User Behavior Analysis Research Articles

Trust factor-based analysis of user behavior using sequential pattern mining for detecting intrusive transactions in databases

Trust factor-based analysis of user behavior using sequential pattern mining for detecting intrusive transactions in databases

Social media user behavior analysis applied to the fashion and apparel industry in the big data era

With the rapid development of the Internet and new media, the enormous data from social media and other public platforms have attracted increasing attention to user behavior research. Fashion is a hot topic for both the general public and the social economy, so there is great potential for exploring and manipulating social media data for the development of the fashion industry in the current era. This paper aims to explore the current status of social media user behavior analysis applied to the fashion and apparel industry for advanced product development, branding strategy planning and the resolution of other decision-making problems in the big data context. First, articles were retrieved from the database "Web of Science". With the assistance of experts, 201 articles were determined for further study. Next, the evolution of hot topics within the domain was visualized and discussed through bibliometric analysis. Then, the application of social media data in the fashion domain was investigated, and common data mining methods were discussed. Finally, the paper summarized the development status of social media user behavior analysis (SMUBA) applied to the fashion and apparel industry and put forward the future prospect under the framework of mass customization in the big data era.

User behaviors analysis on OTT platform with an integration of technology acceptance model

User behaviors analysis on OTT platform with an integration of technology acceptance model

Searching Online for Art and Culture: User Behavior Analysis

Searching Online for Art and Culture: User Behavior Analysis

Design of an automotive platform for computer vision research

The goal of our work is to design an automotive platform for AD/ADAS data acquisition and to demonstrate its application to behavior analysis of vulnerable road users. We present a novel data capture platform mounted on a Mercedes GLC vehicle. The car is equipped with an array of sensors and recording hardware including multiple RGB cameras, Lidar, GPS and IMU. For subsequent research on human behavior analysis in traffic scenes, we have conducted two kinds of data recordings. Firstly, we have designed a range of artificial test cases which we recorded on a safety regulated proving ground with stunt persons to capture rare events in traffic scenes in a predictable and structured way. Secondly, we have recorded data on public streets of Vienna, Austria, showing unconstrained pedestrian behavior in an urban setting, while also considering European General Data Protection Regulation (GDPR) requirements. We describe the overall framework including data acquisition and ground truth annotation, and demonstrate its applicability for the implementation and evaluation of selected deep learning models for pedestrian behavior prediction.

The internet-meme and the ethics: A review of scientific research for 2018–2022

The article accumulates, systematizes and qualifies the most significant modern and relevant scientific works in the field of digital ethics and memetics over the past five years by means of a semisystematic analysis. This method allows us to consider various areas of research for a specified period and provide an overview of scientific sources on issues of digital ethics and memetics. The studies reviewed by the author were selected on scientific and technical bases as eLibrary, CyberLeninka and CORE according to the following keywords: Internet meme, memetics, digital ethics, ethics of a journalist, social networks. The author’s focus is on identifying gaps in research on both internet memes and digital ethics. The author aims to identify different aspects of the relationship between the Internet meme and the ethics of its creation and distribution, as well as to outline the prospects for further research of the problems raised. The presented article specifies the range of existing semantic gaps in scientific concepts and identifies the main lines of development of the problem. As a result of the study the author notes that the study of creolized texts comes down to three problematic issues: how they influence the user’s picture of the world, how they become popular and who creates them. At the same time, the ethical side of the issue is not touched upon by the authors in their works. Most scholarly articles on digital ethics and journalism ethics boil down to three areas: analysis of codes of ethics, analysis of user behavior on social networks and analysis of the spread of fake information online. Thus, the author concludes that digital ethics scholars almost never consider Internet memes as a subject of study, and vice versa, researchers of Internet memes rarely address ethical issues in their works.

