User Trust Research Articles

Interactive Output Modalities Design for Enhancement of User Trust Experience in Highly Autonomous Driving

Autonomous driving (AD) technology has gradually matured, but the lack of trust and acceptance from users limits its adoption and diffusion. This paper aims to solve the challenges and alleviate the trust crisis by exploring reasonable interactive output modalities. Firstly, we propose a multimodal interactive output scheme with 9 different feedback level. Subsequently, we conduct simulated driving experiments on the scheme, using three methods: driving trust experience questionnaire (DTEQ), eye-tracking, and takeover desire recording. Finally, we analyze the trends and correlations of results at different interactive output levels. The results indicate that the user trust experience is highly positively correlated with the level of interactive output modalities. Under reasonable design, multimodal and high-level interactive output is beneficial for providing more comprehensive feedback information, reducing users’ visual workload, and improving trust. This work provides a foundation for enhancement of user trust experience, and helps promote the application and popularization of AD.

Development of trust-based autonomous driving framework in New Zealand

PurposeAutonomous vehicles (AVs) have the potential to transform the infrastructure, mobility and social well-being paradigms in New Zealand (NZ) amid its unprecedented population and road safety challenges. But, public acceptance, co-evolution of regulations and AV technology based on interpersonal and institutional trust perspectives pose significant challenges. Previous theories and models need to be more comprehensive to address trust influencing autonomous driving (AD) factors in natural settings. Therefore, this study aims to find key AD factors corresponding to the chain of human-machine interaction (HMI) events happening in real time and formulate a guiding framework for the successful deployment of AVs in NZ.Design/methodology/approachThis study utilized a comprehensive literature review complemented by an AV users’ study with 15 participants. AV driving sprints were conducted on low, medium and high-density roads in Auckland, followed by 15 ideation workshops to gather data about the users’ observations, feelings and attitudes towards the AVs during HMI.FindingsThis research study determined nine essential trust-influencing AD determinants in HMI and legal readiness domains. These AD determinants were analyzed, corresponding to eight AV events in three phases. Subsequently, a guiding framework was developed based on these factors, i.e. human-machine interaction autonomous driving events relationship identification framework (HMI-ADERIF) for the deployment of AVs in New Zealand.Research limitations/implicationsThis study was conducted only in specific Auckland areas.Practical implicationsThis study is significant for advanced design research and provides valuable insights, guidelines and deployment pathways for designers, practitioners and regulators when developing HMI Systems for AD vehicles.Originality/valueThis study is the first-ever AV user study in New Zealand in live traffic conditions. This user study also claimed its novelty due to AV trials in congested and fast-moving traffic on the four-lane motorway in New Zealand. Previously, none of the studies conducted AV user study on SUV BMW vehicle and motorway in real-time traffic conditions; all operations were completely autonomous without any input from the driver. Thus, it explored the essential autonomous driving (AD) trust influencing variables in human factors and legal readiness domains. This research is also unique in identifying critical AD determinants that affect the user trust, acceptance and adoption of AVs in New Zealand by bridging the socio-technical gap with futuristic research insights.

The Role of Information Governance in Mitigating Financial Crime Risks in Stablecoin Transactions

This study investigates the role of information governance in mitigating financial crime risks in stablecoin transactions. Using a variety of analytical techniques, including simple linear regression, sentiment analysis with NLP tools, logistic regression, and machine learning models, the research evaluates the impact of information governance on innovation, user trust, financial crimes, and the effectiveness of combined compliance measures. The findings indicate that strict information governance regulations reduce innovation but enhance market stability and user trust. Robust governance correlates strongly with increased user adoption, while higher anonymity features in stablecoins are linked to a higher incidence of financial crimes. Integrating KYC/AML compliance with transaction monitoring significantly improves the detection and prevention of financial crimes compared to standalone approaches. These insights provide valuable guidance for policymakers, regulatory authorities, and financial institutions to develop strategies that balance innovation with enhanced security and compliance in the stablecoin market.

