With the development of artificial intelligence, the smart agents are widely used in various fields as auxiliary tools for human–computer interaction (HCI), but there are still deficiencies in providing individuals with diverse emotional experiences. This study focuses on the impact of smart agent appearance design on individual emotional experience and behavioural performance, and analyses the data of emotional experience and interactive behaviour through event-related potentials (ERPs) experiments. These results bridge design aesthetics with HCI experience. This study concluded that: (1) Cartoonish appearances are more conducive to improving emotional cognition efficiency and are suitable for tasks requiring quick responses; (2) Realistic appearances elicit more top-down cognitive control, are more visually appealing, and are better suited for tasks where smart agents are used to attract attention. This study explored the impact of the visual features of smart agents on people’s emotional experience and interactive behaviour, analysed the emotional processing and task performance of individuals when facing smart agents with realistic or cartoon appearance, and discussed the visual and emotional information, research techniques and external behavioural manifestations in the interaction process, providing practical insights for optimising the emotional expression of smart agents in HCI.

As rising traffic density heightens safety challenges, immersive and personalized defensive driving training has become essential. This study employs virtual reality (VR) with integrated eye-tracking to examine how interface variables—traffic light size, brightness, signage size, and information display mode—affect drivers’ visual attention. Results show that enlarging lights and signs to 1.5 times their original size significantly reduced fixation durations and improved cognitive efficiency. Compared to center console displays (CCD), Head-Up Displays (HUD) yielded higher fixation time, more fixation points, and stronger attention stability. Brightness increases mainly influenced initial attention but showed diminishing returns for cognitive processing. The study introduces a Unity-based collider detection and automated eye-tracking script to enhance data accuracy and reproducibility. Theoretically, it integrates visual saliency modeling and user experience design to construct a pathway linking visual features, attention capture, and cognitive processing, offering design implications for VR driving systems.

This study addresses the challenges of vocational training for Middle-aged, Elderly, and Low-educated Individuals (MELI) in hazardous materials transport. We developed an entertainment-based learning approach using TikTok-style short videos to engage this demographic. A customized training app was created, and over 300 videos were developed for a six-month program with 500+ participants. Using a TPB-TAM integrated framework, we analyzed 333 responses with Partial Least Squares Structural Equation Modeling (PLS-SEM). Key findings include: Behavioral attitude (BA) has a significant impact on behavioral intentions (BI); Subjective norms (SN) significantly influence BI through perceived ease of use (PEOU) and perceived usefulness (PU); PEOU significantly influences BI through BA and PU; and PU not only directly influences BI but also significantly impacts BI through BA. This study provides design guidelines for adapting social media formats to vocational training and enhancing engagement for underserved populations.

The evolution of artificial intelligence (AI) has driven AI Agents to shift from passive response to proactive interaction, a critical advancement for optimizing user experience and operational efficiency. Current research predominantly emphasizes functional implementation, while studies on user attention and related task performance of proactive interaction mechanisms remain relatively scarce. This research systematically examines three core characteristics of AI Agent proactive interaction (environmental perception, decision support, and task execution) through an integrated methodology combining eye-tracking, Information Processing Efficiency Index, and Self-Assessment Manikin scales. Key findings reveal: (1) Proactive environmental perception with visual-textual cues significantly enhances user attention and task efficiency; (2) Provision of decision-making rationales strengthens user trust and satisfaction; (3) Proactive information delivery improves both user satisfaction and information processing efficiency. As the first study to jointly analyze AI Agent interaction mechanisms from psychological and cognitive perspectives, this work establishes theoretical foundations and actionable guidelines for designing intelligent assistive systems.

To explore online user behavioral habits from the perspectives of cognitive efficiency and emotional experience, as well as to provide objective and quantitative physiological evidence for the design of intelligent online education platforms and the technological application of Education 4.0. In this paper, 45 subjects were selected and recruited using a combination of eye-tracking and questionnaires, with a male-to-female ratio of 1:2. The results show that: (1) Intelligent interaction modes significantly impact online users’ positive emotional arousal compared to traditional interaction modes; (2) Diversified presentation of interactive information can help online learners understand collaborators’ opinions more quickly and optimize the experience of online peer Interaction; (3) Multi-channel interaction can provide learners with a better emotional experience while improving the efficiency of interacting with instructional information. This paper provides an objective design basis for intelligent platforms like online teaching and conference software in the context of information technology.

In recent years, social media platforms, such as Facebook and Twitter have seen rapid growth and are favored by users of all ages. However, in the age of information overload, the quality of interactions on social media platforms varies significantly, leading to negative feelings among users and affecting their overall experience and loyalty. This study takes the Flow theory as its starting point and investigates the needs of social media users at various stages of the flow experience. We propose modifications to the flow theory model with the aim of enhancing user experience and satisfaction. Firstly, based on literature review, we identify micro-level issues of the product, propose hypotheses, and construct validation experiments in the context of social media. The experiment collects Electrodermal Activity (EDA) and heart rate variability (HRV) data of 31 participants using a multi-channel physiological instrument and collects their emotional experience data using the Pleasure-Arousal-Dominance (PAD) scale. Results indicate that a combined textual-graphical interface layout is superior to other layouts in positively inducing flow and emotional experiences. Positive content tonality is more effective at eliciting positive flow and emotional experiences than negative or neutral content. Video presentations have a stronger sense of immersion and emotional expression, making them more conducive to inducing flow experiences and positive emotional feedback. This study, grounded in user psychology, provides a theoretical framework based on flow and emotional experiences for social media product design, quantitatively examining the positive psychological activities of users when using social media.

With the rapid growth of smart terminal industry and User-Generated Content products, Social Media Applications (SMA) products, represented by TikTok, have been booming growth. How to capture and maintain users’ attention in order to prolong their stay on the product and increase customer stickiness has become the focus of the industry. Therefore, according to the duration and characteristics of users using SMA, this paper takes the layout of SMA as an example to study the visual attention quality. Firstly, through the literature review, the study of visual attention quality in SMA was summarized into four aspects, including the span, maintenance, allocation, and switch of attention. Secondly, eye movement and behavior experiments were designed based on common content consumption tasks of SMA users to verify the hypotheses proposed in this paper. According to the results: (1) In terms of attention maintenance, linear layout outperformed masonry layout, masonry layout outperformed matrix layout, and in terms of attention span, the reverse was true; (2) In attention allocation, linear layout showed the best anti-interference characteristics; The masonry layout is suitable to be used in the task search stage and also in the dual-task execution stage; (3) In terms of attention switch, the energy cost of attention switch increased in the order of matrix layout, masonry layout and linear layout. (4) In terms of interaction, double-clicking interaction had more advantages in attention allocation and cognitive load than swiping interaction. The research in this paper has provided objective and quantitative data support for the design and operation of SMA products.