User Intention Research Articles

Shared Control Design of a Walking-Assistant Robot

Walking-assistant robots serve as a vital aid for individuals with mobility challenges, enhancing their independence and mobility. Shared control systems combine user input and robotic intelligence to ensure safe, adaptable, and intuitive navigation. This paper presents a shared control framework for a walking-assistant robot, focusing on user intention prediction and real-time obstacle avoidance. A Python-based simulation demonstrates the system's performance in a scaled-up environment with larger obstacles and a broader robot trajectory.

Granular intents learning via mutual information maximization for knowledge-aware recommendation

Knowledge-aware recommender systems, which utilize knowledge graphs (KGs) to enrich item information, have been shown to improve the accuracy and explainability of recommendations. Besides, KGs are further explored to determine the intent of choosing items (i.e., the reason why users select items of interest). Conventional methods represent intents either as sets of relations in a KG or as KG entities. However, such approaches fail to fully leverage the combined information provided by both entities and relations. To address this issue, we propose a new KG-based user Intent Extraction Framework (KIEF) to capture user intents at a more fine-grained level for recommendation. Specifically, we propose a novel intent representation constructed with relation-aware entity representation, encouraging finer granularity for user intents. Furthermore, since a KG may contain noisy information that impairs the quality of user intent, it is compulsory to consider which factors in a KG are important to represent a user’s intent. Thus, we introduce global intent which are comprehensive features for the entire interactions of all users and local intent, which are empirical features of individual users from personal history. By maximizing mutual information between global and local intents, KIEF captures user preference for items. Through extensive experiments on four real-world benchmark datasets, we prove the superior performance of KIEF over the state-of-the-art and analyze interpretable explanations for understanding user intents.

An empirical study of factors influencing usage intention for generative artificial intelligence products: A case study of China

The rapid advancement of generative artificial intelligence technologies has sparked widespread interest, yet understanding of user adoption patterns for these tools remains limited. While the unified theory of acceptance and use of technology model has been widely applied to various technologies, its applicability to generative artificial intelligence products, which present unique challenges and opportunities, has not been thoroughly explored. This gap in knowledge hinders the development of effective strategies for promoting user acceptance and optimising the design of generative artificial intelligence tools. This study extends the unified theory of acceptance and use of technology model to investigate the factors influencing usage intention for generative artificial intelligence products. The study incorporates additional variables such as digital literacy, perceived risk and perceived trust to provide a more comprehensive framework. Using structural equation modelling to analyse survey data, the study found that effort expectancy, performance expectancy, social influence, and perceived trust significantly and positively impact usage intention. In addition, digital literacy indirectly enhances usage intention through effort expectancy, while perceived risk negatively influences usage intention through reduced trust. Notably, facilitating conditions did not exhibit a significant effect on usage intention. These findings offer valuable insights for developers and researchers in the field of generative artificial intelligence, highlighting the importance of user-friendly design, performance optimisation, and trust-building measures. By identifying key factors that drive user adoption, this study contributes to a more nuanced understanding of technology acceptance in the context of advanced artificial intelligence systems, paving the way for more effective development and implementation strategies in this rapidly evolving field.

P[formula omitted]ED: A four-quadrant framework for progressive prompt enhancement in 3D interactive medical imaging segmentation

Interactive segmentation allows active user participation to enhance output quality and resolve ambiguities. This may be especially indispensable to medical image segmentation to address complex anatomy and customization to varying user requirements. Existing approaches often encounter issues such as information dilution, limited adaptability to diverse user interactions, and insufficient response. To address these challenges, we present a novel 3D interactive framework P2ED that divides the task into four quadrants. It is equipped with a multi-granular prompt encrypted to extract prompt features from various hierarchical levels, along with a progressive hierarchical prompt decrypter to adaptively heighten the attention to the scarce prompt features along three spatial axes. Finally, it is appended by a calibration module to further align the prediction with user intentions. Extensive experiments demonstrate that the proposed P2ED achieves accurate results with fewer user interactions compared to state-of-the-art methods and is effective in promoting the upper limit of segmentation performance. The code will be released in https://github.com/chuyhu/P2ED.