Relationship Between Trust in the AI Creator and Trust in AI Systems: The Crucial Role of AI Alignment and Steerability

ABSTRACT This paper offers a novel perspective on trust in artificial intelligence (AI) systems, focusing on the transfer of user trust in AI creators to trust in AI systems. Using the agentic information systems (IS) framework, we investigate the role of AI alignment and steerability in trust transference. Through four randomized experiments, we probe three key alignment-related attributes of AI systems: creator-based steerability, user-based steerability, and autonomy. Results indicate that creator-based steerability amplifies trust transference from AI creator to AI system, while user-based steerability and autonomy diminish it. Our findings suggest that AI alignment efforts should consider the entity with which the AI goals and values should be aligned and highlight the need for research to theorize from a triadic view encompassing the user, the AI system, and its creator. Given the diversity in individual goals and values, we recommend that developers move beyond the prevailing “one-size-fits-all” alignment strategy. Our findings contribute to trust transference theory by highlighting the boundary conditions under which trust transference breaks down or holds in the emerging human-AI environment.

AI-Driven UX/UI Design: Empirical Research and Applications in FinTech

This study explores the transformative impact of AI-driven UX/UI design in the FinTech sector, examining current practices, user preferences, and emerging trends. Through a mixed-methods approach, including surveys, interviews, and case studies, the research reveals significant adoption of AI technologies in FinTech UX/UI design, with 78% of surveyed companies implementing such solutions. Personalization emerges as a dominant trend, with 76% of FinTech apps utilizing AI for tailored user interfaces. The study demonstrates a strong correlation between AI-enhanced features and improved user engagement, with apps incorporating advanced AI features showing a 41% increase in daily active users. Ethical considerations, including data privacy and algorithmic bias, are addressed as critical challenges in AI implementation. The research contributes a conceptual framework for AI-driven UX/UI design in FinTech, synthesizing findings from diverse data sources. Future trends, including emotional AI and augmented reality integration, are explored. The study concludes that while AI-driven UX/UI design offers significant potential for enhancing user experiences in FinTech, balancing innovation with ethical considerations is crucial for responsible implementation and user trust.

Evaluation of Explainable Artificial Intelligence using TOPSIS Method

Explainable Artificial Intelligence (XAI) refers to the development of AI systems are transparent, explainable and their comprehensible for results can provide explanations or predictions. As AI technologies, particularly machine learning models, become more complex and sophisticated, there is a growing need to ensure that their decisions can be comprehended and trusted by humans, especially health, Finance and such as criminal justice in important domains. Evaluating Explainable Artificial Intelligence (XAI) is essential to ensure transparency, accountability, and user trust in AI systems. Interpretability is a key factor, examining how easily the model's internal mechanisms can be understood. Model transparency, feature importance, and the clarity of visualizations contribute to this aspect. Differentiate between post-hoc and intrinsic explanations, considering whether the model inherently provides interpretable insights. The distinction between local and global explanations is crucial, as it determines whether explanations focus on individual predictions or the overall model behavior. Robustness and consistency are assessed through stability and sensitivity analysis, ensuring that explanations remain reliable across similar instances. Additionally, ethical considerations, such as fairness and transparency in decision-making, must be addressed to uncover and mitigate biases. User feedback and the relevance of explanations to the specific use case contribute to a comprehensive evaluation, fostering the development of XAI systems that are not only technically robust but also ethically sound and user-friendly. The significance of research in Explainable Artificial Intelligence (XAI) lies in addressing critical challenges associated with the adoption and deployment of AI systems in various domains. As AI technologies, particularly complex machine learning models, become integral to decision-making processes in areas such as healthcare, finance, and criminal justice, the need for transparency and interpretability becomes paramount. Topsis involves optimizing from an advantageous standpoint by simultaneously minimizing the distance to and maximizing the distance from a reference point, which is defined in relation to solutions within a set of alternative options and numerous identification criteria. The importance of Topsis criteria lies in the potential to integrate comparative weights. This study conducts a comprehensive review of Topsis, exploring various weighing schemes and employing different distance measurements. Numerous applications of Topsis are examined, particularly its utilization in comparing results for a diverse set of multiple criteria data with varying weights. Interpretable Machine Learning Models, Human-Centric Design in XAI, Ethical Implications of XAI, Industry-specific Applications of XAI and Hybrid Approaches for Model Interpretability. Interpretability Metrics, Human-Subjective Evaluation, Algorithmic Robustness and Real-world Impact. the Ranking of Evaluation Explainable Artificial Intelligence. Industry-specific Applications of XAI is got the first rank whereas is the Ethical Implications of XAI is having the Lowest rank.

