Earticle

Under the new media era, the film and television post-production technology is changing day by day, in order to explore how to utilize the powerful functions of the Unreal Engine for the production of mythological themes in film and television. This paper in-depth study of the specific functions of the unreal engine on the film and television creation of help, analyze the evolution and development of the creation of mythological themes, put forward the problems it faces. Based on the creation needs of unreal engine and mythological works, this paper uses unreal engine to adapt Lu pan from Liaozai to explore its complete production process, and the production results show that unreal engine greatly improves the quality of the screen and the presentation effect, reduces the cost of the film's production, and improves the collaborative ability of the production team and the ability of creativity. However, the production process still requires high hardware equipment and paid plug-ins for Unreal Engine. We provide the establishment of the process for the combination of Unreal Engine movie and television production and mythological theme re-creation, supplements the production details, and provides suggestions for its further improvement.

Mobile edge computing (MEC) plays a crucial role in improving the performance of resource-constrained mobile devices by offloading computation-intensive tasks to nearby edge servers. However, existing methods often neglect the critical consideration of future task requirements when making offloading decisions. In this paper, we propose an innovative approach that addresses this limitation. Our method leverages recurrent neural networks (RNNs) to predict task sizes for future time slots. Incorporating this predictive capability enables more informed offloading decisions that account for upcoming computational demands. We employ genetic algorithms (GAs) to fine-tune fitness functions for current and future time slots to optimize offloading decisions. Our objective is twofold: minimizing total processing time and reducing energy consumption. By considering future task requirements, our approach achieves more efficient resource utilization. We validate our method using a real-world dataset from Google-cluster. Experimental results demonstrate that our proposed approach outperforms baseline methods, highlighting its effectiveness in MEC systems.

Reliable and fine-grained musical metadata are required for efficient search of rapidly increasing music files. In particular, since the primary motive for listening to music is its emotional effect, diversion, and the memories it awakens, emotion classification along with genre classification of music is crucial. In this paper, as an initial approach towards a “ground-truth” dataset for music emotion and genre classification, we elaborately generated a music corpus through labeling of a large number of ordinary people. In order to verify the suitability of the dataset through the classification results, we extracted features according to MPEG-7 audio standard and applied different machine learning models based on statistics and deep neural network to automatically classify the dataset. By using standard hyperparameter setting, we reached an accuracy of 93% for genre classification and 80% for emotion classification, and believe that our dataset can be used as a meaningful comparative dataset in this research field.

As YouTube is rapidly growing as an information platform, we investigated practical impacts of YouTube knowledge content and creator characteristics on viewer satisfaction and purchase intention. In so doing, an empirical survey was conducted among the viewers of <Chekgrim>, one of representative book YouTube channels in Korea. A total of 641 valid samples were analyzed. This study aims to understand the impact of knowledge contents on YouTube, and creator characteristics on viewer satisfaction and purchase intention. Specifically, for the study, content characteristics were divided into three sub-factors: entertainment, information, and interactivity, and the creator characteristics were divided into two sub-factors: intimacy and professionalism. Viewing satisfaction and purchase intention were set as dependent variables. The results of various analyses confirm that creator characteristics have direct and indirect effects on viewers' purchase intentions, and in particular, intimacy has the greatest influence on purchase intentions. This is expected to be a meaningful empirical analysis for future influencer marketing strategies and effective communications between content creators and consumers.

We examined how different types of brand personality play a role to develop a specific consumers’ expectation toward a brand, and how this expectation works in various ways in different types of brand transgressions. Based on expectancy violation theory and brand transgression research, a 2 (brand personality types: sincerity vs. competence) × 2 (brand transgression types: morality-related vs. competence-related transgression) factorial design was employed. Corporate evaluations and purchase intention toward the brand were considered as dependent variables. We found that a brand having a sincerity personality is more vulnerable to a morality-related transgression. However, there is no difference in consumers’ responses by transgression type for a brand with a competence personality. We identified that brand personality types and transgression types can be critical factors to influence consumers’ responses in times of crisis. Theoretical and empirical implications are discussed.

Tourism is a crucial sector in Vietnam, benefiting significantly from the surge in short video content and the rapid growth of TikTok, a popular new social media platform with a large daily user base. This study explores how digital video marketing factors on TikTok, such as perceived enjoyment, credibility, interactivity, and subtitling, affect users' awareness of destinations and their intention to visit. The findings indicate that perceived enjoyment, interactivity, and subtitling positively influence destination awareness, which in turn impacts the visit intention of TikTok users.

