Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chang-Yi Kao has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Persuasion by an AI-Generated Presenter: Perceived Credibility, Message Quality, Engagement, Realism, and Positive eWOM Intention

    by Chang-Yi Kao

    The rapid development of generative artificial intelligence has enabled brands to create AI-generated influencers capable of producing lifelike videos, product endorsements, and interactive content...

  • Distributional Auditing of Two Large-Language-Model-Augmented Security Pipelines: A Descriptive Enterprise Case Study

    by Chang-Yi Kao

    Large language models (LLMs) are increasingly integrated into zero-trust security pipelines, but their deployment-specific label distributions remain insufficiently examined. This study develops a distributional auditing approach and applies it to two operational pipelines in a financial-sector enterprise: on-premise Mistral-7B Instruct with 5-bit quantisation and GPT-4o through Azure OpenAI. The pipelines processed disjoint, non-random subsets of Windows Active Directory security events, comprising 22,000 and 146,816 successfully parsed events, respectively. The local pipeline assigned 97.4% of events to Medium, whereas the cloud pipeline assigned 87.97% to High. Cohen’s κ was 0.257 locally and 0.287 in the cloud, with raw agreement of 86.4% and 66.4%, respectively. A seven-component descriptive vector combines output-label prevalence, conditional escalation and buffering indices, and ordinal 1-Wasserstein distance; its two-dimensional projection visualises the observed medium-buffering and high-escalation profiles. These case names describe observed patterns rather than threshold-based classifications. The study contributes an interpretable audit representation and a procedure for inspecting how operational pipelines transform upstream security labels without external ground truth. Important limitations constrain interpretation: only 49% of the pre-processed corpus reached inference, scheduling independence could not be verified, rule-baseline prevalence differed substantially between subsets, and inference configurations were confounded with deployment. Because prompts included rule-layer information, agreement measures represent upstream-to-downstream transition consistency rather than independent classifier agreement. The findings therefore describe the analysed subsets and support neither model-specific causal claims nor generalisation to the enterprise event stream. TrustScore results remain exploratory and non-reproducible. Matched-event replication is required before assessing operational benefit or attributing differences to model identity.

  • Open Access

    Evaluating User Experience of a Retrieval-Augmented Generation-Based Customer Service Chatbot

    by Syuan-Yu Chen, Chang-Yi Kao

    As digital services become increasingly widespread, online real-time customer support has become a key way for consumers to seek help. A good service experience can boost customer satisfaction and loyalty, particularly in the financial sector. However, traditional

  • An exploratory study of fake Chinese reviews: detection and analysis of non-reviews

    by Chang-Yi Kao, Zong-Jin Chen

    Purpose: This study explores the influence of fake reviews, with a specific focus on non-reviews, on consumer decision-making and the credibility of e-commerce platforms. Utilizing advanced natural language processing (NLP) and machine learning techniques, the research develops a detection model designed to identify and filter irrelevant reviews, thereby strengthening the reliability of online review systems and fostering consumer trust.Design/methodology/approach: This study employs heterogeneous review corpora to implement NLP and machine learning techniques, including text feature analysis, corpus construction and classification models. Data were collected from Google business reviews via web scraping. The methodology encompasses data preprocessing, feature extraction and model training using support vector machine (SVM), Logistic Regression and Naive Bayes classifier, with performance evaluated through confusion matrices and F1 scores.Findings: The study confirms that the proposed model effectively identifies non-reviews among fake reviews with a high degree of accuracy. Experimental results reveal that the Naive Bayes classifier achieves an F1 score as high as 0.997, with exceptional performance in hotel reviews. Moreover, the findings highlight the superiority of the bag-of-words model in capturing intricate review details and effectively detecting fake reviews. By defining opinion sentences and emphasizing detailed feature extraction, the study significantly improves detection accuracy and model robustness across diverse review types.Originality/value: This research enhances fake review detection by focusing on non-reviews and using detailed feature extraction methods. Innovative NLP and machine learning techniques, such as opinion sentence and term frequency analysis, improve the identification of fake reviews. This study advances the technology for distinguishing genuine reviews and contributes to the healthy development of e-commerce. The findings are expected to improve the online shopping experience and business decision-making, benefiting both consumers and merchants.

  • Open Access

    Smart City Aquaculture: AI-Driven Fry Sorting and Identification Model

    by Chang-Yi Kao, I-Chih Chen

    The development of smart agriculture has become a critical issue for the future of smart cities, with large-scale management of aquaculture posing numerous challenges. Particularly in the fish farming industry, producing single-sex fingerlings (especially male fingerlings) is crucial for enhancing rearing efficiency and could even provide key support in addressing future global food demands. However, traditional methods of manually selecting the gender of broodfish rely heavily on experienced technicians, are labor-intensive and time-consuming, and present significant bottlenecks in improving production efficiency, thus limiting the capacity and sustainable development potential of fish farms. In response to this situation, this study has developed an intelligent identification system based on the You Only Look Once (YOLO) artificial intelligence (AI) model, specifically designed for analyzing secondary sexual characteristics and gender screening in farmed fish. Through this system, farmers can quickly photograph the fish’s cloaca using a mobile phone, and AI technology is then used to perform real-time gender identification. The study involved two phases of training with different sample sets: in the first phase, the AI model was trained on a single batch of images with varying parameter conditions. In the second phase, additional sample data were introduced to improve generalization. The results of the study show that the system achieved an identification accuracy of over 95% even in complex farming environments, significantly reducing the labor costs and physical strain associated with traditional screening operations and greatly improving the production efficiency of breeding facilities. This research not only has the potential to overcome existing technological bottlenecks but also may become an essential tool for smart aquaculture. As the system continues to be refined, it is expected to be applicable across the entire life cycle management of fish, including gender screening during the growth phase, thereby enabling a more efficient production and management model. This not only provides an opportunity for technological upgrades in the aquaculture industry but also promotes the sustainable development of aquaculture. The smart aquaculture solution proposed in this study demonstrates the immense potential of applying AI technology to the aquaculture industry and offers strong support for global food security and the construction of smart cities.


