Use Of Chatbots Research Articles

The Double-Edged Sword: Political Engagement on Social Media and Its Impact on Democracy Support in Authoritarian Regimes

Utilizing data from the Arab Barometer surveys, this study distinguishes between social media and the internet’s general use and their usage for political purposes, examining whether political engagement—obtaining political information and expressing political opinions—on these platforms bolsters or undermines democracy in authoritarian contexts. Initially, political engagement on social media and the internet was positively linked with support for democracy. However, this has recently turned negative, probably reflecting the rise of digital authoritarianism (authoritarian regimes’ use of digital technology to surveil, repress, and manipulate both domestic and foreign populations). This paper argues that there are two potential mechanisms for this: self-censorship and social learning. Self-censorship suggests that individuals critical of the regime may refrain from expressing their political views on social media. Social learning involves acquiring information and forming beliefs through observation and interaction on these platforms. Both phenomena are influenced by digital authoritarianism in two primary ways: First, surveillance and repression by authoritarian regimes suppress political discussion, fostering conformity. Second, tactics like misinformation campaigns, use of chatbots, and artificial intelligence allow authoritarians to flood social media with propaganda, facilitating social learning of authoritarian values. This dynamic is particularly pronounced among those who already trust and support their government.

Enhancing Information Technology Governance in Universities: A Smart Chatbot System based on Information Technology Infrastructure Library

The rapid evolution of information and communication technologies has created a pressing need for higher education institutions to modernize their Information Technology (IT) governance practices. This article proposes an innovative solution to enhance the governance and efficiency of IT services while optimizing and personalizing user experience. The proposed solution consists of a chatbot using Artificial Intelligence (AI) and Natural Language Processing (NLP) combined with the Information Technology Infrastructure Library (ITIL) standard to automate the management of IT services in the digital work environment (ENT). Intended for students, teachers, and administrators, this chatbot provides reactive support by responding to requests, reducing waiting times, and improving satisfaction. It also helps decrease operational costs and the workload of support teams by autonomously handling recurring requests. Beyond efficiency improvements, the chatbot contributes significantly to IT governance by providing structured service management, improving decision-making through real-time data, and supporting compliance with governance frameworks. An online survey conducted among 120 students revealed slow processing of requests and unavailability of services, justifying the need for this chatbot. The chatbot was designed with advanced NLP and Machine Learning (ML) technologies. Preliminary tests demonstrate the chatbot’s response reliability, with an accuracy rate of 96% and a response time decrease to an average of 4.17 seconds. The use of chatbots has considerable potential for universities to improve the efficiency of digital services offered to students.

Perceptions and usage of AI chatbots among students in higher education across genders, academic levels and fields of study

AI chatbots have ignited discussions and controversies about their impact on teaching and learning practices in higher education. This study explores students’ adoption and perceptions of ChatGPT and other AI chatbots in higher education. Based on survey data from a large sample (n=5,894) across Swedish universities, the study employs descriptive statistical methods to analyze usage, attitudes, and concerns, and inferential statistics to identify relations between attitudes and usage and background variables (gender, academic level, and field of study). The results reveal broad awareness and use of ChatGPT among students, but not of other AI chatbots. More than half of the students expressed positive attitudes towards the use of chatbots in education, but almost as many expressed concerns about future use. Statistically significant differences were found across all examined grouping variables, particularly between genders and fields of study. Female students and students from the humanities and medicine consistently expressed more negative attitudes and concerns about AI's role in learning and assessment, while males and technology and engineering students showed higher usage and optimism. These findings not only validate the continued relevance of student backgrounds as a determinant of technology adoption but also expose several challenges and considerations surrounding AI and chatbot usage in education. The study supports the development of local solutions to AI in education tailored to student attributes and needs, and it provides insights for developers, educators, and policymakers.

Chatbots in Cybersecurity: Enhancing Security Chatbot Efficacy through Iterative Feedback Loops and User-Centric Approaches

Chatbots are of continuous importance in our interactive lives. Although used in several domains, there are questions about its security assurance; therefore, there is a need to know its capabilities, limitations, and challenges in cybersecurity. The research explores the use of chatbots in enhancing cyber defences and their potentials. It examines chatbots’ current applications in cybersecurity, including IT services, information protection, and user education. Furthermore, the research proposes implementing an Intelligent Chatbot Security Assistant (ICSA) model on WhatsApp to detect and respond to cyberattacks based on user conversations and identifies the challenges with this implementation. To address these challenges, it suggests incorporating enhanced privacy measures, real-time monitoring, rigorous evaluation and validation, and concludes with user-centric design principles using iterative feedback. This research provides valuable insights into the use of chatbots in cybersecurity, their current level of research and implementation as a cybersecurity tool, and directions for future research.

