User Interest Research Articles

TCSR: Self‐attention with time and category for session‐based recommendation

AbstractSession‐based recommendation that uses sequence of items clicked by anonymous users to make recommendations has drawn the attention of many researchers, and a lot of approaches have been proposed. However, there are still problems that have not been well addressed: (1) Time information is either ignored or exploited with a fixed time span and granularity, which fails to understand the personalized interest transfer pattern of users with different clicking speeds; (2) Category information is either omitted or considered independent of the items, which defies the fact that the relationships between categories and items are helpful for the recommendation. To solve these problems, we propose a new session‐based recommendation method, TCSR (self‐attention with time and category for session‐based recommendation). TCSR uses a non‐linear normalized time embedding to perceive user interest transfer patterns on variable granularity and employs a heterogeneous SAN to make full use of both items and categories. Moreover, a cross‐recommendation unit is adapted to adjust recommendations on the item and category sides. Extensive experiments on four real datasets show that TCSR significantly outperforms state‐of‐the‐art approaches.

What drives user interest and purchase of virtual 3D assets? An empirical investigation of 3D model attributes and pricing dynamics

Virtual 3D assets, i.e., 3D models that form the basis of virtual environments, products, and goods, are essential for the creation of a future metaverse. However, we have limited knowledge about the market dynamics in which virtual 3D assets are traded and the indicators that influence their value and pricing − and thus the purchasing mechanisms. The present study draws on multi-attribute utility and value- and competition-informed pricing theory to determine what drives the purchase of virtual 3D assets using secondary data from the marketplace Sketchfab. The empirical analysis indicates that the sellers’ value perception of virtual 3D assets contradicts the users’ interest and that organizational sellers outperform individual sellers by relying to a higher degree on competition- and value-informed pricing. Based on our findings, we identify implications for both organizational and individual sellers to refine their pricing strategies in accordance with the unique dynamics of 3D virtual asset marketplaces.

Evaluating the Economic Viability of Agro-Ecotourism as a Nature-Based Solution for a Climate Adaptation Strategy: A Case Study of Yuanshan Township, Taiwan

This study applied the contingent valuation method to evaluate the economic viability of climate adaptation policies in the climate-fragile Yuanshan Township (YST), Taiwan, focusing on the balance between forest conservation and local livelihoods. Traditional agriculture in YST is transitioning to agro-ecotourism, supported by leisure-oriented and hillside forest protection policies that attract visitors and cause the local economy to thrive. This research used non-market valuation methods to quantify the value of local recreational resources perceived by visitors at NTD 1002.00 per visitor. The findings indicate that visitors’ willingness to pay for these resources is significantly influenced by their intention to revisit YST, their trust in local conservation efforts, their gender, and their income. The value that visitors place on recreational resources and the aforementioned significant determinants of their willingness to pay highlight the economic potential of agro-ecotourism in supporting both environmental sustainability and community income. This study emphasizes that successful nature-based climate adaptation must consider the economic interests of resource users and local residents. Agro-ecotourism in YST is shown to be a viable policy for balancing forest conservation with societal benefits, providing a model for the sustainable management of local resources. The economic benefits from this transition underscore the feasibility of agricultural transformation for community income generation and climate resilience, demonstrating that environmental and economic goals can be mutually supportive in addressing climate change.

HyperCLR: A Personalized Sequential Recommendation Algorithm Based on Hypergraph and Contrastive Learning