We study three sports media start-ups that seek to promote business model innovation (BMI) in which Web 3.0 and metaverse are converged. In results, LM starts from an innovative digital space platform offering a unique combination of virtual real estate, games, and non-fungible tokens (NFTs) which come with real-world earning potential. It creates value by integrating virtual real estate, training academies, blockchain games, and meta shops to offer a unique experience, capture value by offering monetization tools for buying and trading limited edition NFTs of favorite influencers from various sports leagues, offering access to premier real-world events and VIP game contests, and delivers value by building community to play games with favorite athletes or teams including trivia games, allowing fans to engage with their favorite athletes in a unique exclusive way. SL starts from the customizable digital identities especially for young sports fans like generation (gen) Z to play, hang out, and express themselves with their own avatars. SI starts from a leading Web3.0 metaverse innovator creating NFTs with the greatest athletes of all time, allowing athletes and creators to set up a profile and mint NFTs directly onto the blockchain. It tries to have the partnerships with great athletes revolutionizing the sports media industry to connect sports heroes and their super fans through an immersive, artistic, inspirational NFTs and unlockable content creating a sticky community between them.

Aberration is still a problem for making augmented reality displays. The existing methods to solve this problem are either slow and inefficient, consume too much battery, or are too complex for straightforward implementation. There are still some problems with image quality, and users may suffer from eye strain and headaches because the images provided to each eye lack accuracy, causing the brain to receive mismatched cues between the vergence and accommodation of the eyes. In this paper, we implemented a computer simulation of an optical aberration using Zernike polynomials which are defocus, trefoil, coma, and spherical. The research showed that these optical aberrations impact the Point Spread Function (PSF) and Modulation Transfer Function (MTF). We employed the phase conjugate technique to mitigate aberrations. The findings revealed that the most significant impact on the PSF and MTF comes from the influence of spherical aberration and coma aberration.

In recent years, the Guochao style of virtual idols has proliferated, and the virtual idol market in China has witnessed gradual growth. As Guochao combines traditional Chinese culture with modern aesthetics, it shapes a distinctive visual identity for Chinese virtual idols. We address the current research gap by exploring the characteristics of Guochao style in virtual idol design through literature analysis, semiotics, and comparative studies. We examine how Guochao virtual idols represent the convergence of Chinese culture and modern technology, reflecting cultural characteristics of the era. Through our analysis of virtual idol design, we identify key design features of Guochao virtual idols, bridging a theoretical void in this area. We propose recommendations to foster a more dynamic and culturally enriched virtual idol industry in China. Our research provides new insights into integrating Guochao elements into virtual idol design as an approach to differentiate amid competition while promoting traditional Chinese culture through digital media. We demonstrate how this design approach enhances the uniqueness and cultural value of Chinese virtual idols, contributing to the field's theoretical foundation and practical applications.

As digital education progresses, MOOC (Massive Open Online Courses) are increasingly utilized by learners, making research on MOOC learning outcomes a necessary endeavor. In this study, we systematically investigated the impact of audiovisual elements on learning outcomes in MOOC, highlighting the nuanced role these components play in enhancing educational effectiveness. Through a comprehensive survey and rigorous analysis involving descriptive statistics, reliability metrics, and regression techniques, we quantified the influence of text, graphics, color, teacher images, sound effects, background music, and teacher's voice on learner attention, cognitive load, and satisfaction. We discovered that background music and text layout significantly improve engagement and reduce cognitive burden, underscoring their pivotal role in the instructional design of MOOC. We findings contribute new insights to the field of digital education, emphasizing the critical importance of integrating audiovisual elements thoughtfully to foster better learning environments and outcomes. Not only advances academic understanding of multimedia learning impacts but also offers practical guidance for educators and course designers seeking to enhance the efficacy of MOOC.