A matter of time and space: reflections on the use of chatbots to assist the collection of audio diaries during the COVID-19 pandemic in Brazil

ABSTRACT The use of qualitative audio diaries in research allows people to generate multi-occasion reports of events in their natural, spontaneous contexts in a recorded audio format. Recent technological advances have enabled more rapid, spontaneous means for audio diaries recordings, such as smartphones. This article reports on methodological insights regarding the feasibility and contributions of using chatbots – digital systems that provide an interface for interaction with users that emulate human conversation – to assist the collection of audio diaries. We describe the development of a WhatsApp chatbot for the remote collection and sharing of audio files using a diary format. Methodological considerations are presented, drawing from the results of a remote collection of spoken reports from 19 Brazilian undergraduate students who were experiencing social isolation due to COVID-19 pandemic-related containment measures. Results emphasize the temporal aspect of the data collection process, and indicate that the tool allowed participants to generate accounts depicting changes in their understanding of perceptions and experiences over time. Although leveraging digital technology and conversational-like features of chatbots may promote greater participation and less participant burden, results also suggest that using pre-scripted prompts in the form of open questions may pose a challenge for reflexive engagement with audio diaries.

فاعلية توظيف العلاقات العامة لربورتات الدردشة في التعريف بالخدمات في المؤسسات الحكومية

The study aimed to describe the effectiveness of employing public relations for chat bots in defining services in government institutions, by knowing the manifestations of public relations practitioners' interest in knowing information about chat bots and employing them in defining services in government institutions, services and areas of use, as well as the benefits achieved and the obstacles they face in this field, reaching their suggestions and their evaluation of the impact of these applications on their professional competence, and the future of public relations in light of chat bots. The study used the descriptive approach, and among the tools, the interview was used, and a questionnaire on the reality of public relations practitioners' use of chat bots in defining services in government institutions. The study sample consisted of (240) employees in the Corporate Communications and Public Relations Department in government institutions. As for the results of the study, it showed great interest from public relations practitioners in government institutions in chat bots and their use in managing corporate communication, as their aspects of use varied between crisis management and meeting the needs of the public. These technologies have contributed to improving the professional efficiency of most of the respondents by enhancing daily performance, speed of accomplishment, planning and decision-making. However, users faced challenges such as the difficulty of robots understanding customer feelings and fear of losing jobs. They suggested linking promotion to their ability to use them and provide training and technical support. Despite the benefits of robots, there are still concerns about the future of the public relations profession in light of this technology.

Designing an Chatbot with NLP Technology in a Website-Based New Student Admission Information System

In the fast pace of digitalization, student admission information system websites face the challenge of providing responsive and quality services to applicants. One emerging solution is the use of chatbots, which enable automated interaction with customers. Technology continues to transform over time. At SMK Insan Teknologi (InTek), the service process is still manual, such as physical archives for student registration, incomplete information, and the absence of an official website. To improve administration and data access, a web-based information system is offered. While the Chatbot helps in interactive services and time efficiency to answer registrants' questions, NLP is used to make the conversation in the chat more natural and easy to understand by registrants. The results of testing the system show that the system functions properly in responding to messages sent through the chatbot on the website both from the message text according to the intent, as well as abstract text and not according to the pattern with an accuracy rate of 87,5%. It is hoped that this research can improve the quality of service and administrative efficiency at SMK Insan Teknologi and can be applied in other educational institutions.

Business and Customer-Based Chatbot Activities: The Role of Customer Satisfaction in Online Purchase Intention and Intention to Reuse Chatbots