Research on Task Scenario-oriented Information User Concern Mining Technology

With the rapid evolution of war forms and the profound reform of combat forms, battlefield intelligence information will present complex and diverse characteristics. Faced with a large number of complex intelligence information, it is difficult for users to obtain the key information in the battlefield to make real-time decision aid by using traditional methods. Based on the analysis of user interaction behavior rules of intelligence users of different levels, different identities and different specialties facing different task scenarios and different battle stages, the information that users pay attention to, the way that users want to display information and the way that users want to input information can be obtained. Firstly, the task scene is modeled, and the current task scene can be sensed in real time. Secondly, the user behavior under the current scenario is collected and stored in the user behavior analysis sample database. Finally, the user behavior analysis model is constructed, and the model outputs the content that the current user pays attention to, the desired presentation way and the desired information input way. The mission-scenario-oriented information user concern mining technology is an important component of the mission-scenario-oriented information product adaptive service technology, which can support the collection of operational user behavior and the analysis of behavior rules in the interactive process of operational information. This technology mainly studied user interaction behavior preferences facing different task scenarios, and provides basis for information recommendation and information adaptive presentation.

Cyberattack Detection Framework Using Machine Learning and User Behavior Analytics

This paper proposes a novel framework to detect cyber-attacks using Machine Learning coupled with User Behavior Analytics. The framework models the user behavior as sequences of events representing the user activities at such a network. The represented sequences are then fitted into a recurrent neural network model to extract features that draw distinctive behavior for individual users. Thus, the model can recognize frequencies of regular behavior to profile the user manner in the network. The subsequent procedure is that the recurrent neural network would detect abnormal behavior by classifying unknown behavior to either regular or irregular behavior. The importance of the proposed framework is due to the increase of cyber-attacks especially when the attack is triggered from such sources inside the network. Typically detecting inside attacks are much more challenging in that the security protocols can barely recognize attacks from trustful resources at the network, including users. Therefore, the user behavior can be extracted and ultimately learned to recognize insightful patterns in which the regular patterns reflect a normal network workflow. In contrast, the irregular patterns can trigger an alert for a potential cyber-attack. The framework has been fully described where the evaluation metrics have also been introduced. The experimental results show that the approach performed better compared to other approaches and AUC 0.97 was achieved using RNN-LSTM 1. The paper has been concluded with providing the potential directions for future improvements.

A High Accuracy and Adaptive Anomaly Detection Model With Dual-Domain Graph Convolutional Network for Insider Threat Detection

Insider threat is destructive and concealable, making addressing it a challenging task in cybersecurity. Most existing methods transform user behavior into sequential information and analyze user behavior while neglecting structural information among users, resulting in high false positives. To solve this problem, in this paper, we propose Dual-Domain Graph Convolutional Network (referred to as DD-GCN), a graph-based modularized method for high accuracy and adaptive insider threat detection. The central idea is to convert user features and structural information into heterogeneous graphs in the light of various relationships and take user behavior and relationship into account together. To this end, a weighted feature similarity mechanism is applied to balance the feature similarity of users and original linkages among them so as to generate the fused structure. Next, specific graph embeddings are extracted from the original topology structure and fused structure simultaneously, which convert behavior information into high-level representations. Furthermore, an attention mechanism is applied to learn the adaptive importance weights of the user’s features in the corresponding embedding. The combination and difference constraints are proposed to enhance the learned embeddings’ commonality and the ability to capture different information. Extensive experiments on two real-world datasets clearly show that our proposed DD-GCN extracts the most correlated information from structural topology and feature information substantially, and achieves improved accuracy with a clear margin.

