User Interest Research Articles

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.

Bibliographic Culture as a Factor of Security of Trusted Public Internet

The article deals with the problem of security of search in modern public computer-network resources of reliable, complete sources, their qualitative bibliographic description. The relevance is due to the “digital transformation”, the rapid spread of computer-network technologies since the 2010s to all sectors, as well as everyday life; a sharp and significant increase in the number and variety of electronic databases (libraries); turning the majority of humanity into daily active users. Objective international and national diseases of growth of standardization, streamlining, structuring of databases, development of indexing systems and search public network services, means of verification of electronic documents have manifested themselves.Since 2014 and even later from 2022, the problem was exacerbated by the reduction of international cooperation in computer-network technologies, anti-Russian sanctions of unfriendly countries, violation of Russian legislation by global digital corporations, leapfrogging strengthening of cybercrime and information confrontation in the Internet. The possibilities of attackers who, by exploiting vulnerabilities, reduced the access of mass users to reliable electronic documents in cross-border Internet communications increased. The opportunities caused by the relativistic understanding of truth, fabrication and broadcasting of falsified information, fake news, disinformation, use of new means of “social engineering” (fraud, manipulation of consciousness) that threaten citizens and national interests of Russia have increased.The novelty of the study lies in the integrated application of theoretical and cultural gnoseology (culture of cognition) and methodology of information security (countering deliberate attempts to mislead). The comparative analysis revealed significant differences between Russian state electronic libraries, document management systems, registers and services and non-state, as well as foreign public Internet resources and services. The result of the study is the conclusion about the importance of the prevalence of essential interests of mass users of Russian public libraries and electronic services. Recommendations on the preferability of applying this experience in the creation and modernization of Russian public non-state digital databases, libraries, services, as well as the development of standardization on its basis are formulated.

IDC-CDR: Cross-domain Recommendation based on Intent Disentanglement and Contrast Learning

Using the user’s past activity across different domains, the cross-domain recommendation (CDR) predicts the items that users are likely to click. Most recent studies on CDR model user interests at the item level. However because items in other domains are inherently heterogeneous, direct modeling of past interactions from other domains to augment user representation in the target domain may limit the effectiveness of recommendation. Thus, in order to enhance the performance of cross-domain recommendation, we present a model called Cross-domain Recommendation based on Intent Disentanglement and Contrast Learning (IDC-CDR) that performs contrastive learning at the intent level between domains and disentangles user interaction intents in various domains. Initially, user–item interaction graphs were created for both single-domain and cross-domain scenarios. Then, by modeling the intention distribution of each user–item interaction, the interaction intention graph and its representation were updated repeatedly. The comprehensive local intent is then obtained by fusing the local domain intents of the source domain and the target domain using the attention technique. In order to enhance representation learning and knowledge transfer, we ultimately develop a cross-domain intention contrastive learning method. Using three pairs of cross-domain scenarios from Amazon and the KuaiRand dataset, we carry out comprehensive experiments. The experimental findings demonstrate that the recommendation performance can be greatly enhanced by IDC-CDR, with an average improvement of 20.62% and 25.32% for HR and NDCG metrics, respectively.

Hybrid Text Embedding and Evolutionary Algorithm Approach for Topic Clustering in Online Discussion Forums

Leveraging discussion forums as a medium for information exchange has led to a surge in data, making topic clustering in these platforms essential for understanding user interests, preferences, and concerns. This study introduces an innovative methodology for topic clustering by combining text embedding techniques—Latent Dirichlet Allocation (LDA) and BERT—trained on a singular autoencoder. Additionally, it proposes an amalgamation of K-Means and Genetic Algorithms for clustering topics within triadic discussion forum threads. The proposed technique begins with a preprocessing stage to clean and tokenize textual data, which is then transformed into a vector representation using the hybrid text embedding method. Subsequently, the K-Means algorithm clusters these vectorized data points, and Genetic Algorithms optimize the parameters of the K-Means clustering. We assess the efficacy of our approach by computing cosine similarities between topics and comparing performance against coherence and graph visualization. The results confirm that the hybrid text embedding methodology, coupled with evolutionary algorithms, enhances the quality of topic clustering across various discussion forum themes. This investigation contributes significantly to the development of effective methods for clustering discussion forums, with potential applications in diverse domains, including social media analysis, online education, and customer response analysis.