In the online shopping context, brands aim to achieve a high level of profit by providing better customer satisfaction by using various artificial intelligence tools. They try creating a satisfactory customer experience by creating a system that provides never-ending customer support by using dialog-based chatbots, especially in the field of customer service. However, there is a lack of research investigating the impact of business and customer-based chatbot activities together on online purchase intention and the intention to reuse chatbots. This research considers the use of chatbots as a marketing tool from both customer and business perspectives and aims to determine the factors that affect the customers’ intention to purchase online and reuse chatbots. Accordingly, the impact on customer satisfaction with chatbot usage, which is based on chatbots’ communication quality and customers’ motivations to use chatbots, on online purchase intention and intention to reuse chatbots was examined. Through an online questionnaire with two hundred and ten participants, employing structural equation modeling, we revealed that customer satisfaction with chatbot usage has a greater impact on the intention to reuse chatbots than on online purchase intentions. In addition, chatbot communication quality has a greater impact on customer satisfaction with chatbot usage than customers’ motivation to use chatbots. To solidify these findings, confirmatory factor analysis, along with reliability and validity assessments, were implemented within the analytical framework to provide robust support for the study’s hypotheses. These findings not only provide empirical evidence and implications for companies in online shopping but also extend the understanding of AI tools in marketing, highlighting their subtle impact on consumer decision-making in the dynamic digital marketplace.

Impact of ChatGPT and generative AI on lifelong learning and upskilling learners in higher education: unveiling the challenges and opportunities globally

PurposeA gripping keyword emerged in the dynamic world of 2022: GPT or the advent of Generative Artificial Intelligence (GAI), at its forefront, embodied by the mysterious ChatGPT. This technological marvel had been silently lurking in the background for just over five years. However, all of a sudden, it emerged onto the scene, capturing the public’s attention and quickly becoming one of the most widely adopted inventions in history. Therefore, this narrative review is conducted in order to explore the impact of generative AI and ChatGPT on lifelong learning and upskilling of students in higher education and address opportunities and challenges proposed by Artificial Intelligence from a global perspective.Design/methodology/approachThis review has been conducted using a narrative literature review approach. For in-depth identification of research gaps, 105 relevant articles were included from scholarly databases such as Scopus, Web of Science, ERIC and Google Scholar. Seven major themes emerged from the literature to answer the targeted research questions that describe the use of AI, the impact of generative AI and ChatGPT on students, the challenges and opportunities of using AI in education and mitigating strategies to cope with the challenges associated with the integration of ChatGPT and generative AI in education.FindingsThe review of the literature presents that generative AI and ChatGPT have gained a lot of recognition among students and have revolutionized educational settings. The findings suggest that there are some contexts in which adult education research and teaching can benefit from the use of chatbots and generative AI technologies like ChatGPT. The literature does, however, also highlight the necessity of carefully considering the benefits and drawbacks of these technologies in order to prevent restricting or distorting the educational process or endangering academic integrity. In addition, the literature raises ethical questions about data security, privacy and cheating by students or researchers. To these, we add our own ethical concerns about intellectual property, such as the fact that, once we enter ideas or research results into a generative chatbot, we no longer have control over how it is used.Practical implicationsThis review is helpful for educators and policymakers to design the curriculum and policies that encourage students to use generative AI ethically while taking academic integrity into account. Also, this review article identifies the major gaps that are associated with the impact of AI and ChatGPT on the lifelong learning skills of students.Originality/valueThis review of the literature is unique because it explains the challenges and opportunities of using generative AI and ChatGPT, also defining its impact on lifelong learning and upskilling of students.

СУЧАСНИЙ ІНТЕРНЕТ-МАРКЕТИНГ З ВИКОРИСТАННЯМ ТЕХНОЛОГІЙ ШТУЧНОГО ІНТЕЛЕКТУ

The article discusses the essence and features of modern Internet marketing based on the use of artificial intelligence (AI) technologies. The article examines how AI can help online marketers collect and analyze consumer data, segment and personalize audiences, create and distribute effective content, optimize and automate advertising campaigns, and measure and improve marketing results. The article also analyzes the latest trends in the use of AI technologies by Ukrainian and foreign companies and identifies their advantages.The investigation identified effective AI tools in online marketing, such as chatbots, recommender systems, text generators, sentiment analysers, face and speech recognition systems, etc. The article presents a comparison of AI tools in online marketing of Ukrainian and foreign companies. Foreign companies use modern products that have no analogues in Ukraine. This is due to the popularity of the trend of using AI technologies in foreign companies. In Ukraine, this trend is developing and we can see it in the use of chatbots and CRM systems. They have been implemented by such companies as PrivatBank and Promodo. Despite this, the development of foreign companies is progressive. Previously, only large corporations could afford to use AI technologies, but now young startups are catching up with the trend. AI combined with human capabilities can actually turn business into a universal tool for profit. However, this path is not without obstacles, so the article highlights the challenges of AI that may affect the economic, legal, ethical, and social spheres of life. Scenarios for preventing possible problems allow for the effective use of AI's potential. The article suggests measures that should help society adapt to changes in the socio-economic environment associated with the displacement of humans by AI. It is important to understand the advantages and disadvantages of modern online marketing tools to ensure effective solutions to business problems.

