Social chatbots are designed to build emotional bonds with users, and thus it is particularly
important to design these technologies so as to elicit positive perceptions from users. In the
current study, we investigate the impacts transparent explanations of chatbots’ mechanisms have
on users’ perceptions of the chatbots. A total of 914 participants were recruited from Amazon
Mechanical Turk. They were randomly assigned to observe conversation between a hypothetical
chatbot and user in one of the two-by-two experimental conditions: whether the participants
received an explanation about how the chatbot was trained and whether the chatbot was framed
as an intelligent entity or a machine. A fifth group, who believed they were observing
interactions between two humans, served as a control. Analyses of participants’ responses to
post-observation survey indicated that transparency positively affected perceptions of social
chatbots by leading users to (1) find the chatbot less creepy, (2) feel greater affinity to the
chatbot, and (3) perceive the chatbot as more socially intelligent, thought these effects were
small. Importantly, transparency appeared to have a larger effect in increasing the perceived
social intelligence among participants with lower prior AI knowledge. These findings have
implications for the design of future social chatbots and support the addition of transparency and
explanation for chatbot users.
more »
« less
CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation
In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.
more » « less- Award ID(s):
- 2125183
- NSF-PAR ID:
- 10472694
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- Proceedings of the ACM on Human-Computer Interaction
- Volume:
- 7
- Issue:
- CSCW1
- ISSN:
- 2573-0142
- Page Range / eLocation ID:
- 1 to 32
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, in particular, conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying question have been recently studied in the literature. However, accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we propose a neural network model based on a novel attention mechanism, called multi source attention network. Our model learns a representation for a user-system conversation that includes clarifying questions. In more detail, with the help of multiple information sources, our model weights each term in the conversation. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. We evaluate our models using a public dataset for search clarification. Our experiments demonstrate significant improvements compared to competitive baselines.more » « less
-
Background Chatbots are being piloted to draft responses to patient questions, but patients’ ability to distinguish between provider and chatbot responses and patients’ trust in chatbots’ functions are not well established. Objective This study aimed to assess the feasibility of using ChatGPT (Chat Generative Pre-trained Transformer) or a similar artificial intelligence–based chatbot for patient-provider communication. Methods A survey study was conducted in January 2023. Ten representative, nonadministrative patient-provider interactions were extracted from the electronic health record. Patients’ questions were entered into ChatGPT with a request for the chatbot to respond using approximately the same word count as the human provider’s response. In the survey, each patient question was followed by a provider- or ChatGPT-generated response. Participants were informed that 5 responses were provider generated and 5 were chatbot generated. Participants were asked—and incentivized financially—to correctly identify the response source. Participants were also asked about their trust in chatbots’ functions in patient-provider communication, using a Likert scale from 1-5. Results A US-representative sample of 430 study participants aged 18 and older were recruited on Prolific, a crowdsourcing platform for academic studies. In all, 426 participants filled out the full survey. After removing participants who spent less than 3 minutes on the survey, 392 respondents remained. Overall, 53.3% (209/392) of respondents analyzed were women, and the average age was 47.1 (range 18-91) years. The correct classification of responses ranged between 49% (192/392) to 85.7% (336/392) for different questions. On average, chatbot responses were identified correctly in 65.5% (1284/1960) of the cases, and human provider responses were identified correctly in 65.1% (1276/1960) of the cases. On average, responses toward patients’ trust in chatbots’ functions were weakly positive (mean Likert score 3.4 out of 5), with lower trust as the health-related complexity of the task in the questions increased. Conclusions ChatGPT responses to patient questions were weakly distinguishable from provider responses. Laypeople appear to trust the use of chatbots to answer lower-risk health questions. It is important to continue studying patient-chatbot interaction as chatbots move from administrative to more clinical roles in health care.more » « less
-
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.more » « less
-
Aim/Purpose: The purpose of this paper is to explore the efficacy of simulated interactive virtual conversations (chatbots) for mentoring underrepresented minority doctoral engineering students who are considering pursuing a career in the professoriate or in industry. Background: Chatbots were developed under the National Science Foundation INCLUDES Design and Developments Launch Pilot award (17-4458) and provide career advice with responses from a pre-programmed database populated by renowned emeriti engineering faculty. Chatbots have been engineered to fulfill a myriad of roles, such as undergraduate student advisement, but no research has been found that addresses their use with supplemental future faculty mentoring for doctoral students.Methodology: Chatbot efficacy is examined through a phenomenological design with focus groups with underrepresented minority doctoral engineering students. No theoretical or conceptual frameworks exist relative to chatbots designed for future faculty mentoring; therefore, an adaptation and implementation of the conceptual model posited on movie recommendations was utilized to ground this study. The four-stage process of phenomenological data analysis was followed: epoché, horizontalization, imaginative variation, and synthesis.Contribution: No studies have investigated the utility of chatbots in providing supplemental mentoring to future faculty. This phenomenological study contributes to this area of investigation and provides greater consideration into the unmet mentoring needs of these students, as well as the potential of utilizing chatbots for supplementary mentoring, particularly for those who lack access to high quality mentoring.Findings: Following the data analysis process, the essence of the findings was, while underrepresented minority doctoral engineering students have ample unmet mentoring needs and overall are satisfied with the user interface and trustworthiness of chatbots, their intent to use them is mixed due to a lack of personalization in this type of supplemental mentoring relationship.Recommendations for Practitioners: One of the major challenges faced by underrepresented doctoral engineering students is securing quality mentoring relationships that socialize them into the engineering culture and community of practice. While creating opportunities for students and incentivizing faculty to engage in the work of mentoring is needed, we must also consider the ways in which to leverage technology to offer supplemental future faculty mentoring virtually. Recommendation for Researchers: Additional research on the efficacy of chatbots in providing career-focused mentoring to future faculty is needed, as well as how to enhance the functionality of chatbots to create personal connections and networking opportunities, which are hallmarks of traditional mentoring relationships.Impact on Society: An understanding of the conceptual pathway that can lead to greater satisfaction with chatbots may serve to expand their use in the realm of mentoring. Scaling virtual faculty mentoring opportunities may be an important breakthrough in meeting mentoring needs across higher education.Future Research: Future chatbot research must focus on connecting chatbot users with human mentors; standardizing the process for response creation through additional data collection with a cadre of diverse, renowned faculty; engaging subject matter experts to conduct quality verification checks on responses; testing new responses with potential users; and launching the chatbots for a broad array of users.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3579469