The Moderating Role of Structural Assurance in the Unified Theory of Acceptance and Use of Technology (UTAUT): A Study of E-wallet Behavioural Intention of Users and Non-users Among Adults in Malaysia

The Moderating Role of Structural Assurance in the Unified Theory of Acceptance and Use of Technology (UTAUT): A Study of E-wallet Behavioural Intention of Users and Non-users Among Adults in Malaysia

Pathways to Resilient and Sustainable Online Education in the New Normal: Interpreting University Teachers’ Willingness to Use Online Teaching Platforms Consistently

In the new normal, online education has become a norm and is considered equally important as traditional face-to-face education. Although online teaching has improved accessibility, reduced management costs, and expanded educational opportunities, there are also some issues, such as whether technology and internet access are widespread and whether the quality of online education is better or worse compared to previous modes. With the rapid development of online education, it is crucial to investigate the key factors influencing university teachers’ continuous usage of online teaching platforms and their working mechanisms, which is of great significance for improving the level of educational informatization and promoting educational modernization. This study mainly explores the continuous usage intention of online teaching platforms by Chinese university teachers under the new normal and its influencing factors, aiming to provide theoretical support and practical insights for improving educational informatization, promoting educational modernization, and designing and optimizing online teaching platforms. This study builds a new theoretical framework based on the technology acceptance model (TAM), UTAUT model, and the theory of planned behavior (TPB). From April to November 2024, 343 questionnaires were collected from Chinese university teachers. Combining structural equation modeling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA), the key factors influencing teachers’ continuous usage of online platforms and their configuration relationships are systematically discussed. Not only are the key factors verified, but the configuration relationships are also revealed, providing deeper insights for universities to design, promote, and optimize online teaching platforms and offering theoretical support and practical guidance for promoting sustainable educational development.

Towards the measurement of consumer trust in media brands—scale development and validation

ABSTRACT Media brands in today’s digitized economy are facing growing competition and the increasing need for valid parameters to measure success and the perception of their brand. Trust in media brands is one of the most important factors in that regard, influencing the decision for and against certain media brands and driving factors, such as brand equity and usage intention. While research on trust in corporate, product and service brands is abundant, trust research specifically focusing on media brands has been widely neglected. Due to the strong possible impact of singular events particularly on trust in media brands and the connected high variance in consumer trust, a valid tool to track consumer perceptions over time thus would add a worthwhile contribution to media management. Due to significant differences between brands and media brands based on divergent business models, business partners and sources of revenue, currently available brand trust scales, however, cannot simply be applied in the media sector. In our study, we are conducting quantitative, multinational research to establish a valid and reliable media brand trust scale. We aim for the empirically based development of the focal construct building on the framework of media brand trust. The framework results from 11 components derived from previous studies. With this development, we are providing actors of the media economy with a scale to measure consumers’ trust in the media brand and generating an understanding of the specific elements required to improve media brands’ business operations.

User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants

Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader contextual understanding, an area in which Large Language Models (LLMs) excel. However, current LLMs are largely designed for text-based interactions, thus making it unclear how user interactions will evolve if their modality is changed to voice. In this work, we investigate whether LLMs can enrich VA interactions via an exploratory study with participants (N=20) using a ChatGPT-powered VA for three scenarios (medical self-diagnosis, creative planning, and discussion) with varied constraints, stakes, and objectivity. We observe that LLM-powered VA elicits richer interaction patterns that vary across tasks, showing its versatility. Notably, LLMs absorb the majority of VA intent recognition failures. We additionally discuss the potential of harnessing LLMs for more resilient and fluid user-VA interactions and provide design guidelines for tailoring LLMs for voice assistance.

Understanding users’ trust transfer mechanism in food delivery apps

PurposeDrawing upon the trust transfer theory and IS success model, this study investigates the transfer mechanism and the antecedents of trust to the platform and trust to a food vendor in the FDA, which subsequently affect users’ behavioral intention.Design/methodology/approachData collection was carried out through an online questionnaire via the Prolific platform. Respondents were exclusively selected from Uber Eats users in the US market due to the popularity of this food delivery app and the volume of food delivery transactions in this country.FindingsThe findings confirmed the trust transfer between trust in the platform and trust in the food vendor, ultimately contributing to users’ continuance usage intention and purchase intention. Our empirical results also show that system quality and service quality lead to trust-in-platform, while product presentation richness, vendor reputation and social referrals enhance trust in food vendors.Practical implicationsThe results offer valuable insights for FDA providers and food vendors to offer better user experiences to foster trust, enhance purchase intention and retain their commitment to the platform.Originality/valueUnlike past research in an e-commerce context that mainly concentrates on the role of trust in general or trust in the platform, this study expands the understanding of trust-related research by exploring the predictors and consequences of both trust toward the platform and trust toward the vendors in the FDA settings.