Impact of Chatbots on Satisfaction and Loyalty in Lima's Telecom Sector

The migration towards digital environments has transformed the expectations of consumers, who now not only look for quality products and services, but also convenience, personalization and efficiency in each interaction with the brand. This change presents significant challenges for companies, as they need to constantly adapt to meet their needs and thus maintain loyalty in a highly competitive market. The pressure to offer added value and maintain customer preference is intensified by the ease with which consumers switch to competitors. which drives companies to innovate and adapt AI such as chatbots, which could be the answer to this challenge. The objective of this research work is to know if the use of chatbots positively influences the satisfaction and perceived loyalty of consumers of telephone services, since in this case the speed, quality of the service and the customer's need for understanding. They are critical and represent a greater challenge to differentiate. The methodology used for this research maintains a quantitative, correlational, non-experimental approach. The type of sampling was non-probabilistic, and the strategy was snowball. The instrument used was a questionnaire with a sample of around 130 consumers in the city of Metropolitan Lima in Peru. The findings suggest that chatbots are not only innovative tools, but also strategic ones for telephone companies seeking to improve customer satisfaction and loyalty. The implementation of appropriate chatbots can transform the customer experience, providing a more agile, personalized and effective service, thus seeing a close relationship between the dimensions of the chatbot with the satisfaction and loyalty perceived in consumers. In a world where these variables are key to business survival, chatbots represent an opportunity to create exceptional experiences. Uncover how cutting-edge AI chatbots are revolutionising customer satisfaction and loyalty in the competitive telephone service industry, offering transformative, personalised, and efficient interactions.

Infinite Potential of AI Chatbots: Enhancing User Experiences and Driving Business Transformation in E-commerce: Case of Palestinian E-Commerce

In the much-evolving digital age landscape, it is difficult to overlook artificial intelligence's enormous role in people. This study entails an empirical examination of the impact of AI-powered chatbots on improving customer experience, customer satisfaction, and potential benefits in the digital era. This study was handled by the use of quantitative data collection methods through an online survey from 221 online users of AI-powered chatbots in Palestine. The collected data was then analyzed using descriptive statistics and structural equation modeling techniques. According to the results, it was shown that service quality significantly influenced the intention to use chatbots by customers or users thus indirectly influencing the net benefits enjoyed by users in the digital era. Similarly, the service quality provided by AI-powered chatbots was found to significantly influence the intention to use them, thus indirectly influencing the net benefits of AI-powered chatbots. Additionally, service quality was found to influence user satisfaction with chatbots, which indirectly influenced the net benefits enjoyed by users/customers in the digital era. On the other hand, user satisfaction significantly and directly influenced the net benefits of AI-powered chatbots in the digital era. In this regard, this study significantly contributed to the AI-powered chatbot's body of knowledge in the Palestinian digital context by identifying the factors that influence the use of chatbots in the digital era from the users’ point of view with the capacity to help transform the Palestinian business landscape

Interruption Audio & Transcript: Derived from Group Affect and Performance Dataset

Despite the widespread development and use of chatbots, there is a lack of audio-based interruption datasets. This study provides a dataset of 200 manually annotated interruptions from a broader set of 355 data points of overlapping utterances. The dataset is derived from the Group Affect and Performance dataset managed by the University of the Fraser Valley, Canada. It includes both audio files and transcripts, allowing for multi-modal analysis. Given the extensive literature and the varied definitions of interruptions, it was necessary to establish precise definitions. The study aims to provide a comprehensive dataset for researchers to build and improve interruption prediction models. The findings demonstrate that classification models can generalize well to identify interruptions based on this dataset’s audio. This opens up research avenues with respect to interruption-related topics, ranging from multi-modal interruption classification using text and audio modalities to the analysis of group dynamics.