패션 디지털 커머스에서 챗봇 특성이 사용자 신뢰와 지속사용 의도에 미치는 영향

As chatbots become integral to digital commerce in the fashion industry, this study evaluates their influence on user trust and the consequent intention for continued engagement. Specifically, it investigates how chatbot characteristics—namely interest, effectiveness, immersion, anthropomorphism, and innovation—affect user trust and their continuous usage intentions within fashion digital commerce platforms. Employing a quantitative survey method, the study gauges the impact of chatbot attributes on trust and the likelihood of ongoing interaction. Findings reveal that chatbot effectiveness, immersion, anthropomorphism, and innovation substantially bolster user trust, which fosters a higher propensity for users to maintain their engagement with the platform. This highlights trust as a pivotal mediating factor that connects chatbot features to the enduring engagement of users in the digital commerce landscape.

A Comprehensive Review on an Advanced Machine Learning Approach for Enhancing Phishing Website Detection

Abstract: Phishing attacks continue to pose a significant threat to online security, exploiting user trust to steal sensitive information. This paper presents a comprehensive review of advanced machine learning techniques for enhancing phishing website detection. We analyze recent developments in feature engineering, focusing on content-based, URL-based, and networkbased attributes. Various machine learning algorithms, including supervised and unsupervised learning, are examined, highlighting their strengths and limitations in this domain. Furthermore, we investigate the potential of ensemble methods and deep learning models to improve detection accuracy. Additionally, we address challenges such as concept drift and adversarial attacks, discussing potential mitigation strategies. Finally, we outline future research directions, emphasizing the need for adaptable and real-time detection systems to counter evolving phishing tactics. This review serves as a valuable resource for researchers and practitioners seeking to develop more robust and effective phishing website detection solutions.

MODERASI AUDITOR PROFESSIONAL SCEPTICISMPADA KOMPLEKSITAS TUGAS AUDIT, LOCUS OF CONTROLDAN KUALITAS AUDIT

Audit quality is the result achieved from financial statements that are presented fairly, all material matters or provide a true picture according to the financial reporting framework in order to increase the trust of users of financial statements. The purpose of this study is to investigate whether the complexity of the audit task, and locus of control can affect audit quality and auditor professional scepticism can moderate the effect of audit task complexity, and locus of control on audit quality. Type of research is quantitative research, in this study the data collection method is the distribution of questionnaires via g-form. The data collected in this study are the results of questionnaires distributed to auditors at public accounting firms in Indonesia. The results of this study audit task complexity and locus of control have a positive effect on audit quality, auditor professional scepticism cannot moderate the effect of audit task complexity and locus of control on audit quality.Keyword: Audit Quality, Audit Task Complexity, Locus of Control, and AuditorProfessional Scepticism.

Evaluating the AI dialogue System's intercultural, humorous, and empathetic dimensions in English language learning: A case study

The rise of artificial intelligence (AI) technologies has been notable in supporting English as an Additional Language (EAL) learners, particularly in offering interactive assessments. AI-driven dialogue systems that produce culturally relevant humor and empathy, bridging the native language (L1) and the target language (L2), have been employed to engage EAL learners more effectively and boost their learning results. However, there's a noticeable gap in research concerning the fusion of humor, empathy, and intercultural dimensions in language learning. Intercultural dimensions encompass acquiring crucial knowledge, communication skills, and the values essential for meaningful interactions across cultures. This case study examines the effectiveness of an AI dialogue system, termed the Multidimensional Approach Culture, Humor, and Empathy Bot (MACHE-Bot), in elevating the English language learning experience and its potential to enhance EAL proficiency. Using convenience sampling, 37 individuals were selected from an English language learning group on Facebook. Following a two-week pilot study, semi-structured interviews were conducted. The results revealed that MACHE-Bot adeptly initiated and reciprocated with humor, empathy, and cultural nuances in a manner well-received by participants. Additionally, the study identified five pivotal factors in EAL learning with MACHE-Bot: (1) intercultural dimensions, which include culturally humorous interaction and culturally empathetic support; (2) user trust comprising both affective and cognitive elements; (3) anthropomorphism; (4) reciprocal self-disclosure; and (5) higher engagement and motivation. These five factors collectively contribute to creating an engaging, relatable, and supportive learning environment, facilitating a more natural learning process, and fostering a deeper learner-bot connection, thereby potentially enhancing motivation and investment in the learning process.