A Review of Gait Coordination Control Methods for Lower Limb Exoskeleton Robots Based on Visual Models

The ongoing evolution of exoskeleton technology has rendered the exclusive reliance on a single vision technology an impractical approach to addressing the complexities of diverse environments and individual requirements. This paper therefore explores the potential of combining traditional visual models with movement intention prediction based on surface electromyography (sEMG) and virtual reality (VR) technology in the context of gait control. The study concluded that traditional visual models are capable of providing accurate environmental perception and gait planning; however, they are deficient in forecasting user intentions. Surface electromyography (sEMG) technology can supplement this deficiency with muscle activity signals, enabling the system to respond dynamically to user needs. Concurrently, virtual reality (VR) technology furnishes users with a more personalized training program through immersive environmental simulation and feedback. The combination of these three technologies not only enhances the system's real-time responsiveness but also exhibits commendable adaptability in complex terrain and rehabilitation training. This paper examines the three fundamental technologies of lower limb exoskeleton robots in gait control and their fusion applications, with the objective of enhancing the system's intelligence and adaptability, providing a direction for the future development of lower limb exoskeleton technology, and highlighting the challenges and potential of multimodal data fusion and computational optimisation.

The Role of AI-Based Destination Chatbots in Satisfaction, Continued Usage Intention, and Visit Intention: A Study from Quito, Ecuador

Framed on the Expectation-Confirmation Model (ECM), the Information System Success Model (ISSM), and the Technology Acceptance Model (TAM), the aim of the study is to investigate destination chatbots to know the factors that generate user satisfaction, chatbot continued usage and destination visit intentions. Ecuador has the city of Quito as its capital and has been a World Heritage Site (WHS) since 1978. To provide tourists with information about the city, the Chatbot Quito Guide Bot. A convenience sampling method was employed to collect data from 284 participants who tried the QuitoGuide chatbot before answering a self-administered questionnaire. The Partial Least Squares Structural Equation Modeling (PLS-SEM) was used to test the proposed structural model. The results showed that the quality of information, the perceived enjoyment, and the perceived usefulness positively influence satisfaction. The findings also revealed that satisfaction with the chatbot is a strong determinant and a predictor of continued use of the chatbot and visit intentions.

Motivational determinants of continuance usage intention for generative AI: an investment model approach for ChatGPT users in the United States

ABSTRACT The proliferation of generative artificial intelligence (AI) chatbots such as ChatGPT has sparked a transformation in the dynamics of human–machine interactions. However, little is known about the psychological mechanisms underlying generative AI chatbot–human relationships. Building on the investment model, this study examined the influence of generative AI user-friendliness and playfulness on ChatGPT commitment and continuance usage intention. The results of an online survey conducted in the United States (N = 446) indicated that user-friendliness and playfulness positively affect satisfaction, investment size, and perceived quality of alternatives. Both satisfaction and investment size positively affect commitment to ChatGPT, thereby influencing the intention to continue using generative AI chatbots. However, the quality of alternatives did not significantly affect user commitment to ChatGPT. The findings of this study contribute to our understanding of building user relationships with generative AI chatbots by identifying user-friendliness (representing utilitarian value) and playfulness (representing hedonic value) as key factors in determining generative AI continuance usage intention.

Domain-aware Multimodal Dialog Systems with Distribution-based User Characteristic Modeling

Textual response generation is a pivotal yet challenging task for multimodal task-oriented dialog systems, which targets at generating the appropriate textual response given the multimodal context. Although existing efforts have obtained remarkable advancements, they ignore the potential of the domain information in revealing the key points of the user intention and the user's history dialogs in indicating the user's characteristics. To address this issue, in this work, we propose a novel domain-aware multimodal dialog system with distribution-based user characteristic modeling (named DMDU). In particular, DMDU contains three vital components: context-knowledge embedding extraction , domain-aware response generation and distribution-based user characteristic injection . Specifically, the context-knowledge embedding extraction component aims to extract the embedding of multimodal context and related knowledge following existing studies. The domain-aware response generation component targets at conducting domain-aware fine-grained intention modeling based on the context and knowledge embedding, and thus fulfills the textual response generation. Moreover, the distribution-based user characteristic injection component first captures the user's characteristics and current intention with the Gaussian distribution, and then conducts the sampling-based contrastive semantic regularization to promote the context representation learning. Experimental results on the public dataset demonstrate the effectiveness of DMDU. We release codes to promote other researchers.