Identity Disclosure and Anthropomorphism in Voice Chatbot Design: A Field Experiment

Fueled by the widespread adoption of algorithms and artificial intelligence, the use of chatbots has become increasingly popular in various business contexts. In this paper, we study how to effectively and appropriately use voice chatbots, particularly by leveraging the two design features identity disclosure and anthropomorphism, and evaluate their impact on the firm operational performance. In collaboration with a large truck-sharing platform, we conducted a field experiment that randomly assigned 11,000 truck drivers to receive outbound calls from the voice chatbot dispatcher of our focal platform. Our empirical results suggest that disclosing the identity of the chatbot at the beginning of the conversation negatively affects operational performance, leading to around 11% reduction in the response probability. However, humanizing the voice chatbot by adding our proposed anthropomorphism features (i.e., interjections and filler words) significantly improves response probability, conversation length, and the probability of order acceptance intention by over 5.6%, 24.9%, and 10.1%, respectively. Moreover, even when the chatbot’s identity is disclosed along with humanizing features, the operational outcomes still improve. This finding suggests that enhancing anthropomorphism may potentially counteract the negative effects of chatbot identity disclosure. Finally, we propose one plausible explanation for the performance improvement—the enhanced trust between humans and algorithms—and provide empirical evidence that drivers are more likely to disclose information to chatbot dispatchers with anthropomorphism features. Our proposed anthropomorphism improvement solutions are currently being implemented and utilized by our collaborator platform. This paper has been This paper was accepted by Felipe Caro for the Special Issue on the Human-Algorithm Connection. Funding: This study is supported by the National Natural Science Foundation of China [Grants 72172169 and 91646125], Program for Innovation Research at the Central University of Finance and Economic, and Shanghai Pujiang Program. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.03833 .

AI-driven Strategies for Enhancing MSME Sales and Business Communication: A Case Study

This research is motivated by the challenges faced by Micro, Small, and Medium Enterprises (MSMEs) in Indonesia in adopting artificial intelligence (AI) technology to enhance sales and business sustainability. The objective of this study is to examine the impact of AI adoption on the operational efficiency and sales of MSMEs, as well as to identify the challenges encountered in implementing this technology. The research methods used include in-depth interviews with ten MSME owners and a questionnaire survey involving 50 MSME participants. The findings indicate that AI implementation, particularly through the use of chatbots and data analytics for marketing, significantly enhances operational efficiency and sales, with approximately 70% of respondents reporting increased sales. However, the study also identifies key challenges such as high implementation costs, limited technological literacy, and uneven digital infrastructure. The conclusion emphasizes the importance of support from the government and relevant institutions in providing financial incentives and training programs to encourage broader AI adoption among MSMEs.

AI-Driven Patient Education in Chronic Kidney Disease: Evaluating Chatbot Responses against Clinical Guidelines.

Chronic kidney disease (CKD) patients can benefit from personalized education on lifestyle and nutrition management strategies to enhance healthcare outcomes. The potential use of chatbots, introduced in 2022, as a tool for educating CKD patients has been explored. A set of 15 questions on lifestyle modification and nutrition, derived from a thorough review of three specific KDIGO guidelines, were developed and posed in various formats, including original, paraphrased with different adverbs, incomplete sentences, and misspellings. Four versions of AI were used to answer these questions: ChatGPT 3.5 (March and September 2023 versions), ChatGPT 4, and Bard AI. Additionally, 20 questions on lifestyle modification and nutrition were derived from the NKF KDOQI guidelines for nutrition in CKD (2020 Update) and answered by four versions of chatbots. Nephrologists reviewed all answers for accuracy. ChatGPT 3.5 produced largely accurate responses across the different question complexities, with occasional misleading statements from the March version. The September 2023 version frequently cited its last update as September 2021 and did not provide specific references, while the November 2023 version did not provide any misleading information. ChatGPT 4 presented answers similar to 3.5 but with improved reference citations, though not always directly relevant. Bard AI, while largely accurate with pictorial representation at times, occasionally produced misleading statements and had inconsistent reference quality, although an improvement was noted over time. Bing AI from November 2023 had short answers without detailed elaboration and sometimes just answered "YES". Chatbots demonstrate potential as personalized educational tools for CKD that utilize layman's terms, deliver timely and rapid responses in multiple languages, and offer a conversational pattern advantageous for patient engagement. Despite improvements observed from March to November 2023, some answers remained potentially misleading. ChatGPT 4 offers some advantages over 3.5, although the differences are limited. Collaboration between healthcare professionals and AI developers is essential to improve healthcare delivery and ensure the safe incorporation of chatbots into patient care.

Artificial Intelligence: A Help or Hindrance to Scientific Writing?