“Sorry, I Don’t Understand …”: effects of task type, personality presentation and performance error on user trust of a personal digital assistant

PurposeBased on the theoretical predictions of media equation theory and the computers-are-social-actors (CASA) perspective, this study aims to examine the effects of performance error type (i.e. logical, semantic or syntactic), task type and personality presentation (i.e. dominant/submissive and/or friendly/unfriendly) on users’ level of trust in their personal digital assistant (PDA), Siri.Design/methodology/approachAn experimental study of human–PDA interactions was performed with two types of tasks (social vs functional) randomly assigned to participants (N = 163). While interacting with Siri in 15 task inquiries, the participants recorded Siri’s answers for each inquiry and self-rated their trust in the PDA. The answers were coded and rated by the researchers for personality presentation and error type.FindingsLogical errors were the most detrimental to user trust. Users’ trust of Siri was significantly higher after functional tasks compared to social tasks when the effects of general usage (e.g. proficiency, length and frequency of usage) were controlled for. The perception of a friendly personality from Siri had an opposite effect on social and functional tasks in the perceived reliability dimension of trust and increased intensity of the presented personality reduced perceived reliability in functional tasks.Originality/valueThe research findings contradict predictions from media equation theory and the CASA perspective while contributing to a theoretical refinement of machine errors and their impact on user trust.

Effective Application of Computer Network Security Technology in E-commerce Operation and Maintenance

As an important part of the modern economy, the security of e-commerce operation and maintenance directly affects the business continuity of enterprises and the trust of users. This paper explores the application of computer network security technology in operation and maintenance, analyzes existing technologies and actual cases, evaluates its effects, and looks forward to future development trends. The paper shows that the use of advanced network security technology can significantly improve the security and reliability of e-commerce systems.IntroductionIt has developed rapidly around the world and has become an important way for people to shop and for enterprises to operate e-commerce. However, the booming development of e-commerce also inevitably brings serious security threats, including data leakage, hacker attacks, and malware. In order to ensure the normal operation of e-commerce systems and the security of user data, the application of computer network security technology is extremely important. This paper aims to systematically explore the actual application effects of these technologies in e-commerce and provide reference for future research and practice.

Effective Application of Computer Network Security Technology in E-commerce Operation and Maintenance

As an important part of the modern economy, the security of e-commerce operation and maintenance directly affects the business continuity of enterprises and the trust of users. This paper explores the application of computer network security technology in operation and maintenance, analyzes existing technologies and actual cases, evaluates its effects, and looks forward to future development trends. The paper shows that the use of advanced network security technology can significantly improve the security and reliability of e-commerce systems.IntroductionIt has developed rapidly around the world and has become an important way for people to shop and for enterprises to operate e-commerce. However, the booming development of e-commerce also inevitably brings serious security threats, including data leakage, hacker attacks, and malware. In order to ensure the normal operation of e-commerce systems and the security of user data, the application of computer network security technology is extremely important. This paper aims to systematically explore the actual application effects of these technologies in e-commerce and provide reference for future research and practice.

The Influence of E-Service Quality and Service Features on Customer Trust in Gojek Application Users

This research was conducted to analyze the influence of E-Service Quality and Service Features on Customer Trust among Gojek application users. The data in this research was collected through distributing questionnaires and analyzed using quantitative analysis. The population taken was students at Swadaya Gunung Jati University with a sample of level 4 students. The sample taken was 208 respondents using a non-probability sampling technique, namely purposive sampling. In this study, the data was processed using SPSS version 25 with cross descriptive model analysis (Crosstab), as well as the relationship between the respondent's character and the question variables. And to test the data using validity and reliability tests. The research results show that E-Service Quality has a significant influence on Customer Trust, Service Features have a significant influence on Customer Trust, and the two variables between E-Service Quality and Service Features both have a significant influence on Customer Trust