Recently, case presentations using AI functions such as ChatGPT are increasing in many industrial fields. As AI-based results emerge even in the areas of images and videos, traditional animation production tools are in need of significant changes. Unreal Engine is the tool that adapts most quickly to these changes, proposing a new animation production workflow by integrating tools such as Metahuman and Marvelous Designer. Working with realistic metahumans allows for the production of realistic and natural movements, such as those captured through motion capture data. Implementing this approach presents many challenges for production tools that adhere to traditional methods. In this study, we investigated the differences between the cell animation workflow and the computer graphics animation production workflow. We compared and analyzed whether these differences could be reduced by creating sample movements using character rigs in Maya and Cascadeur tools. Our results showed that a similar cell animation workflow could be constructed using the Cascadeur tool. To improve the accuracy of our conclusions, we created large, action-packed short animations to demonstrate and validate our findings.

Artificial intelligence is crucial to manufacturing productivity. Understanding the difficulties in producing disruptions, especially in linear feed robot systems, is essential for efficient operations. These mechanical tools, essential for linear movements within systems, are prone to damage and degradation, especially in the LM guide, due to repetitive motions. We examine how explainable artificial intelligence (XAI) may diagnose wafer linear robot linear rail clearance and ball screw clearance anomalies. XAI helps diagnose problems and explain anomalies, enriching management and operational strategies. By interpreting the reasons for anomaly detection through visualizations such as Class Activation Maps (CAMs) using technologies like Grad-CAM, FG-CAM, and FFT-CAM, and comparing 1D-CNN with 2D-CNN, we illustrates the potential of XAI in enhancing diagnostic accuracy. The use of datasets from accelerometer and torque sensors in our experiments validates the high accuracy of the proposed method in binary and ternary classifications. This study exemplifies how XAI can elucidate deep learning models trained on industrial signals, offering a practical approach to understanding and applying AI in maintaining the integrity of critical components such as LM guides in linear feed robots.

In modern society, many adults seek emotional solace by reconnecting with their childhood memories through "kidult" culture, especially as single-person households increase. This trend spans fashion, collectibles, movies, animations, games, and character merchandise, with Hollywood playing a significant role in its growth during the 1980s and 1990s. Kidult culture allows adults to relieve stress, foster creativity, and strengthen social connections, enhancing their quality of life. As this culture gains mainstream acceptance, companies are producing diverse products featuring beloved characters, appealing to a wide age range. The rise in single-person households has amplified the importance of personal expression and individuality, driving the popularity of kidult culture. Companies are leveraging this trend to create innovative designs that resonate with consumer preferences. This cultural expansion promotes new design forms and aesthetics, reflecting the evolving relationship between design and consumption. Kidult culture's growth underscores its significance in contemporary consumer and design culture, offering valuable insights into modern societal trends.

Despite numerous air mattresses marketed to prevent Pressure Ulcers (PU), none have fully succeeded due to residual pressure surpassing critical levels. We introduces an innovative medical bed system aiming at complete PU prevention. This system employs a unique 4-bar link mechanism, moving keys up and down to manage body pressure. Each of the 17 keys integrates a sensor controller, reading pressure from 10 sensors. By regulating motor input, we maintain body pressure below critical levels. Keys are equipped with a servo drive and sensor controller, linked to the main controller via two CAN series. Using fuzzy or PI/IP controllers, we adjust keys to minimize total error, dispersing body pressure and ensuring comfort. In case of controller failure, keys alternate swiftly, preventing ulcer development. Through experimental tests under varied conditions, the fuzzy controller with tailored membership functions demonstrated swift performance. PI control showed rapid convergence, while IP control exhibited slower convergence and oscillations near zero error. Our specialized medical robot bed, incorporating 4-bar links and pressure sensors, underwent testing with three controllers—fuzzy, PI, and IP—showcasing their effectiveness in keeping body pressure below critical ulcer levels. Experimental results validate the proposed approach’s efficacy, indicating potential for complete PU prevention.

Virtual world technology is driving major advances in education, entertainment, and professional training. Metaverse and extended reality (XR) technologies maximize immersion to enhance learning, provide global learning environments, and expose students to situations that are difficult to experience in real life. Career exploration is an important developmental task in adolescence, and virtual training maximizes learning by providing life-like experiences with imagery training. Virtual training overcomes spatial, financial, performance, and situational constraints and is effective in a variety of fields, including military and disaster training. It provides customized learning for various users such as youth, job seekers, and people with disabilities, deepening their understanding of professional activities and improving their problem-solving skills. It also improves the quality of learning through repetitive learning and contributes to the improvement of teamwork and communication skills, and helps to solve financial problems by using unlimited internal resources and space in virtual space, and enables people with disabilities to perform in various professions. This paper investigated the value of virtual training as a comprehensive educational tool through an economical and efficient learning experience.