We have assessed the chatbot Generative Pretrained Transformer, a type of artificial intelligence software designed to simulate conversations with human users, in an experiment designed to test its relevance to scientific writing. chatbot Generative Pretrained Transformer could become a promising and powerful tool for tasks such as automated draft generation, which may be useful in academic activities to make writing work faster and easier. However, the use of this tool in scientific writing raises some ethical concerns and therefore there have been calls for it to be regulated. It may be difficult to recognize whether an abstract or paper is written by a chatbot or a human being because chatbots use advanced techniques, such as natural language processing and machine learning, to generate text that is similar to human writing. To detect the author is a complex task and requires thorough critical reading to reach a conclusion. The aim of this paper is, therefore, to explore the pros and cons of the use of chatbots in scientific writing.

Investigation of users’ opinions, perceptions and attitudes towards the use of artificial intelligence in online learning environments

Abstract The impact and importance of AI are being increasingly recognised, although there are still uncertainties regarding its innovative potential. These same uncertainties and effects are also evident in educational contexts. In this study, teacher, student and parents’ opinions, perceptions and attitudes towards the use of AI in online education were examined through a systematic review of the literature on AI applications in online learning environments. Quantitative data on AI studies in education, the role of AI in education and teacher, student and parents’ opinions, perceptions and attitudes towards AI were compiled. The study outcomes present an overview of AI’s role in education and offer recommendations for researchers in this field. In line with the findings, the role of AI in education is divided into six categories, namely ‘chatbot, content, learning assistant, learning incentive, measurement and evaluation, and early warning system’. The study’s results indicate that students hold favourable opinions towards AI applications, particularly in relation to chatbots, adaptive learning techniques and automatic assessment methods. They appreciate the support, friendship and easy use of chatbots. Students perceive AI as a tool that enhances learning experiences, increases motivation and engagement, and improves learning outcomes.

The rapid rise of generative AI and its implications for academic integrity: Students’ perceptions and use of chatbots for assistance with assessments

The rapid adoption of generative AI tools such as ChatGPT by students has the potential to disrupt the higher education sector, with concerns being raised by academics about potential threats to academic integrity. This paper contributes to the pressing discussion about responses to AI tools by examining students' perceptions and the use of generative AI to assist them with assessments. Based on a survey among 337 Australian university students, this study found that more than a third of students have used a chatbot for assistance with an assessment, and do not necessarily perceive this as a breach of academic integrity. The study further investigated to what extent different psychosocial factors such as learning motivations, distress or resilience are associated with students’ use of AI chatbots in order to ascertain environmental conditions or risk factors driving their use. Findings suggest that the higher education sector faces the challenge of not only defining clear policies and guidelines about ethical and academically honest ways to use and integrate generative AI tools into university education and assessments, but also to rethink the design of assessment pieces.

ChatGPT compared to national guidelines for management of ovarian cancer: Did ChatGPT get it right? – A Memorial Sloan Kettering Cancer Center Team Ovary study

ObjectivesWe evaluated the performance of a chatbot compared to the National Comprehensive Cancer Network (NCCN) Guidelines for the management of ovarian cancer. MethodsUsing NCCN Guidelines, we generated 10 questions and answers regarding management of ovarian cancer at a single point in time. Questions were thematically divided into risk factors, surgical management, medical management, and surveillance. We asked ChatGPT (GPT-4) to provide responses without prompting (unprompted GPT) and with prompt engineering (prompted GPT). Responses were blinded and evaluated for accuracy and completeness by 5 gynecologic oncologists. A score of 0 was defined as inaccurate, 1 as accurate and incomplete, and 2 as accurate and complete. Evaluations were compared among NCCN, unprompted GPT, and prompted GPT answers. ResultsOverall, 48% of responses from NCCN, 64% from unprompted GPT, and 66% from prompted GPT were accurate and complete. The percentage of accurate but incomplete responses was higher for NCCN vs GPT-4. The percentage of accurate and complete scores for questions regarding risk factors, surgical management, and surveillance was higher for GPT-4 vs NCCN; however, for questions regarding medical management, the percentage was lower for GPT-4 vs NCCN. Overall, 14% of responses from unprompted GPT, 12% from prompted GPT, and 10% from NCCN were inaccurate. ConclusionsGPT-4 provided accurate and complete responses at a single point in time to a limited set of questions regarding ovarian cancer, with best performance in areas of risk factors, surgical management, and surveillance. Occasional inaccuracies, however, should limit unsupervised use of chatbots at this time.