From Virtual Trainers to Companions? Examining How Digital Agency Types, Anthropomorphism, and Support Shape Para‐Social Relationships in Online Fitness

ABSTRACTThe role of virtual trainers in online fitness has increasingly captured the attention of consumers and brands as digital technology becomes more interwoven with daily life. This study extends the para‐social relationship theory by developing and testing a research model through five studies that simulate online fitness interactions. In Study 1, we examine the model and find that three characteristics (interactivity, authenticity, and companionship) positively influence consumers' social perceptions (perceived warmth and competence), para‐social relationship building, and intentions to continue using the service. Our findings also reveal that the moderating roles of coach types (human vs. avatar vs. agent) in Study 2, anthropomorphic appearance levels (high vs. low) in Study 3, and the nature of support provided (emotional vs. technical) in Study 4 significantly affect users' social perceptions and their intentions to continue using the service. Interestingly, compared to humans and avatars, using agent coaches requires greater authenticity to strengthen the para‐social relationship. When using low‐anthropomorphic digital agents and avatars, building para‐social relationships more effectively promotes consumers' continued usage intentions. Additionally, the relationship between para‐social relationship building and continued usage intentions was stronger in the emotional support group than in the technical support group. In Study 5, we found that continued usage intention positively affects online fitness subscription behaviors. These findings have implications for integrating digital agencies to enhance consumer experience and engagement in health‐focused digital environments, especially for physical fitness service providers and platform course designers.

An empirical analysis of user intention to use chatbots for airline tickets consultation

Purpose This study aims to empirically analyze the factors influencing users’ intention to use chatbots for airline ticket consultation. It seeks to introduce a comprehensive framework based on the technology acceptance model (TAM) that integrates key factors alongside traditional TAM constructs to understand what drives behavioral intention to use chatbots in the context of airline ticket consultation. Design/methodology/approach The study uses the partial least squares-structural equation modeling (PLS-SEM) approach to validate the proposed model empirically. Data were collected through a survey questionnaire distributed to potential users in Saudi Arabia, with 393 valid responses from a total of 409 received being included in the analysis. Findings The empirical analysis confirms the significance of perceived usefulness and user satisfaction as direct determinants of behavioral intention. Additionally, it reveals that factors such as perceived ubiquitous access, perceived completeness, perceived accuracy, perceived unbiased response and perceived convenience have both direct and indirect significant impacts on the behavioral intention to use chatbots for airline ticket consultation. Originality/value This research advances theoretical understanding and holds practical implications for designing and implementing effective chatbot services. By investigating the complex interplay of these factors, the study makes substantive contributions to both theoretical advancements and practical applications in the field, particularly in enhancing the user experience and acceptance of chatbots for airline ticket consultations.

Evaluating the benefits and risks of facial recognition payment systems adoption in Malaysia

PurposeCurrent developments in the FinTech payment industry have shown a rapid revolution in Industry 4.0, and understanding the factors affecting individual acceptance of facial recognition payment (FRP) is crucial. Hence, this study aims to evaluate the benefits and risks of FRP system adoption in Malaysia.Design/methodology/approachThe perceived risks and benefits framework is adopted as the foundation in this study to examine the various risks and benefits that users perceive, along with the trust factor, to study the relationships between these variables. Data were collected via an online questionnaire, and the hypotheses were tested using Partial Least Squares analysis on 277 responses.FindingsThe results revealed that perceived risk is a significant predictor of users' intention to use the FRP system. Privacy risk and financial risk significantly influence perceived risks, while security risk does not. Although convenience, perceived ease of use and perceived trust positively influence perceived benefits, perceived benefits do not significantly influence adoption intention. Moreover, perceived trust negatively affects perceived risks while positively affecting both perceived benefits and adoption intention. Additionally, personal innovativeness moderates the relationship between perceived risks and the intention to use the FRP system.Practical implicationsThis study helps policymakers and service providers understand individuals’ concerns and expectations regarding FRP systems. It aids practitioners in developing strategies to build trust, address innovativeness differences and mitigate risks, serving as a roadmap for integrating these systems into Malaysia's financial landscape.Originality/valueThis study distinguishes itself from prior research by evaluating FRP system adoption in Malaysia through the lens of perceived risks and benefits framework. It also explores personal innovativeness as a moderator, examining its impact on the relationship between usage intention and perceived risks and benefits. Additionally, it highlights perceived trust as a crucial factor influencing individuals' intention to adopt FRPs.