The history of animals raised by humans began in prehistoric times, and in modern times they were classified as livestock and pets. As social awareness changes, the term 'companion animal' is used instead of 'pet', and related content has also become more diverse. Recently, digital contents such as virtual pet training, memorial space, and AI health diagnosis using metaverse and AI technology are developing. Developed digital content makes pet care convenient and provide emotional support and economic benefits to users. As technology develops and content becomes more diverse, the relationship between pets and humans will become closer in the future, and related laws and ethical guidelines will need to be established.

In producing anamorphic 3D advertisement projects, it is necessary to apply the principles of illusion art to distort the images output to the screen (Image Distortion) so that their display aligns with our visual perception in a real three-dimensional environment. We focuse on the methods of image distortion in the creation of content for anamorphic 3D advertisement screens in this thesis. We propose using Unity 3D's real-time rendering instead of the offline rendering method of compositing method, and employing UV grid mapping to replace the manual correction in Adobe After Effects(AE). The significance of this paper lies in simplifying the image distortion processing workflow in anamorphic 3D projects and optimizing the image distortion creation methods used in compositing method. In outdoor anamorphic 3D advertisement projects, the proposed image distortion creation method demonstrates significant advantages in terms of production time, process simplification, flexibility, and expansion possibilities. Our research provides new perspectives and methods for the creation of anamorphic 3D content, offering theoretical and methodological references for professionals working on similar contents.

The focus of this paper is secure code development and maintenance. When it comes to safe code, it is most important to consider code readability and maintainability. This is because complex code has a code smell, that is, a structural problem that complicates code understanding and modification. In this paper, the goal is to improve code quality by detecting and removing smells existing in code. We target the encryption and decryption code SEED.c and evaluate the quality level of the code using several metrics such as lines of code (LOC), number of methods (NOM), number of attributes (NOA), cyclo, and maximum nesting level. We improved the quality of SEED.c through systematic detection and refactoring of code smells. Studies have shown that refactoring processes such as splitting long methods, modularizing large classes, reducing redundant code, and simplifying long parameter lists improve code quality. Through this study, we found that encryption code requires refactoring measures to maintain code security.

This paper investigates the application of multi-agent deep reinforcement learning in the fighting game Samurai Shodown using Proximal Policy Optimization (PPO) and Advantage Actor-Critic (A2C) algorithms. Initially, agents are trained separately for 200,000 timesteps using Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) with LSTM networks. PPO demonstrates superior performance early on with stable policy updates, while A2C shows better adaptation and higher rewards over extended training periods, culminating in A2C outperforming PPO after 1,000,000 timesteps. These findings highlight PPO's effectiveness for short-term training and A2C's advantages in long-term learning scenarios, emphasizing the importance of algorithm selection based on training duration and task complexity. The code can be found in this link https://github.com/Lexer04/Samurai-Shodown-with-Reinforcement-Learning-PPO.

This study aims to explore the issue of character consistency in AI-generated artwork. First, the concept of character consistency is explained, including the consistency of appearance, actions, and lighting, and its importance in continuous creation and storytelling is analyzed. Next, the study examines current mainstream AI drawing tools such as MidJourney and Stable Diffusion-based WebUI and ComfyUI, evaluating their strengths and limitations in maintaining character consistency. Finally, methods to improve AI drawing technology were proposed to enhance character consistency, aiming to achieve a higher level of consistency in AI art creation.

Effective warehouse management requires advanced resource planning to optimize profits and space. Robots offer a promising solution, but their effectiveness relies on embedded artificial intelligence. Multi-agent reinforcement learning (MARL) enhances robot intelligence in these environments. This study explores various MARL algorithms using the Multi-Robot Warehouse Environment (RWARE) to determine their suitability for warehouse resource planning. Our findings show that cooperative MARL is essential for effective warehouse management. IA2C outperforms MAA2C and VDA2C on smaller maps, while VDA2C excels on larger maps. IA2C’s decentralized approach, focusing on cooperation over collaboration, allows for higher reward collection in smaller environments. However, as map size increases, reward collection decreases due to the need for extensive exploration. This study highlights the importance of selecting the appropriate MARL algorithm based on the specific warehouse environment's requirements and scale.

