João Sedoc

João Sedoc

Auto-generated profile, based on publicly available information

João Sedoc

New York University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
YCYoung Min Cho
Young Min Cho
SRSunny Rai
Sunny Rai
LULyle Ungar
Lyle Ungar
JSJoão Sedoc
João Sedoc
SGSharath Guntuku
Sharath Guntuku
Young Min Cho, Sunny Rai, Lyle Ungar, João Sedoc, Sharath Guntuku. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

6 July 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
RWRose Weeks
Rose Weeks
LCLyra Cooper
Lyra Cooper
PSPooja Sangha
Pooja Sangha
JSJoão Sedoc
João Sedoc
SWSydney White
Sydney White
NBNaor Bar-Zeev
Naor Bar-Zeev
Background: Automated conversational agents, or chatbots, have a role in reinforcing evidence-based guidance delivered through other media and offer an accessible, individually tailored channel for public engagement. In early-to-mid 2021, young adults and minority populations disproportionately affected by COVID-19 in the United States were more likely to be hesitant toward COVID-19 vaccines, citing concerns regarding vaccine safety and effectiveness. Successful chatbot communication requires purposive understanding of user needs. Objective: We aimed to review the acceptability of messages to be delivered by a chatbot named VIRA from Johns Hopkins University. The study investigated which message styles were preferred by young, urban-dwelling Americans as well as public health workers, since we anticipated that the chatbot would be used by the latter as a job aid. Methods: We conducted 4 web-based focus groups with 20 racially and ethnically diverse young adults aged 18-28 years and public health workers aged 25-61 years living in or near eastern-US cities. We tested 6 message styles, asking participants to select a preferred response style for a chatbot answering common questions about COVID-19 vaccines. We transcribed, coded, and categorized emerging themes within the discussions of message content, style, and framing. Results: Participants preferred messages that began with an empathetic reflection of a user concern and concluded with a straightforward, fact-supported response. Most participants disapproved of moralistic or reasoning-based appeals to get vaccinated, although public health workers felt that such strong statements appealing to communal responsibility were warranted. Responses tested with humor and testimonials did not appeal to the participants. Conclusions: To foster credibility, chatbots targeting young people with vaccine-related messaging should aim to build rapport with users by deploying empathic, reflective statements, followed by direct and comprehensive responses to user queries. Further studies are needed to inform the appropriate use of user-customized testimonials and humor in the context of chatbot communication.

30 January 2023 in JMIR Human Factors
Verified
Journal Article
Open access
RWRose Weeks
Rose Weeks
PSPooja Sangha
Pooja Sangha
LCLyra Cooper
Lyra Cooper
JSJoão Sedoc
João Sedoc
SWSydney White
Sydney White
NBNaor Bar-Zeev
Naor Bar-Zeev
Background: The COVID-19 pandemic raised novel challenges in communicating reliable, continually changing health information to a broad and sometimes skeptical public, particularly around COVID-19 vaccines, which, despite being comprehensively studied, were the subject of viral misinformation. Chatbots are a promising technology to reach and engage populations during the pandemic. To inform and communicate effectively with users, chatbots must be highly usable and credible.Objective: We sought to understand how young adults and health workers in the United States assessed the usability and credibility of a web-based chatbot called Vira, created by the Johns Hopkins Bloomberg School of Public Health and IBM Research using natural language processing technology. Using a mixed method approach, we sought to rapidly improve Vira’s user experience to support vaccine decision-making during the peak of the COVID-19 pandemic.Methods: We recruited racially and ethnically diverse young people and health workers, with both groups from urban areas of the United States. We used the validated Chatbot Usability Questionnaire to understand the tool’s navigation, precision, and persona. We also conducted 11 interviews with health workers and young people to understand the user experience, whether they perceived the chatbot as confidential and trustworthy, and how they would use the chatbot. We coded and categorized emerging themes to understand the determining factors for participants’ assessment of chatbot usability and credibility.Results: In all, 58 participants completed a web-based usability questionnaire and 11 completed in-depth interviews. Most questionnaire respondents said the chatbot was “easy to navigate” (51/58, 88%) and “very easy to use” (50/58, 86%), and many (45/58, 78%) said its responses were relevant. The mean Chatbot Usability Questionnaire score was 70.2 (SD 12.1) and scores ranged from 40.6 to 95.3. Interview participants felt the chatbot achieved high usability due to its strong functionality, performance, and perceived confidentiality and that the chatbot could attain high credibility with a redesign of its cartoonish visual persona. Young people said they would use the chatbot to discuss vaccination with hesitant friends or family members, whereas health workers used or anticipated using the chatbot to support community outreach, save time, and stay up to date.Conclusions: This formative study conducted during the pandemic’s peak provided user feedback for an iterative redesign of Vira. Using a mixed method approach provided multidimensional feedback, identifying how the chatbot worked well—being easy to use, answering questions appropriately, and using credible branding—while offering tangible steps to improve the product’s visual design. Future studies should evaluate how chatbots support personal health decision-making, particularly in the context of a public health emergency, and whether such outreach tools can reduce staff burnout. Randomized studies should also be conducted to measure how chatbots countering health misinformation affect user knowledge, attitudes, and behavior.