Modeling and Analyzing User Behavior Risks in Online Shopping Processes Based on Data-Driven and Petri-Net Methods

With the rapid spread of e-commerce and e-payment, the increasing number of people choose online shopping instead of traditional buying way. However, the malicious user behaviors have a significant influence on the security of users' accounts and property. In order to guarantee the security of shopping environment, a method based on Complex Event Process (CEP) and Colored Petri nets (CPN) is proposed in this paper. CEP is a data-driven technology that can correlate and process a large amount of data according to Event Patterns, and CPN is a formal model that can simulate and verify the specifications of the online shopping processes. In this work, we first define the modeling scheme to depict the user behaviors and Event Patterns of online shopping processes based on CPN. The Event Patterns can be constructed and verified by formal methods, which guarantees the correctness of Event Patterns. After that, the Event Patterns are translated into Event Pattern Language (EPL) according to the corresponding algorithms. Finally, the EPLs can be inserted into the complex event processing engine to analyze the users' behavior flows in real-time. In this paper, we validate the effectiveness of the proposed method through case studies.

A VR User Behavior Classification Method Integrating Scene Information and Operation Information

With the rapid growth of the virtual reality industry, the number of users participating in virtual reality has rapidly increased, and analyzing user behavior in virtual reality scenarios has become increasingly important. Compared with general time series classification tasks, the input sources in virtual reality are more complex and diverse, and traditional time series classification models are difficult to handle this complexity. This article designs a series of methods for classifying VR user behavior and conducts experiments. Apply video motion recognition methods to VR motion recognition based on VR scene data. Due to the ability to obtain a series of image data from both videos and scenes, this article uses the method of video action recognition to process VR scene data. On this basis, a series of fusion methods were designed to fuse the operational information of VR. Experiments have shown that these methods can effectively handle action recognition problems in VR scenes.

Analysis of online user sentiment and behavior in the tourism sector in Vietnam based on reviews and comments

As an attractive destination, Vietnam’s tourism industry attracts a large number of tourists and has become a spearhead industry that plays an important role in the country’s GDP. The large number of tourists leads to the development of the hotel industry, especially online hotel business services. Today, the explosion of social platforms and e-commerce sites has helped businesses collect large amounts of data from customer feedback. Exploiting this endless resource will give businesses a competitive advantage over competitors. Within the scope of this research, the sentiment analysis based on reviews and comments is focused on considering. Sentiment analysis is very useful to help business managers understand the needs and desires of customers. From there, come up with appropriate strategies to develop and improve the quality of products and services. The data of the study was collected on the online travel platform agoda.com with 272,835 comments. Research using machine learning models and algorithms Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Naive Bayes (NB) to evaluate and analyze customer views in the business sector online hotel business in Vietnam. The research results have high accuracy up to 90% in both English and Vietnamese.

Human-computer interaction for virtual-real fusion

Human-computer interaction for virtual-real fusion

The Utility Impact of Differential Privacy on Credit Card Data in Machine Learning Algorithms

With the development of networks and financial technologies, credit card data is increasingly being used in various fields of data analysis such as user behavior, financial transactions, and market analysis. These fields often use multiple machine learning algorithms for data mining on credit card dataset. It is worth noting that credit card data contains more diverse and comprehensive information compared to traditional data, and the dataset may contain multiple data types. At the same time, credit card data may also expose users’ privacy information. Differential privacy algorithms can add random noise to the data set, protecting sensitive information while ensuring certain data utility. However, there has been little research on the use of differential privacy algorithms on credit card data in multiple machine learning algorithms, and there has been insufficient exploration of the utility impact of differential privacy on complex credit card data. These research gaps exist in both the financial technology and privacy protection industries. Therefore, this paper applies differential privacy to credit card data in multiple classic machine learning algorithms, discusses the utility impact of various differential privacy algorithms on credit card data, and compares the performance of credit card data sets protected by differential privacy in different algorithms.