Sequential recommendations aim to predict users’ next interactions by modeling their interaction sequences. Most existing work concentrates on user preferences within these sequences, overlooking the complex item relationships across sequences. Additionally, these studies often fail to address the diversity of user interests, thus not capturing their varied latent preferences effectively. To tackle these problems, this paper develops a novel recommendation algorithm based on hypergraphs and contrastive learning named HyperCLR. It dynamically incorporates the time and location embeddings of items to model high-order relationships in user preferences. Moreover, we developed a graph construction approach named IFDG, which utilizes global item visit frequencies and spatial distances to discern item relevancy. By sampling subgraphs from IFDG, HyperCLR can align the representations of identical interaction sequences closely while distinguishing them from the broader global context on IFDG. This approach enhances the accuracy of sequential recommendations. Furthermore, a gating mechanism is designed to tailor the global context information to individual user preferences. Extensive experiments on Taobao, Books and Games datasets have shown that HyperCLR consistently surpasses baselines, demonstrating the effectiveness of the method. In particular, in comparison to the best baseline methods, HyperCLR demonstrated a 29.1% improvement in performance on the Taobao dataset.

Graph contrast learning for recommendation based on relational graph convolutional neural network

Current knowledge graph-based recommendation methods heavily rely on high-quality knowledge graphs, often falling short in effectively addressing issues such as the cold start problem and heterogeneous noise in user interactions. This leads to biases in user interest and popularity. To overcome these challenges, this paper introduces a novel recommendation approach termed Knowledge-enhanced Perceptive Graph Attention with Graph Contrastive Learning (KPA-GCL), which leverages relational graph convolutional neural networks. The proposed method optimizes the triplet embedding representation of entity-item interactions based on relationships between adjacent entities in a heterogeneous graph. Subsequently, a graph convolutional neural network is employed for enhanced aggregation. Similarity scores from a contrastive view serve as the selection criterion for high-quality embedded representations, facilitating the extraction of refined knowledge subgraphs. Multiple adaptive contrast-loss optimization functions are introduced by combining Bayesian Personalized Ranking (BPR) and hard negative sampling techniques. Comparative experiments are conducted with ten popular existing methods using real public datasets. Results indicate that the KPA-GCL method outperforms compared methods in all datasets based on Recall, NDCG, Precision, and Hit-ratio measures. Furthermore, in terms of mitigating cold start and noise, the KPA-GCL method surpasses other ten methods. This validates the reasonability and effectiveness of KPA-GCL in real-world datasets.

Fuzzy-Logic-Based Cascaded Decentralized Control and Power Quantification of Residential Buildings for Effective Energy Load Management

In large buildings, effective load shedding and shifting and providing the maximum power through solar renewable sources remain challenges because of users’ unpredictable load consumption. Conventionally, load shifting, load shedding, and load covering are majorly dependent on user inputs. The lack of user interest in participating in demand responses for effective load shifting and covering remains a problem. Effective load covering through renewables and user-friendly load shedding and shifting with maximized user participation are challenging and demand high-resolution user load consumption information, which are not possible without sophisticated communication and digital twins. In this research work, a novel fuzzy-logic-based cascaded decentralized load-controlling mechanism has been developed that manages the residential building load through load-shifting, load-covering, and load-shedding schemes without any communication protocols and digitization between residential units. The decentralized controller aims to effectively utilize the centralized resources of power generation with the effective automated participation of users. The quantification of the load shifting, covering, and shedding performed during peak hours was well covered under the load-covering scheme, and the results showed that flexibility capacities of 1617 kW were achieved for load covering, 294 kW for load shedding, and 166.34 kW through shifting. A total load of 60 kW, which was reduced during shedding and shifting, was well covered during load covering through renewables.

Assessing and Enhancing Movement Quality Using Wearables and Consumer Technologies: Thematic Analysis of Expert Perspectives.