Enhancing user engagement and satisfaction through personalized news recommendation systems

Personalized news recommendation systems have emerged as essential tools in addressing information overload by tailoring news content to individual user preferences. This paper provides a comprehensive overview of the advanced techniques employed in these systems, their impacts on user engagement, and the ethical considerations surrounding their development and implementation. We delve into the intricacies of data collection, processing, and user profiling, highlighting the methodologies and challenges inherent in each stage. Additionally, we explore advanced algorithmic foundations, including collaborative filtering, content-based filtering, and hybrid methods, elucidating their strengths and limitations. Furthermore, we examine the dynamics of user engagement within personalized news recommendation systems, analyzing key metrics and the role of user feedback in refining recommendation algorithms. Finally, we address privacy concerns, data sparsity issues, and biases, proposing solutions to mitigate ethical challenges and uphold user trust and fairness. This paper serves as a comprehensive guide for researchers, practitioners, and policymakers navigating the complexities of personalized news recommendation systems.

Improving interpretability via regularization of neural activation sensitivity

State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their widespread adoption in mission-critical contexts is limited due to two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about DNNs’ security and generalization in real-world conditions, while the latter, opaqueness, directly impacts interpretability. The lack of interpretability diminishes user trust as it is challenging to have confidence in a model’s decision when its reasoning is not aligned with human perspectives. In this research, we (1) examine the effect of adversarial robustness on interpretability, and (2) present a novel approach for improving DNNs’ interpretability that is based on the regularization of neural activation sensitivity. We evaluate the interpretability of models trained using our method to that of standard models and models trained using state-of-the-art adversarial robustness techniques. Our results show that adversarially robust models are superior to standard models, and that models trained using our proposed method are even better than adversarially robust models in terms of interpretability.(Code provided in supplementary material.)

Responsible AI for cardiovascular disease detection: Towards a privacy-preserving and interpretable model

Background and objectiveCardiovascular disease (CD) is a major global health concern, affecting millions with symptoms like fatigue and chest discomfort. Timely identification is crucial due to its significant contribution to global mortality. In healthcare, artificial intelligence (AI) holds promise for advancing disease risk assessment and treatment outcome prediction. However, machine learning (ML) evolution raises concerns about data privacy and biases, especially in sensitive healthcare applications. The objective is to develop and implement a responsible AI model for CD prediction that prioritize patient privacy, security, ensuring transparency, explainability, fairness, and ethical adherence in healthcare applications. MethodsTo predict CD while prioritizing patient privacy, our study employed data anonymization involved adding Laplace noise to sensitive features like age and gender. The anonymized dataset underwent analysis using a differential privacy (DP) framework to preserve data privacy. DP ensured confidentiality while extracting insights. Compared with Logistic Regression (LR), Gaussian Naïve Bayes (GNB), and Random Forest (RF), the methodology integrated feature selection, statistical analysis, and SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) for interpretability. This approach facilitates transparent and interpretable AI decision-making, aligning with responsible AI development principles. Overall, it combines privacy preservation, interpretability, and ethical considerations for accurate CD predictions. ResultsOur investigations from the DP framework with LR were promising, with an area under curve (AUC) of 0.848 ± 0.03, an accuracy of 0.797 ± 0.02, precision at 0.789 ± 0.02, recall at 0.797 ± 0.02, and an F1 score of 0.787 ± 0.02, with a comparable performance with the non-privacy framework. The SHAP and LIME based results support clinical findings, show a commitment to transparent and interpretable AI decision-making, and aligns with the principles of responsible AI development. ConclusionsOur study endorses a novel approach in predicting CD, amalgamating data anonymization, privacy-preserving methods, interpretability tools SHAP, LIME, and ethical considerations. This responsible AI framework ensures accurate predictions, privacy preservation, and user trust, underscoring the significance of comprehensive and transparent ML models in healthcare. Therefore, this research empowers the ability to forecast CD, providing a vital lifeline to millions of CD patients globally and potentially preventing numerous fatalities.

