scantamburlo

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper discusses the results of an exploratory study aimed at investigating the impact of conversational agents (CAs) and specifically their agential characteristics on collaborative decision-making processes. The study involved 29 participants divided into 8 small teams engaged in a question-and-answer trivia-style game with the support of a text-based CA, characterized by two independent binary variables: personality (gentle and cooperative vs blunt and uncooperative) and gender (female vs male). A semi-structured group interview was conducted at the end of the experimental sessions to investigate the perceived utility and level of satisfaction with the CAs. Our results show that when users interact with a gentle and cooperative CA, their user satisfaction is higher. Furthermore, female CAs are perceived as more useful and satisfying to interact with than male CAs. We show that group performance improves through interaction with the CAs, confirming that a stereotype favoring the female with a gentle and cooperative personality combination exists in regard to perceived satisfaction, even though this does not lead to greater perceived utility. Our study extends the current debate about the possible correlation between CA characteristics and human acceptance and suggests future research to investigate the role of gender bias and related biases in human-AI teaming.

show abstract

Designing Personalities of Conversational Agents

Cited by 16 publications

References 7 publications

Chatbot for social needs screening and resource sharing with vulnerable families: Iterative design and evaluation study

Chatbot for social needs screening and resource sharing with vulnerable families: Iterative design and evaluation study

Chatbot for Social Need Screening and Resource Sharing With Vulnerable Families: Iterative Design and Evaluation Study

The Impact of Gender and Personality in Human-AI Teaming: The Case of Collaborative Question Answering

Contact Info

Product

Resources

About