Improvements in movement quality (ie, how well an individual moves) facilitate increases in movement quantity, subsequently improving general health and quality of life. Wearable technology offers a convenient, affordable means of measuring and assessing movement quality for the general population, while technology more broadly can provide constructive feedback through various modalities. Considering the perspectives of professionals involved in the development and implementation of technology helps translate user needs into effective strategies for the optimal application of consumer technologies to enhance movement quality. This study aimed to obtain the opinions of wearable technology experts regarding the use of wearable devices to measure movement quality and provide feedback. A secondary objective was to determine potential strategies for integrating preferred assessment and feedback characteristics into a technology-based movement quality intervention for the general, recreationally active population. Semistructured interviews were conducted with 12 participants (age: mean 42, SD 9 years; 5 males) between August and September 2022 using a predetermined interview schedule. Participants were categorized based on their professional roles: commercial (n=4) and research and development (R&D; n=8). All participants had experience in the development or application of wearable technology for sports, exercise, and wellness. The verbatim interview transcripts were analyzed using reflexive thematic analysis in QSR NVivo (release 1.7), resulting in the identification of overarching themes and subthemes. Three main themes were generated as follows: (1) "Grab and Go," (2) "Adjust and Adapt," and (3) "Visualize and Feedback." Participants emphasized the importance of convenience to enhance user engagement when using wearables to collect movement data. However, it was suggested that users would tolerate minor inconveniences if the benefits were perceived as valuable. Simple, easily interpretable feedback was recommended to accommodate diverse audiences and aid understanding of their movement quality, while avoiding excessive detail was advised to prevent overload, which could deter users. Adaptability was endorsed to accommodate progressions in user movement quality, and customizable systems were advocated to offer variety, thereby increasing user interest and engagement. The findings indicate that visual feedback representative of the user (ie, an avatar) should be used, supplemented with concise text or audible instructions to form a comprehensive, multimodal feedback system. The study provides insights from wearable technology experts on the use of consumer technologies for enhancing movement quality. The findings recommend the prioritization of user convenience and simplistic, multimodal feedback centered around visualizations, and an adaptable system suitable for a diverse audience. Emphasizing individualized feedback and user-centric design, this study provides valuable findings around the use of wearables and other consumer technologies to enhance movement quality among the general population. These findings, in conjunction with those of future research into user perspectives, should be applied in practical settings to evaluate their effectiveness in enhancing movement quality.

Cocreative Development of Robotic Interaction Systems for Health Care: Scoping Review.

Robotic technologies present challenges to health care professionals and are therefore rarely used. Barriers such as lack of controllability and adaptability and complex control functions affect the human-robot relationship. In addition to educational opportunities, the possibility of individual adaptation can improve the usability and practical implementation of robotics. Previous work has focused on developments from a technology-centered perspective and has included user interests too late in the process. This study addresses the following research question: What cocreative research approaches are used in the field of nursing robotics to improve the usability, intended use, and goal-directed application of robotic developments for nurses and to support the nursing process? This scoping review provides an overview of the topic and the research activities taking place within it. Five databases and the reference lists of the identified publications were searched for studies without further restrictions. Studies were included if they developed and evaluated interaction and control platforms for robotic systems in health care in a cocreative way with end users. The search resulted in 419 hits, of which 3 publications were included. All publications were feasibility or user studies that were mainly carried out in the European Union. The 3 interaction and control platforms presented were all prototypes and not commercially available. In addition to those in need of care, all studies also included family carers and health care professionals. Robotic interaction and control platforms in health care are rarely, if ever, developed and evaluated with feasibility or user studies that include prototypes and end users. While the involvement of end users is crucial, this review emphasizes that all stakeholders, including health care professionals, should participate in the development process to ensure a holistic understanding of application needs and a focus on user experiences and practical health care needs. It is emphasized that the active involvement of end users in the development process is critical to effectively meeting the needs of the target group.

The Influence of Perceived Use of Gopay On Ease of Payment And Improvement of Security Quality In Student Transactions of Faculty of Economics, University of Jakarta

Abstract This study aims to look at the relationship between perceptions of GoPay use, ease of payment, security quality and transaction interest in students of the Faculty of Economics, State University of Jakarta. This study involved FE UNJ students who used the GoPay service with 110 respondents selected using purposive sampling and data collected using a questionnaire via Google From. The research method used is quantitative method. To analyze the data results, researchers used the SmartPLS 4 application to determine the relationship between variables or hypotheses. The results of this study indicate a positive and significant relationship between variables or hypotheses, namely: perceived ease of use affects interest in using GoPay, perceived ease of use affects interest in using GoPay as a transaction tool, perceived use affects user interest as a transaction tool and perceived efficiency affects interest in using GoPay as a transaction tool.

