Jonghyuk Kim

Abusive news refers to digital content designed to maximize clicks and advertising revenue through sensational headlines, repetitive postings, or emotionally charged language, rather than upholding journalistic integrity. Despite growing concerns about its impact on media credibility and public trust, existing detection approaches lack systematic categorization and type-specific methodologies. This study addresses this gap by proposing a six-type typology of abusive news—content recycling, keyword insertion, title–body inconsistency, commercial promotion, emotionally stimulating headline, and automatically generated types—based on five analytical dimensions: content structure, authenticity, algorithmic manipulability, sensationalism, and information-ecosystem impact. We developed type-specific detection pipelines combining BERT-based embeddings, TF-IDF features, and rule-based indicators and evaluated them using a large-scale Korean clickbait corpus. Results demonstrate that BERT achieves higher F1-scores (0.89) for automatically generated content, while TF-IDF with SVM provides more stable precision (0.60) for emotionally charged articles under class imbalance. Cross-domain experiments confirm that models trained on diverse, balanced topic sets generalize better than volume-focused models, with diversity improving F1-scores by up to 0.07. BERT models show higher false positive rates on repetitive legitimate content compared to TF-IDF approaches, highlighting the importance of type-adaptive architectures and diversity-aware data design in abusive news detection systems.

Optimizing ambulance deployment is a critical task in emergency medical services (EMS), as it directly affects patient outcomes and system efficiency. This study proposes a cyber-secure, machine learning-based framework for predicting region-specific ambulance allocation and response times across South Korea. The model integrates heterogeneous datasets—including demographic profiles, transportation indices, medical infrastructure, and dispatch records from 229 EMS centers—and incorporates real-time IoT streams such as traffic flow and geolocation data to enhance temporal responsiveness. Supervised regression algorithms—Random Forest, XGBoost, and LightGBM—were trained on 2061 center-month observations. Among these, Random Forest achieved the best balance of accuracy and interpretability (MSE = 0.05, RMSE = 0.224). Feature importance analysis revealed that monthly patient transfers, dispatch variability, and high-acuity case frequencies were the most influential predictors, underscoring the temporal and contextual complexity of EMS demand. To support policy decisions, a Lasso-based simulation tool was developed, enabling dynamic scenario testing for optimal ambulance counts and dispatch time estimates. The model also incorporates the coefficient of variation (CV) of workload intensity as a performance metric to guide long-term capacity planning and equity assessment. All components operate within a cyber-secure architecture that ensures end-to-end encryption of sensitive EMS and IoT data, maintaining compliance with privacy regulations such as GDPR and HIPAA. By integrating predictive analytics, real-time data, and operational simulation within a secure framework, this study offers a scalable and resilient solution for data-driven EMS resource planning.

Modern buildings are large and complex, and as more time is spent inside them, the risk of indoor disasters such as fires and gas leaks increases. In the event of such a disaster, the success of the rescue operation depends on the ability of the rescue team to navigate and respond to the complex environment. To address this challenge, we designed a mixed reality (MR)-based system simulating indoor disaster rescue. This system uses augmented indoor maps and MR technology to help rescue teams quickly, and effectively respond to unexpected environmental variables and carry out rescue activities. To test the effectiveness of the system, we created a virtual disaster scenario and evaluated the rescue and escape performance within a shortened “golden time” of 2 min, as opposed to 5 min, given the virtual characteristics of the simulation. The results showed that the system is particularly effective at increasing the speed of rescue activities. Additionally, our results indicated the potential for further improvement through additional research. By applying this system for disaster rescue simulations and training, the safety of firefighters and rescuers can be improved by reducing the risk of injury during rescue operations.

Owing to the recent increase in mobile banking customers, studies exploring self-service channels and customer responses as distribution channels in the retail banking industry are also rapidly expanding. Moreover, with the emergence of big data and a series of artificial intelligence (AI) technologies, customer pattern analysis using deep learning, insurance fraud prevention, software development and various types of blockchain-based FinTech technologies, offline banks are disappearing. Accordingly, many commercial banks are attempting to find technological alternatives. However, maintaining a profitable bank branch is a crucial factor in the relationship between service quality and customer satisfaction because excellent service quality prevents existing customers from leaving. This study sought to quantitatively prove the change in customer service quality and profit due to the introduction of technology in the financial industry. We microscopically compared the effects between bank branch closures and changes in net profit using a time-series analysis. Specifically, we quantitatively analyzed actual customer attrition behavior with a time-series analysis across the three quarters before and after the closure of 88 branches of major commercial banks in South Korea in the Seoul metropolitan area and nearby cities. The findings prove that branch closures and multi-channel effects in the financial sector are gradually being resolved through immediate technology acceptance, contrary to popular concern.