From FoMO to Discontinuous Usage Intention: Information Overload and Social Media Fatigue for Chinese Weibo Users

ABSTRACT Weibo is an event-focused microblogging platform open to the public, easily triggering users’ social media fatigue. Based on the Stressor – Strain – Outcome (S-S-O) model, this research proposes a path model to explore the antecedents and consequences of social media fatigue among Chinese Weibo users. Findings from an online survey of 414 Weibo users reveal that caused of fear of missing out (FoMO), they might experience social media fatigue through information overload, further causing them to develop discontinuous usage intentions. This study contributes to the literature on Chinese social media platforms and their cultural-specific nuances. Theoretical insights for future research are provided, and practical suggestions are recommended for Weibo users.

Usage Intention of ChatGPT for Health in Turkey: An Extended Technology Acceptance Model

The use of ChatGPT is spreading rapidly in the world. Although studies on the use of ChatGPT in healthcare are widespread, there have been very few studies examining ChatGPT technology in the context of the extended technology acceptance model (TAM), particularly from the perspective of end users. This study aims to investigate users’ perspectives on utilizing ChatGPT in acquiring health information, employing the extended TAM that encompasses social influence, trust, and perceived surprise factors. The data were collected from a total of 1135 ChatGPT users in Turkey, a developing country, using convenience sampling. Confirmatory factor analyses and structural equation modeling were applied. Findings revealed that the variables affected each other within both TAM and extended TAM models. While focusing on health consumers’ experiences with the use of ChatGPT is referred as the novelty of the study, it provides new insights into the use of ChatGPT in health-based research from the user’s perspective.

The Influence of Foundational Bases of Internet-Only Banks on Consumer Attitudes and Usage Intentions: Focused on the Moderating Effect of Involvement, Usage Purpose, and Construal Level

This study investigates how the foundational bases of internet-only banks shape consumer attitudes and intentions to use these services. Specifically, it examines how consumer attitudes and usage intentions toward internet-only banks are moderated by factors such as involvement, purpose of use, and construal level. This research contrasts consumer attitudes based on the foundational bases of internet-only banks (ICT-driven vs. bank-driven) and analyzes whether involvement (high vs. low) and usage purpose (deposit vs. loan) have moderating effects on these attitudes. Furthermore, it explores whether construal level (low vs. high) moderates usage intentions depending on the bank’s foundational base (ICT-driven vs. bank-driven). For empirical analysis, two types of surveys representing ICT-driven and bank-driven internet-only banks were administered to a sample of 360 participants, including university students, graduate students, and the general public in Daegu and Gyeongbuk. Key Findings: 1) Consumer attitudes were significantly more favorable toward ICT-driven internet-only banks compared to bank-driven counterparts. 2) High involvement correlated with more positive attitudes toward ICT-driven internet-only banks, whereas low involvement correlated with more favorable attitudes toward bank-driven banks. 3) For usage purpose, consumers with a loan-oriented purpose demonstrated a stronger positive attitude toward ICT-driven internet-only banks, while, counter to the hypothesis, deposit-oriented consumers also showed a preference for ICT-driven banks. 4) Regarding construal level, lower construal levels were associated with stronger usage intentions for ICT-driven internet-only banks. Unexpectedly, high construal levels also displayed elevated usage intentions for ICT-driven models. In conclusion, initial consumer responses to internet-only banks, which incorporate ICT as an enabling technology within essential financial services, appear to prioritize convenience and procedural efficiency. This study thus offers theoretical insights suggesting that both internet-only and traditional banks should address these consumer demands by enhancing service speed and simplicity.

Understanding User Intention to Adopt Augmented Reality Head-Up Display: A Study Based on Design Factors

Augmented Reality Head-Up Display (AR-HUD) is designed to engender immersive experiences and possess vast potential in enhancing vehicular safety. In the context of advancing digital technologies, the intention to use such innovations represents a significant field of study. Drawing on the Perceived Value Theory and the Stimulus-Organism-Response (S-O-R) framework, this study formulates a model to evaluate user intentions regarding the use of automotive Augmented Reality Head-Up Display (AR-HUD). This model integrates design elements, including user interface attractiveness, sense of presence, controllability, and responsiveness, along with perceived utilitarian and hedonic values. Through Structural Equation Modeling (SEM) of 230 valid questionnaire results, the analysis identifies both utilitarian and hedonic values as pivotal in influencing AR-HUD adoption, with utilitarian value being preeminent. Additionally, it is evidenced that design attributes influence the usage intention via perceived utilitarian and hedonic values. Consequently, this study presents design strategies for auto manufacturers and designers aimed at amplifying the advantages of AR-HUD, thus fostering greater user adoption willingness.