A Symbolic Algorithm to Obtain Low or High Degree Splines from Discrete Fourier Transforms

Obtaining high-degree splines with the use of traditional spline interpolation methods is not an easy task; therefore, traditional spline interpolation is typically limited to cubic splines. In this paper, we present a symbolic and numeric algorithm to obtain splines of any degree, while providing detailed procedures and examples of how to use this algorithm so that it is immediately useful for an interested user. This method, which was initially developed by Beaudoin and Beauchemin [2, 3], works for splines of any degree and yields very accurate results when the boundary conditions are chosen wisely. It also provides approximations of higher order derivatives, something that is not available with the use of cubic splines. This paper presents formulas that can be used in a straightforward manner to obtain interpolation splines of first degree (linear splines), second degree (parabolic splines) and third degree (cubic splines). For splines of higher degree, a short but complete symbolic algorithm to compute the formulas is presented. The resulting formulas can be used in the same manner as those presented for splines of lower degree. A complete numerical example is included to show how the results are obtained and a link to the complete Maple source code is given.

Unveiling user interests: A deep user interest exploration network for sequential location recommendation

Sequential location recommendation, also known as next location prediction, is a crucial task aiming to compute the likelihood of a user visiting a certain point of interest (POI). It has significant applications in route planning and location-based advertisements. Despite the utilization of geographical information, existing methods often adopt a rigidly sequential prediction mode, focusing solely on predicting the next destination (i.e., where to go), which limits their ability to effectively model user trajectories in terms of predicting from where the user came. Moreover, these methods struggle to capture the evolving and deep user interests along their trajectory. To deal with these problems, we propose a novel approach called Deep User Interest Exploration Network (DUIEN) for sequential location recommendation. DUIEN incorporates two essential components to enhance recommendation accuracy. First, we employ a bidirectional neural network with the Cloze objective, enabling it to predict random masked POIs within user trajectories. This approach aids the model in gaining a better understanding of the context and dynamics of user trajectories. Second, we introduce a user interest exploration layer that seamlessly integrates into the sequential learning process. This layer effectively utilizes tag information associated with POIs and learns the intricate interplay between user interests and their trajectories using a deep user interest exploration method. In our experiments, DUIEN outperforms state-of-the-art sequential location recommendation models, demonstrating the effectiveness of the designed update mechanisms for deep user interest exploration. This showcases the potential of our approach to significantly enhance the accuracy of sequential location recommendation.

Graphical contrastive learning for multi-interest sequential recommendation

Multi-interest sequential recommendation aims to deliver accurate recommendations by modeling users’ sequential behaviors and multi-faceted interests. Contrastive learning (CL) possesses an inborn advantage in distinguishing users’ multiple interests. However, existing CL-based multi-interest sequential recommenders tend to overlook the issue of data sparsity which deteriorates model performance. Graph neural network (GNN), on the other hand, has been proven as an effective measure of tackling the data sparsity problem. However, incorporating GNN into CL requires a delicate design to simultaneously achieve distinctive interest representation learning and relieve data sparsity. To address the challenges, we propose a Graphical Contrastive Learning for Multi-Interest Sequential Recommendation (GCL4MI), which first extracts user interest and constructs interest-specific graph based on item clusters and then perform graphical contrastive learning to enhance the independence between multiple interests. Furthermore, we explore different extensible CL sampling strategies with the facilitation of GNN to learn distinct interests in a high-cohesion and low-coupling manner. Extensive experiments on three real-world datasets demonstrate that our proposed GCL4MI significantly outperforms state-of-the-arts, with average lifts of 7.0%, 7.1%, and 5.8% on recall, NDCG, and HR, respectively.