A recently the advancement of society, AI technology has made significant strides, especially in the fields of computer vision and voice recognition. This study introduces a system that leverages these technologies to recognize users through a camera and relay commands within a vehicle based on voice commands. The system uses the YOLO (You Only Look Once) machine learning algorithm, widely used for object and entity recognition, to identify specific users. For voice command recognition, a machine learning model based on spectrogram voice analysis is employed to identify specific commands. This design aims to enhance security and convenience by preventing unauthorized access to vehicles and IoT devices by anyone other than registered users. We converts camera input data into YOLO system inputs to determine if it is a person, Additionally, it collects voice data through a microphone embedded in the device or computer, converting it into time-domain spectrogram data to be used as input for the voice recognition machine learning system. The input camera image data and voice data undergo inference tasks through pre-trained models, enabling the recognition of simple commands within a limited space based on the inference results. This study demonstrates the feasibility of constructing a device management system within a confined space that enhances security and user convenience through a simple real-time system model. Finally our work aims to provide practical solutions in various application fields, such as smart homes and autonomous vehicles.

In autonomous navigation systems, the need for fast and accurate image processing using deep learning and advanced sensor technologies is paramount. These systems rely heavily on the ability to process and interpret visual data swiftly and precisely to ensure safe and efficient navigation. Despite the critical importance of such capabilities, there has been a noticeable lack of research specifically focused on ship image classification for maritime applications. This gap highlights the necessity for more in-depth studies in this domain. In this paper, we aim to address this gap by presenting a comprehensive comparative study of ship image classification using two distinct neural network models: the Feedforward Neural Network (FNN) and the Convolutional Neural Network (CNN). Our study involves the application of both models to the task of classifying ship images, utilizing a dataset specifically prepared for this purpose. Through our analysis, we found that the Convolutional Neural Network demonstrates significantly more effective performance in accurately classifying ship images compared to the Feedforward Neural Network. The findings from this research are significant as they can contribute to the advancement of core source technologies for maritime autonomous navigation systems. By leveraging the superior image classification capabilities of convolutional neural networks, we can enhance the accuracy and reliability of these systems. This improvement is crucial for the development of more efficient and safer autonomous maritime operations, ultimately contributing to the broader field of autonomous transportation technology.

Battery use is increasing worldwide to achieve carbon neutrality and improve energy efficiency, but batteries are a finite resource and their application is determined by capacity and specifications. Battery performance deteriorates as the number of uses increases. A certain level of battery performance degradation has become an issue in the field of reuse and recycling, and various studies are being conducted on reuse to solve power shortages. Waste batteries from electric vehicles are suitable for building ESS based on reusable batteries, and for stable use, technical skills are needed to accurately predict battery life and determine status information. Predicting battery life and determining status information are difficult due to non-linearity due to internal structure or chemical changes. In this paper, we manufactured a modular internal resistance measuring device and compared the measured values with Hioki equipment to minimize the error rate through a correction method. As a result of testing Hioki equipment and modular measuring instruments to ensure efficiency and safety based on reusable batteries, an accuracy of over 95% was confirmed.

Due to the recent emphasis on carbon neutrality and environmental regulations, the global electric vehicle (EV) market is experiencing rapid growth. This surge has raised concerns about the recycling and disposal methods for EV batteries. Unlike traditional internal combustion engine vehicles, EVs require unique and safe methods for the recovery and disposal of their batteries. In this process, predicting the lifespan of the battery is essential. Impedance and State of Charge (SOC) analysis are commonly used methods for this purpose. However, predicting the lifespan of batteries with complex chemical characteristics through electrical measurements presents significant challenges. To enhance the accuracy and precision of existing measurement methods, this paper proposes using a Long Short-Term Memory (LSTM) model, a type of deep learning-based recurrent neural network, to diagnose battery performance. The goal is to achieve safe classification through this model. The designed structure was evaluated, yielding results with a Mean Absolute Error (MAE) of 0.8451, a Root Mean Square Error (RMSE) of 1.3448, and an accuracy of 0.984, demonstrating excellent performance.