Zero-Shot Content-Based Crossmodal Recommendation System

Information Recommendation (IR) systems are conventionally designed to operate within a single modality at a time, such as Text2Text or Image2Image. However, the concept of cross-modality aims to facilitate a versatile recommendation experience across different modalities, such as Text2Image. In recent years, significant strides have been made in developing neural recommender models that are multimodal and capable of generalizing across a broad spectrum of domains in a zero-shot manner, thanks to the robust representation capabilities of neural networks. These architectures enable the generation of embeddings for assets (i.e., content uploaded on a platform by users), presenting a concise representation of their semantics and allowing for comparisons through similarity ranking. In this paper, we present ZCCR, a Zero-shot Content-based Crossmodal Recommendation System that leverages knowledge from large-scale pretrained Vision-Language Models (VLMs) such as CLIP and ALBEF to redefine the recommendation task as a zero-shot retrieval task, eliminating the need for labeled data or prior knowledge about the recommended content. Furthermore, ZCCR performs crossmodal similarity search on an optimized index, such as FAISS, to improve the speed of recommendation. The goal is to recommend to the user assets that are similar to those they have previously uploaded, commonly referred to as their user profile. Within the user profile, we identify “areas of interest”—groups of assets associated with specific user interests, such as cooking, sports, or cars. To identify these areas of interest and construct the search query for the retrieval operation, ZCCR employs an innovative use of Agglomerative Clustering. This technique groups user past assets by similarity without requiring prior knowledge of the number of clusters. Once the areas of interest, or clusters, are identified, the centroid is utilized as the search seed to find similar assets. Experimental results demonstrate the efficiency of the selected components in terms of search time and retrieval performance on modified MSCOCO and FLICKR30k datasets tailored for the recommendation task. Furthermore, ZCCR outperforms both a baseline tagging system (BT) and a more advanced tag system which utilizes a Large Language Model (LLM) to extract embeddings from tags. The results show that, even compared with the latter, embeddings directly extracted from raw assets yield superior outcomes compared to relying on intermediate tags generated by other tools. The code implementation to reproduce all experiments and results shown in this paper is provided at the following link: ZCCR-experiments.

User Acceptance of Blockchain Technology in Financial Applications: Information Security, Technology Awareness and Privacy Aspects

Blockchain technology is now an advanced and innovative database technology and the attributes of blockchains are apparent in a variety of industries, especially in the financial industry. One of the most famous blockchain use cases, cryptocurrencies, has provoked much interest in social network users and customers. According to CoinMarketCap’s information, the global crypto market capitalization has reached around USD 2.37 T and there are around 9975 different cryptocurrencies available in the market. Despite the fact that academia and industry have paid much attention towards the blockchain direction, there is not much research on the factors that influence customer acceptability. This paper studies blockchains from a different angle, probing the factors prompting customers to use financial applications that utilize blockchain technology. We established the model and sorted the individual factors of perceived information security, technology awareness and privacy and found that users’ acceptance is significantly affected by information security and technology awareness, while privacy does not significantly influence users. According to the findings, we provide useful insights for application developers, conclude by presenting the limitations of the research and provide guidelines for future research.

On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming from its interactive nature. The training of reinforcement learning-based recommender systems demands expensive online interactions to amass adequate trajectories, essential for agents to learn user preferences. This inefficiency renders reinforcement learning-based recommender systems a formidable undertaking, necessitating the exploration of potential solutions. Recent strides in offline reinforcement learning present a new perspective. Offline reinforcement learning empowers agents to glean insights from offline datasets and deploy learned policies in online settings. Given that recommender systems possess extensive offline datasets, the framework of offline reinforcement learning aligns seamlessly. Despite being a burgeoning field, works centered on recommender systems utilizing offline reinforcement learning remain limited. This survey aims to introduce and delve into offline reinforcement learning within recommender systems, offering an inclusive review of existing literature in this domain. Furthermore, we strive to underscore prevalent challenges, opportunities, and future pathways, poised to propel research in this evolving field.

Pengaruh Gaya Hidup dan Motivasi Belanja Hedonis Terhadap Minat Beli Pengguna Aplikasi Shopee di Kota Banjarmasin

This study aims to examine the influence of lifestyle and hedonic shopping motivation on the buying interest of Shopee application users in Banjarmasin City.The research method used is quantitative method. The number of samples used by 106 respondents was taken by purposive sampling. Data collection using online questionnaires. Data analysis methods use descriptive statistics, instrumental testing, multiple linear analysis and hypothesis testing. This test uses the help of SPSS 26 statistical software.The results of this study show that lifestyle variables (X1) have a significant positive influence on buying interest variables. The hedonic shopping motivation variable (X2) has a positive influence on the buying interest variable. Based on simultaneous testing, lifestyle variables (X1) and hedonic shopping motivation variables (X2) on the buying interest of shopee application users together have a significant influence.

The Challenges and Responses of Artificial Intelligence Technology to Journalism Ethics

With the popularization of artificial intelligence technology in the news industry, more and more people have begun to pay attention to and worry about journalism ethics. On the one hand, AI helps journalists to process and analyze massive information quickly and accurately, which improves the efficiency and quality of journalism and enhances the productivity and competitiveness of the news industry. On the other hand, the application of AI technology has generated many new problems and risks. However, due to its data-driven nature, it is difficult to avoid the existence of data loss, abuse and other problems, which can cause damage to the rights and interests of users and seriously affect the dissemination of false information. The article provides an in-depth analysis of the challenges in the application of artificial intelligence technology in the news industry and puts forward coping strategies for the reference of related personnel.