Evaluation criteria for network security solutions based on behaviour analytics

This research aims to develop a set of evaluation criteria to identify and select a reliable user entity behaviour analytics (UEBA) solution for enterprises. A quantitative method is used to validate a set of evaluation criteria. Data were obtained from 280 high-profile network security professionals and analysed. Researchers used confirmatory factor analysis to validate the measurement model for convergent validity and reliability of criteria constructs, including evaluating the priority of each criterion item by security professionals. Findings depict that UEBA criteria are a multidimensional construct comprising six factors: 1) general capabilities; 2) use cases; 3) log reports for analysis of user behaviour; 4) profiling models; 5) alert reports; 6) integration with other solutions. Although the study's limitations might come from the respondents if selected globally, the results might be somewhat different. The novelty of this research work lies in developing and validating an instrument, empirically tested and validated by network security professionals and used by them to choose a reliable solution for their companies and what features of network security solutions are a must as per the perception of high profile users.

Chatbots in Online Marketing: A work in progressNajlae Zhani

In the digital era, chatbots have emerged as a transformative tool in online marketing (Crolic et al. 2022). This abstract introduces an ongoing research endeavor that specifically explores the role of chatbots in online marketing strategies. The research is a work in progress, aimed at understanding and contributing to the dynamic field of chatbot marketing. In today's dynamic digital landscape, chatbots have gained prominence as a powerful element of online marketing (Nwachukwu and Affen, 2023). This abstract serves as a preliminary exploration of the role of chatbots and conveys that our research is in progress, intended to provide insights into their evolving significance in online marketing. Chatbots, AI-driven virtual conversational agents, are becoming ubiquitous in digital marketing. Our research in progress focuses on understanding how these chatbots engage with customers, answer queries, and facilitate personalized interactions. We explore how chatbots enhance customer experience and drive engagement on websites and messaging platforms. A key aspect of our research in progress is dedicated to conversational marketing, wherein chatbots play a pivotal role in guiding customers through their journey. We investigate how chatbots create a seamless conversational experience and the impact on lead generation and conversions. Our research explores how chatbots collect and analyze data to offer personalized recommendations and insights. We aim to understand how chatbots leverage data-driven personalization to enhance user experience and provide tailored solutions to customers. As part of our research in progress, we delve into the future of chatbots in marketing. We anticipate discussing emerging trends and potential challenges, such as the integration of chatbots with emerging technologies, including voice assistants and augmented reality. Methodology and Data Collection Our ongoing research employs a mixed-method approach, combining quantitative and qualitative data collection techniques. We conduct surveys, interviews, and user behavior analysis to gather insights into how chatbots are perceived and utilized by businesses and consumers. Implications for Businesses Our research aims to offer practical insights for businesses aiming to leverage chatbots in their marketing strategies. We discuss potential benefits and challenges, providing guidance on the optimal use of chatbots to drive brand engagement and customer satisfaction. In conclusion, this abstract represents an ongoing research initiative focusing on the pivotal role of chatbots in online marketing. By emphasizing that our research is a work in progress, we signal our commitment to contributing to the evolving field of chatbot marketing. As we continue our research journey, we anticipate providing valuable insights to assist businesses in harnessing the potential of chatbots for online marketing success.

Context-Aware and Click Session-Based Graph Pattern Mining With Recommendations for Smart EMS Through AI

In the field of Artificial Intelligence (AI), Smart Enterprise Management Systems (Smart EMS) and big data analytics are the most prominent computing technologies. A key component of the Smart EMS system is E-commerce, especially Session-based Recommender systems (SRS), which are typically utilized to enhance the user experience by providing recommendations analyzing user behavior encoded in browser sessions. Also the work of the recommender is to predict users’ next actions (click on an item) using the sequence of actions in the current session. Current developments in session-based recommendation have primarily focused on mining more information accessible within the current session. On the other hand, those approaches ignored sessions with identical context for the current session that includes a wealth of collaborative data. Therefore this paper proposed Context-aware and Click session-based graph pattern mining with recommendations for Smart EMS through AI. It employs a novel Triple Attentive Neural Network (TANN) for SRS. Specifically, TANN contains three main components, i.e., Enhanced Sqrt-Cosine Similarity based Neighborhood Sessions Discovery (NSD), Frequent Subgraph Mining (FSM) using Neighborhood Click session-based graph pattern mining and Top-K possible Next-clicked Items Discovery (TNID). The NSD module uses a session-level attention mechanism to find m most similar sessions of the query session, and the FSM module also extracts the frequent subgraphs from the already discovered m most similar sessions of the query session via item-level attention. Then, TNID module is used to discover the top-K possible next-clicked items using the NSD and FSM module via a target-level attention. Finally, we perform comprehensive experiments on one big dataset, DIGINETICA, to verify the effectiveness of the TANN model, and the results of this experiment clearly illustrate the performance of TANN.