This study introduces a prototype for a virtual zoo initiative, aimed at optimizing resource utilization and minimizing animal displacement from their natural habitats. The prototype features a thoughtfully developed three-dimensional representation of an emperor penguin, with animations designed to emulate real-life behaviors. An investigation into file format distinctions for scientific research, encompassing Wavefront(OBJ), Collada(DAE), and Filmbox(FBX) formats, was conducted. The research utilized the Hololens 2 device for visualization, Unity for environment development, Blender for modeling, and C# for programming, with deployment facilitated through Visual Studio 2019 and the Mixed Reality Toolkit. Empirical examination revealed the OBJ format's suitability for simple geometric shapes, while DAE and FBX formats were preferred for intricate models and animations. DAE files offer detailed preservation of object structure and animations albeit with larger file sizes, whereas FBX files provide compactness but may face scalability constraints due to extensive data integration. This investigation underscores the potential of virtual zoos for conservation and education, advocating for further exploration and context-specific implementation.

The role of the library is as a public institution that provides academic information to a variety of people, including students, the general public, and researchers. These days, as the importance of lifelong education is emphasized, libraries are evolving beyond simply storing and lending materials to complex cultural spaces that share knowledge and information through various educational programs and cultural events. One of the problems library user’s faces is locating books to borrow. This problem occurs because of errors in the location of borrowed books due to delays in updating library databases related to borrowed books, incorrect labeling, and books temporarily located in different locations. The biggest problem is that it takes a long time for users to search for the books they want to borrow. In this paper, we propose a system that visually displays the location of books in real time using an AI vision sensor and LED. The AI vision sensor-based book location guidance system generates a QR code containing the call number of the borrowed book. When the AI vision sensor recognizes this QR code, the exact location of the book is visually displayed through LED to guide users to find it easily. We believe that the AI vision sensor-based book location guidance system dramatically improves book search and management efficiency, and this technology is expected to have great potential for use not only in libraries and bookstores but also in a variety of other fields.

We provide a detailed analysis of the data processing and model training process for vulnerability classification using Transformer-based language models, especially sentence text-to-text transformers (ST5)-XXL and XLNet. The main purpose of this study is to compare the performance of the two models, identify the strengths and weaknesses of each, and determine the optimal learning rate to increase the efficiency and stability of model training. We performed data preprocessing, constructed and trained models, and evaluated performance based on data sets with various characteristics. We confirmed that the XLNet model showed excellent performance at learning rates of 1e-05 and 1e-04 and had a significantly lower loss value than the ST5-XXL model. This indicates that XLNet is more efficient for learning. Additionally, we confirmed in our study that learning rate has a significant impact on model performance. The results of the study highlight the usefulness of ST5-XXL and XLNet models in the task of classifying security vulnerabilities and highlight the importance of setting an appropriate learning rate. Future research should include more comprehensive analyzes using diverse data sets and additional models.

The smart factory promotion project is a project that improves the entire management environment system, including the production process, using ICT technology. According to the 2019 Smart Factory Survey and Analysis Research Report of the Ministry of SMEs and Startups, small and medium-sized enterprises that introduced smart factories reported positive effects such as increased productivity, improved quality, and reduced costs on average. On the other hand, the survey results of companies that promoted the project despite positive results showed that there was room for improvement. This study dealt with the contents of the survey conducted on companies by the smart factory promotion agency in 2020 regarding the infrastructure configuration for promoting smart factories. We examined the meaningful contents implied by the data related to the infrastructure configuration. These meaningful survey results can lead to more efficient business promotion in the future when promoting smart factory projects.

Online consumer reviews have become the most important basis for online shopping and product sales. Fake reviews are generated to boost sales because online consumer reviews play a vital role in consumers’ decision making. The prevalence of fake reviews violates the regulations of the online business environment and misleads consumers in decision making. Thus, the present research investigates the effects of reviews’ linguistic characteristics (i.e., analytical thinking, authenticity) on review fakeness. Specifically, this research examines whether (1) the level of analytical thinking is lower for fake (vs. genuine) reviews (hypothesis 1) and (2) the level of authenticity is lower for fake (vs. genuine) reviews (hypothesis 2). This research analyzed usergenerated hotel reviews (genuine reviews, fake reviews) collected from MTurk. Linguistic Inquiry and Word Count (LIWC) 2022 was adopted to code review contents, and the hypotheses were tested using logistic regression. Consistent with the hypotheses 1 and 2, the results indicate that (1) analyticial thinking is negatively associated with review fakeness; and (2) authenticity is negatively associated with review fakeness. The findings provide important implications to identify fake reviews based on linguistic characteristics.