26 June 2024 in Psychiatry Research
Verified
Journal Article
Open access
SGSalvatore Giorgi
Salvatore Giorgi
KIKelsey Isman
Kelsey Isman
TLTingting Liu
Tingting Liu
ZFZachary Fried
Zachary Fried
JSJoão Sedoc
João Sedoc
BCBrenda Curtis
Brenda Curtis
Generative Artificial Intelligence (AI) systems such as OpenAI's ChatGPT, capable of an unprecedented ability to generate human-like text and converse in real time, hold potential for large-scale deployment in clinical settings such as substance use treatment. Treatment for substance use disorders (SUDs) is particularly high stakes, requiring evidence-based clinical treatment, mental health expertise, and peer support. Thus, promises of AI systems addressing deficient healthcare resources and structural bias are relevant within this domain, especially in an anonymous setting. This study explores the effectiveness of generative AI in answering real-world substance use and recovery questions. We collect questions from online recovery forums, use ChatGPT and Meta's LLaMA-2 for responses, and have SUD clinicians rate these AI responses. While clinicians rated the AI-generated responses as high quality, we discovered instances of dangerous disinformation, including disregard for suicidal ideation, incorrect emergency helplines, and endorsement of home detox. Moreover, the AI systems produced inconsistent advice depending on question phrasing. These findings indicate a risky mix of seemingly high-quality, accurate responses upon initial inspection that contain inaccurate and potentially deadly medical advice. Consequently, while generative AI shows promise, its real-world application in sensitive healthcare domains necessitates further safeguards and clinical validation.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
TLTingting Liu
Tingting Liu
SGSalvatore Giorgi
Salvatore Giorgi
AAAnkit Aich
Ankit Aich
ALAllison Lahnala
Allison Lahnala
BCBrenda Curtis
Brenda Curtis
JSJoão Sedoc
João Sedoc
As AI chatbots increasingly incorporate empathy, understanding user-centered perceptions of chatbot empathy and its impact on conversation quality remains essential yet under-explored. This study examines how chatbot identity and perceived empathy influence users' overall conversation experience. Analyzing 155 conversations from two datasets, we found that while GPT-based chatbots were rated significantly higher in conversational quality, they were consistently perceived as less empathetic than human conversational partners. Empathy ratings from GPT-4o annotations aligned with user ratings, reinforcing the perception of lower empathy in chatbots compared to humans. Our findings underscore the critical role of perceived empathy in shaping conversation quality, revealing that achieving high-quality human-AI interactions requires more than simply embedding empathetic language; it necessitates addressing the nuanced ways users interpret and experience empathy in conversations with chatbots.

20 December 2020 in Drug and Alcohol Dependence
Verified
Journal Article
Closed access
MKMichelle R. Kaufman
Michelle R. Kaufman
ABAlicia T. Bazell
Alicia T. Bazell
ACAnne Collaco
Anne Collaco
JSJoão Sedoc
João Sedoc