Occupant-centric control in buildings: Investigating occupant intentions and preferences for indoor environment and grid flexibility interactions

Occupant-centric control (OCC) systems have recently gained attention as they fulfill the energy efficiency goals of buildings while prioritizing occupant comfort and well-being. However, many studies overlook the core principle of focusing on occupants and their preferences. Instead, they assume seamless interaction between individuals and advanced controls reliant on occupant data. This study investigates occupant preferences in control systems, including control access, automation level preferences, interface design, and data sharing. Furthermore, it assesses occupant willingness to interact with OCC by sharing data as feedback for indoor environment control and grid flexibility purposes. This study is based on a survey conducted in six educational buildings involving 959 respondents with varying levels of technical knowledge. The method includes a well-established behavioral science theory called the Theory of Planned Behaviour. Structural equation modeling with SmartPLS statistical software was used for data analysis. The study reveals that 55.6% of occupants are willing to interact with OCC by sharing data. The key influences are occupants’ attitudes, social norms, ease of use, and user trust. The proposed behavioral models predict user interaction with OCC with moderate prediction, with R2 values reaching 63.9%, which is satisfactory in behavioral sciences. The results also show a correlation between willingness to interact with OCC and engagement in grid flexibility. These findings are important for OCC designers and building control practitioners who aim to prioritize occupant needs and preferences. The behavioral prediction models present a tool for assessing occupant data sharing inclination, thereby helping to prevent data shortages.

Research Paper on Exploring the Landscape of Recommendation Systems: A Comparative Analysis of Techniques and Approaches

The field of recommendation systems has witnessed a profound evolution since its inception with Grundy, the first computer-based librarian, in 1979. From its humble beginnings, recommendation systems have become integral to various facets of daily life, particularly in e-commerce, thanks to breakthroughs like Amazon’s Collaborative Filtering in the late 1990s. This led to widespread adoption across diverse sectors, prompting significant research interest and investment, exemplified by Netflix’s renowned recommendation system contest in 2006. Today, recommendation systems employ various techniques such as Hybrid Filtering, Content-Based Filtering, Demographic Filtering, and Collaborative Filtering catering to personalized information needs across industries like entertainment, education, and healthcare. Moreover, emerging types of recommendation systems, including Knowledge-Based, RiskAware, Social-Networking, and Context-Aware, further broaden their applicability, addressing specific user needs and preferences. Leveraging machine learning and AI algorithms on big data, recommendation systems have become a quintessential application of big data analytics, enhancing user experience and engagement in domains like e-learning, tourism, and news dissemination. However, scaling recommendation systems present challenges due to the exponential growth of input data, necessitating strategies like Dimensionality Reduction and cluster-based methods. Integrating multiple recommendation algorithms enhances system complexity, requiring careful consideration of algorithm selection, performance monitoring, and maintenance. Transparency and explanation mechanisms become crucial in complex systems to foster user trust and understanding. Despite challenges, recommendation systems continue to drive innovation, delivering personalized recommendations and enriching user experiences across various domains.

Design and Evaluation of Cafe Kahuripan Booking and Reservation Website User Interface with Design Thinking

Cafe Kahuripan is a business engaged in the culinary field where customers can order menus and rent a place. Currently, the process of ordering menus and renting a place is done manually with customers coming directly to the place or contacting the admin via WhatsApp listed on Facebook. However, there is a decrease in subscribers from 2021 to 2022 due to a lack of marketing which is only limited to Facebook and Whatsapp. To overcome these problems, it is necessary to design a website as a solution to make it easier for customers to order menus and rent places online. In this design, it is necessary to pay attention to a good User Interface (UI) in order to increase the level of user trust and satisfaction. The website must also have easy access that can be done anywhere. Cafe Kahuripan website user interface design uses the design thinking method. The design of the user section, there are several pages such as home, about us, menu, reservation, contact us, order status and reservation status. The design of the admin section, there is an admin dashboard, customer data, menus, orders and reviews. The result of this study is the design of the user interface for the Cafe Kahuripan website from the user side (front-end), which allows users to order menus and rent places online. The results of the usability testing which obtained an average score of 79 is a good achievement and indicates that the UI design that has been carried out has succeeded in meeting user needs. Hypothesis analysis shows that the hypothesis H0 is rejected and H1 is accepted, this is in accordance with the average score of the System Usability Scale (SUS). Respondents' feedback was analyzed and improved according to the suggestions given based on the priority level to produce a better website for users.