This study aims to investigate how humans and artificial intelligence (AI) speakers interact and to examine the interactions based on three types of communication failures: system, semantic, and effectiveness. We divided service failures using AI speaker user data provided by the top telecommunication service providers in South Korea and investigated the means to increase the continuity of product use for each type. We proved the occurrence of failure due to system error (H1) and negative results on sustainable use of the AI speaker due to not understanding the meaning (H2). It was observed that the number of users increases as the effectiveness failure rate increases. For single-person households constituted by persons in their 30s and 70s or older, the continued use of AI speakers was significant. We found that it alleviated loneliness and that human-machine interaction using AI speaker could reach a high level through a high degree of meaning transfer. We also expect AI speakers to play a positive role in single-person households, especially in cases of the elderly, which has become a tough challenge in the recent times.

This study explores changes in a set of brand considerations as a result of web search strategies. Survey and personal computer log data of car buyers were used to identify online information search behavior for brands and products. Through this study, we found that higher frequencies of brand searching are associated with how much consumer-initiated sites and third-party-initiated sites are used, while lower frequencies of brand searching are only related to how much brand-initiated websites are used. We also concluded that ambivalent messages on consumer-initiated sites lead to the postponement of a decision and a continued search for another brand. In addition, third party-initiated information sources lower search costs, which lead to longer consumer journeys and expand the set of brands considered and searched. The results of this study can help marketers understand the importance of their own media and aid in the development of a digital media strategy.

This study indirectly verifies the possibility of telemedicine for humans through a mobile application (app) targeting pets. It examined the perception of telemedicine services and the current status of the companion animal industry, the app platform, and its applied technology by industry domain, and four representative types of artificial intelligence (AI) technologies applicable in the medical field. A survey was conducted through an app implementing pet telemedicine, and hypotheses were established and statistically tested based on the adoption period of pets, health status, mobile service utilization (as an index measuring the ease of use of recent AI functions), and positive and negative perceptions of telemedicine services. As revealed by prospect theory, users with a negative perception of pet telemedicine tended to maintain negative perceptions about telemedicine for humans. This study proved that the severity of pet diseases and the ease of use of recent AI technologies act as a moderating effect on the perception of telemedicine services through the verification of reinforcement and additional hypotheses. It suggests a plan to overcome sanctions against telemedicine by utilizing AI technology. A positive effect on changing the medical paradigm to telemedicine and the improvement of the medical legal system were also observed.

This study examines technology effectiveness for industry demand in which artificial intelligence (AI) is applied in the financial sector. It summarizes prior studies on chatbot and customer service and investigates theories on acceptance attitudes for innovative technologies. By setting variables, the study examines bank revenue methodologically and assesses the impact of customer service and chatbot on bank revenues through customer age classification. The results indicate that new product-oriented funds or housing subscription savings are more suitable for purchase through customer service than through chatbot. However, services for existing products through chatbot positively affect banks’ net income. When classified by age, purchases by the majority age group in the channel positively affect bank profits. Finally, there is a tendency to process small banking transactions through the chatbot system, which saves transaction and management costs, positively affecting profits. Through empirical analysis, we first examine the effect of an AI-based chatbot system implemented to strengthen financial soundness and suggest policy alternatives. Second, we use banking data to increase the study’s real-life applicability and prove that problems in customer service can be solved through a chatbot system. Finally, we investigate how resistance to technology can be reduced and efficiently accommodated.

Seoul Metropolitan City’s buses cater to more than 50% of the average daily public transportation use, and they are the most important transportation mode in Korea, together with the subway. Since 2004, all public transportation records of passengers have been stored in Seoul, using smart transportation cards. This study explores the environmental and psychological factors in implementing a smart transportation system. We analyze the switching behavior of traffic users according to traffic congestion time and number of transfers based on public transportation data and show that bus-use behavior differs according to the traffic information of users and the degree of traffic congestion. Information-based switching behavior of people living near bus stops induces people to change routes during traffic congestion. However, in non-congested situations, the original routes are used. These results can guide the formulation of policy measures on bus routes. We made it possible to continuously change the routes for certain buses, which were temporarily implemented due to traffic congestion. Moreover, we added a service that posts the estimated arrival time to major stops while reflecting real-time traffic conditions in addition to the bus location and arrival time information through the global positioning system.

The application of smart city technologies requires new data analysis methods to interpret the voluminous data collected. In this study, we first analyzed the transfer behavior of subway pedestrians using the fingerprinting technique using data collected by more than 100 MAC (Media Access Control) ID sensors installed in a congested subway station serving two subway lines. We then developed a model that employs an AI (Artificial Intelligence)-based methodology, the cumulative visibility of moving objects (CVMO), to present the data in such a manner that it could be used to address pedestrian flow issues in this real-world implementation of smart city technology. The MAC ID location data collected during a three-month monitoring period were mapped using the fingerprinting wireless location sensing method to display the congestion situation in real time. Furthermore we developed a model that can inform immediate response to identified conditions. In addition, we formulated several schemes for disbursing congestion and improving pedestrian flow using behavioral economics, and then confirmed their effectiveness in a follow-up monitoring period. The proposed pedestrian flow analysis method cannot only solve pedestrian congestion, but can also help to prevent accidents and maintain public order.