Pengaruh Daya Tarik Iklan Dan Electronic Word Of Mouth (E-Wom) Terhadap Minat Pengguna Jasa Transportasi Online Grab: Studi pada Mahasiswa/I Universitas Buana Perjuangan Karawang

The emergence of the Grab service in Indonesia is an example of how the contemporary era and globalization have encouraged innovation and change. The business actively uses internet marketing techniques, with a focus on making advertising and electronic word of mouth more attractive to attract users. This research tries to find the impact of advertising attractiveness on e-Wom as well as the impact of user interest in Grab influenced by advertising and electronic word-of-mouth. SmartPLS 4 analysis is used in a research approach with the student population of Buana Perjuangan University, Karawang. By implementing the Slovin formula in the analysis, a sample of 385 respondents was selected with an error rate of 5%. The findings of this study show that e-Wom is strongly influenced by advertising attractiveness, and users' propensity to purchase Grab services is very positively influenced by e-Wom and advertising attractiveness.

Knowledge distillation-based abnormal power consumption pattern detection for edge environment

Abstract Abnormal power consumption pattern detection can effectively reduce the non-technical loss of electric energy, which is of great significance in maintaining the safe operation of the power grid and protecting the rights and interests of normal users. However, for edge environments with limited communication conditions, uploading electricity consumption data to the cloud for centralized computation is prone to problems such as network congestion and transmission delays. For this reason, this paper proposes a knowledge distillation (KD)-based anomalous power consumption pattern detection model that can be deployed at edge computing terminals. First, the ResNet50 network is selected as the teacher model, and the self-attention mechanism (SAM) is introduced to improve the feature extraction capability of long-term dependency. Then, ResNet18 is used as the student model, and the difference between the output of the student model and the output of the teacher model is minimized by optimizing the distillation loss function. Finally, the effectiveness of the proposed method is verified in practice.

AI-empowered consumer behavior analysis for trustworthy track recommendation over musical dance electronic products

—In the digital music era, accurate and trustworthy track recommendations for musical dance electronic products are becoming increasingly important to improve user experiences and attract more consumers. Consumer behavior modeling is critical in user interest learning and has been extensively used in recommender systems to improve recommendation accuracy. This paper proposes a novel AI-empowered consumer behavior analysis method for trustworthy track recommendations over musical dance electronic products. Specifically, we first model consumer behavior by integrating collaborative filtering and a hidden Markov model to capture the key interactive patterns between consumers and musical dance electronic products. Then, we develop a trustworthy track recommendation method based on multi-layer attention representation learning, which leverages scattering transform for audio preprocessing and attention-based independent recurrent neural networks for encoding user preferences and product features. Extensive experiments on real-world datasets demonstrate the superiority of our proposed method in terms of recommendation accuracy and trustworthiness.

중국 택배기업의 서비스 품질이 고객만족도와 지속사용의도에 미치는 영향에 관한 연구

As an important part of the postal industry after the reform and opening up, Chinese courier services have made rapid development. However, there are also problems with the development of Chinese courier companies, such as uneven service quality and difficulty in protecting the rights and interests of users. With the increasingly explosive development of e-commerce such as C2C, problems are increasing along with the rapid development of the courier industry. Whether it is the final stage of online marketing and distribution or the service industry, the overall service quality of the courier industry has declined. For example, consumer complaints have increased and netizens have complained. As consumers’ rights protection consciousness is strengthened, one of the ways to increase customer satisfaction is to improve the quality of service of the company and increase the customer’s intention to continue using it.