  • Investigating the impact of fear of missing out on inaction inertia in live streaming purchase intention

    by Chang-Yi Kao, Ching Huang

    Purpose: The main purpose of the study is to investigate the influence of live streaming participation on purchase intention, specifically focusing on how fear of missing out (FOMO) impacts live streaming purchase intention and its subsequent effect on inaction inertia. Additionally, the study aims to ex-amine the indirect influence of FOMO on the relationship between live streaming participation and purchase intention. Design/methodology/approach: The research employs SEM to assess the properties of measures. The investigation consists of four main constructs: live streaming shopping participation, fear of missing out, live streaming purchase intention, and inaction inertia. Live streaming shopping participation is further divided into two dimensions: live streaming immersion and live streaming social presence, with the latter encompassing social presence and telepresence. Findings: The study reveals the significant role of FOMO in livestream shopping. Viewers' fear of missing out on information and products presented in livestreams results in heightened attention to these streams and an elevated willingness to purchase. This finding emphasizes the impact of FOMO emotions in driving consumer action and purchasing intent, particularly in situations of product scarcity. Originality/value: The study uniquely explores FOMO as a factor disrupting consumer inertia, influencing decisive purchasing. It shows that FOMO enhances perceived value of products, altering consumer behavior in live streaming and e-commerce, thus providing a novel perspective on FOMO’s extended impact.


  • Open Access

    Enhancing Energy Efficiency in Retail within Smart Cities through Demand-Side Management Models

    by Ching-Bang Yao, Chang-Yi Kao

    The energy discourse is multifaceted, encompassing energy creation, storage, and conservation. Beyond the imperative of conserving energy consumption, effective energy management is a critical aspect of achieving overall energy efficiency. Despite being traditionally regarded as low electricity consumers, retailers play a pivotal role in economic activity. While categorized as non-productive energy users, the retail industry operates numerous establishments, facing substantial energy costs that make energy management integral to its operations. Historically, smaller retail stores have lacked awareness of energy saving. However, by connecting these stores, even modest reductions in individual electricity consumption can yield significant overall energy savings. This study aims to investigate the feasibility of implementing the demand-side management (DSM) aggregator model in the retail industry. Through surveys on awareness of energy saving and the application of deep learning techniques to analyze the effectiveness of the Aggregator model, the results reveal that the mean squared prediction error (MSPE) of this research is below 2.05%. This indicates substantial accuracy and offers meaningful reference value for Energy Service Company (ESCO) providers. The findings contribute practical recommendations for the sustainable and competitive implementation of DSM energy management practices in smart cities.


  • Open Access

    Drone for Dynamic Monitoring and Tracking with Intelligent Image Analysis

    by Ching-Bang Yao, Chang-Yi Kao, Jiong-Ting Lin

    Traditional monitoring systems that are used in shopping malls or community management, mostly use a remote control to monitor and track specific objects; therefore, it is often impossible to effectively monitor the entire environment. When finding a suspicious person, the tracked object cannot be locked in time for tracking. This research replaces the traditional fixed-point monitor with the intelligent drone and combines the image processing technology and automatic judgment for the movements of the monitored person. This intelligent system can effectively improve the shortcomings of low efficiency and high cost of the traditional monitor system. In this article, we proposed a TIMT (The Intelligent Monitoring and Tracking) algorithm which can make the drone have smart surveillance and tracking capabilities. It combined with Artificial Intelligent (AI) face recognition technology and the OpenPose which is able to monitor the physical movements of multiple people in real time to analyze the meaning of human body movements and to track the monitored intelligently through the remote control interface of the drone. This system is highly agile and could be adjusted immediately to any angle and screen that we monitor. Therefore, the system could find abnormal conditions immediately and track and monitor them automatically. That is the system can immediately detect when someone invades the home or community, and the drone can automatically track the intruder to achieve that the two significant shortcomings of the traditional monitor will be improved. Experimental results show that the intelligent monitoring and tracking drone system has an excellent performance, which not only dramatically reduces the number of monitors and the required equipment but also achieves perfect monitoring and tracking.


  • Open Access

    A Real-Time Bidding Gamification Service of Retailer Digital Transformation

    by Chang-Yi Kao, Hao-En Chueh

    Real-time bidding (RTB), which holds bids for advertisers to choose when and where to display their advertisements with desired budgets, is one way to improve effectiveness. We proposed supply side platform (SSP) and demand side platform (DSP) to integrate supplier side and demand side as solution. The proposed method combines two digital technology service, gamified RTB and mobile location-based analysis (LBA). In order to make target customers make interactions actively with the advertisement contents, the idea of gamification is employed to increase customer participation. By the coupons in the gamifying RTB App, it have increased the coupon usage rate of 16.7% and 11.6% in the restaurant and apparel industries. It is a successfully digital transformation marketing service for retail industries. The gamified RTB plays an important role in making old business circles accept new technologies for the renewal of promotion strategies and help find the business directions in the future.