Federated Learning-Based Cross-Enterprise Recommendation With Graph Neural Networks

Recommender systems are technology-driven marketing solutions for businesses that analyze user behavior data. However, collaborative data sharing between enterprises is often prohibited by privacy protection regulations, leading to insufficient data for graph neural networks (GNNs) training. Fortunately, federated learning (FL), a collaborative training framework without exposing source data, can be applied congruently. Nevertheless, most of FL-based GNN model training methods adopt federated averaging, which performs poorly on highly heterogeneous graph data. To solve this problem, a FL-based GNN Model Training framework for cross-enterprise recommendation, named FL-GMT, is proposed. Specifically, a GNN-based recommendation model is deployed as the local training model. Then, considering the performance inequity caused by uneven sample quality, a loss-based federated aggregation algorithm is designed, effectively improving the performance of disadvantaged participants. To improve the system stability at the end of the aggregation, a dynamic update method of loss attention is designed. Extensive experiments on benchmark datasets demonstrate that FL-GMT outperforms baselines in terms of system fairness, stability, and accuracy.

Multi-homed abnormal behavior detection algorithm based on fuzzy particle swarm cluster in user and entity behavior analytics

User and entity behavior analytics (UEBA) is an anomaly detection technique that identifies potential threat events in the enterprise's internal threat analysis and external intrusion detection. One limitation of existing methods in UEBA is that many algorithms use deterministic algorithms only for one category labeling and only compare with other samples within this category. In order to improve the efficiency of potential threat identification, we propose a model to detect multi-homed abnormal behavior based on fuzzy particle swarm clustering. Using the behavior frequency-inverse entities frequency (BF-IEF) technology, the method of measuring the similarity of entity and user behavior is optimized. To improve the iterative speed of the fuzzy clustering algorithm, the particle swarm is introduced into the search process of the category centroid. The entity's nearest neighbor relative anomaly factor (NNRAF) in multiple fuzzy categories is calculated according to the category membership matrix, and it is combined with boxplot to detect outliers. Our model solves the problem that the sample in UEBA is evaluated only in one certain class, and the characteristics of the particle swarm optimization algorithm can avoid clustering results falling into local optimal. The results show that compared with the traditional UEBA approach, the abnormal behavior detection ability of the new method is significantly improved, which can improve the ability of information systems to resist unknown threats in practical applications. In the experiment, the accuracy rate, accuracy rate, recall rate, and F1 score of the new method reach 0.92, 0.96, 0.90, and 0.93 respectively, which is significantly better than the traditional abnormal detections.

A Survey of Artificial Intelligence in Cyber Security

Artificial intelligence (AI) and cyber security are two emerging technologies in the modern world. Machine learning (ML) models serve as the cornerstone of AI. Access control, user authentication, user behaviour analysis, spam, malware, and botnet identification are all areas where AI is crucial. The security issues of today, however, are many. Users now face substantial security threats due to the increasing use of apps like WhatsApp and Viber, social media, mobile devices, cloud computing, and social media. We will explain how artificial intelligence (AI) can be used to handle cyber security concerns and cyber threats in this essay. Since the past decade, the field of cyber security has expanded significantly. Thus, both the number of applications and the number of risks are continuously increasing. Artificial intelligence's applications in cyber security are covered in this essay. With a primary focus on studies between 2018 and 2022, the study technique involved online desk research.