Analysis on recommendation systems based on ML and DL approaches

The explosive growth of the Internet has led to an unprecedented increase in available information, creating a major challenge in identifying content that aligns with user interests. Recommendation systems (RS) address this challenge by providing personalized content recommendations based on user behavior and preferences. This article systematically reviews the evolution of recommendation systems with a focus on the methodologies of machine learning (ML) and deep learning (DL). It highlights core technologies in ML-based RS, such as content-based recommendation, collaborative filtering (CF), and hybrid filtering (HF). The article evaluates the effectiveness of various DL models, including autoencoders (AE), convolutional neural networks (CNN), and recurrent neural networks (RNN). The review also addresses key challenges faced by RS, such as cold start issues and the need for improved model transparency and interpretability. DL methods are shown to significantly enhance recommendation accuracy by leveraging complex patterns in large-scale data, to improve the user experience. Future research directions include refining data preprocessing, enhancing feature engineering, compressing and accelerating DL models, and improving interpretability through advanced mechanisms. This study provides valuable insights and references for researchers aiming to advance recommendation system design and performance optimization.

Enhancing Repurchase Intention: The Impact of Service Quality and Facilities at Garuda Pontianak Hotel

This research aims to find out whether there is a relationship between service quality and facilities. With a positive data collection strategy and a sample size of 100 participants, this research applies associative methodology. Participants must be customers who have used Garuda Pontianak hotel services at least twice, in order to be considered for taking part in this research. Statistical methods used in the analysis include: multiple linear regression, correlation and determination coefficients, simultaneous testing (F test), and partial testing (t test). The data are linear, normally distributed, and show no signs of multicollinearity; these findings were confirmed by standard assumption tests. The variables included in this study contributed 61% of the variance in repurchase interest, while the remaining 39% was influenced by other factors that could not be explained. Initial research shows that the quality of services and facilities available at the Garuda Pontianak hotel has a significant effect on repurchase interest for users of Garuda hotel services in Pontianak City.

Keywords-enhanced Contrastive Learning Model for travel recommendation

Travel recommendation aims to infer travel intentions of users by analyzing their historical behaviors on Online Travel Agencies (OTAs). However, crucial keywords in clicked travel product titles, such as destination and itinerary duration, indicating tourists’ intentions, are often overlooked. Additionally, most previous studies only consider stable long-term user interests or temporary short-term user preferences, making the recommendation performance unreliable. To mitigate these constraints, this paper proposes a novel Keywords-enhanced Contrastive Learning Model (KCLM). KCLM simultaneously implements personalized travel recommendation and keywords generation tasks, integrating long-term and short-term user preferences within both tasks. Furthermore, we design two kinds of contrastive learning tasks for better user and travel product representation learning. The preference contrastive learning aims to bridge the gap between long-term and short-term user preferences. The multi-view contrastive learning focuses on modeling the coarse-grained commonality between clicked products and their keywords. Extensive experiments are conducted on two tourism datasets and a large-scale e-commerce dataset. The experimental results demonstrate that KCLM achieves substantial gains in both metrics compared to the best-performing baseline methods. Specifically, HR@20 improved by 5.79%–14.13%, MRR@20 improved by 6.57%–18.50%. Furthermore, to have an intuitive understanding of the keyword generation by the KCLM model, we provide a case study for several randomized examples.

Motivations for Using Religious Digital Media: A Hierarchical Regression Analysis Among Jordanian University Students

This study investigated the factors influencing motivations for using religious digital media (RDMUM) among 330 Jordanian university students through hierarchical regression analysis. The analysis revealed that demographic factors, particularly age and gender, significantly predicted motivation, with younger individuals and males showing higher engagement. Educational level, explicitly having a BA degree, also influences motivation, whereas university location and specialization do not have significant effects. The type of digital media used (websites, social media, podcasts) does not significantly impact motivation, although a negative association with Twitter suggests that platform-specific characteristics may affect engagement. Prior knowledge and specific interests in Islamic thought, faith, and jurisprudential topics are strong motivators that highlight the importance of content relevance and depth. The final model, which explains 49% of the variance in the RDMUM, underscores the robust explanatory power of the included variables. These findings emphasize the need for tailored content to address user interests and knowledge levels. Content creators and practitioners can leverage these insights to develop more engaging and effective religious digital media, ultimately enhancing users’ engagement and satisfaction. Moreover, this study's potential to inspire and guide future research in this field is significant and contributes to the academic community's understanding of religious digital media.