INTERNATIONAL JOURNAL OF CONTENTS, The Korea Contents Association

PDF Citaion CNN based Estimating Patent Quality: Focusing on AI Convergences

Won Sang Lee pp.1-10

초록보기

Abstract

Recently, obtaining high quality patents has become increasingly important for the pursuit of technological convergence. However, it is insufficient for effectively estimating patent quality, especially in the emerging convergent technology. This research newly proposed a technique to evaluate patents, focusing on AI convergences, by considering both bibliometric aspects and embedded citations of patents with Convolutional Neural Network. Findings of this research empirically contribute to the estimation of patent quality. The proposed technique is expected to discover patents with high quality. Related policy implications based on this research could leverage R&D management in AI area.

PDF Citaion Exploring the Determinants of Satisfaction and Continuous Intention to Use TVing

Soo Jin Lee ; Sun Kyong Lee pp.11-22

초록보기

Abstract

Several factors, including personalization, content diversity, user interface, and cost, wield influence over consumer satisfaction and their enduring commitment to using a platform. This research, centered on TVing, a South Korean Over-the-Top service (also known as streaming service, OTT), aims to unearth the factors that can bolster user satisfaction and mitigate subscriber churn. The study's findings underscore the significant role of personalization and cost in shaping users' expectation confirmation. Moreover, perceived usefulness emerges as a multifaceted construct influenced by all four factors: personalization, content diversity, user interface, and cost. Crucially, the research reveals the interconnectedness of these variables. Expectation confirmation and perceived usefulness are all intrinsically linked to user satisfaction. Higher satisfaction, in turn, yields a greater likelihood of users harboring a continuous intention to utilize the service in the long term. These insights shed light on the complex dynamics governing user interactions with OTT service platforms and offer valuable guidance to service providers like TVing. By understanding and leveraging these factors, platforms can fine-tune their offerings, enhance user experiences, and bolster user retention in a competitive and ever-evolving landscape.

PDF Citaion Qualitative Comparison between TikTok and YouTube

Jiye Jung ; Sang-Ho Yoon ; Dinara Kengesbay ; Sun Kyong Lee pp.23-36

초록보기

Abstract

This study compared TikTok and YouTube users' perceptions and experiences of the two video-sharing platforms (VSPs). A thematic analysis of 351 survey responses revealed six key themes. TikTok's short videos and algorithm-driven scrolling were distinct features. TikTok was primarily used for entertainment, while YouTube served practical purposes, such as tutorials and music. YouTube featured longer videos, often used as background noise during other activities. Content length and platform algorithms influenced users' attention and satisfaction. Younger users, especially Generation Z, were drawn to TikTok's short, algorithm-curated content. YouTube attracted users with longer videos and individual searches. These findings offer theoretical and practical insights into gratification niches, competition, and the coexistence of TikTok and YouTube.

PDF Citaion Efficient Sensor-Based Environmental Monitoring for Stored Missiles: Data-Driven Adaptive Sampling for Battery Optimization

Yunhee Choi ; Hyunwoo Kim ; Kwangho Yoo ; Younho Lee ; Sojung Kim pp.37-45

초록보기

Abstract

The need for condition-based maintenance and sustainability management of military assets has become increasingly important due to reductions in military personnel and budget constraints. In this context, research is actively being conducted using sensors that collect environmental data to determine optimal inspection intervals and identify vulnerabilities early. This study proposes an algorithm to dynamically adjust the sampling interval based on the rate of change in measured physical quantities to reduce sensor battery consumption. Various environmental sensing data, such as temperature, humidity, acceleration, and pressure, were collected from a simulation device that mimicked the storage environment of actual guided missiles. The analysis of the collected data revealed that setting the RSME threshold within 5 improved battery lifespans by 11% compared to the original data, while demonstrating that the temperature RMSE was estimated to improve by about 4.76 in adaptive sampling and 5.44 in uniform sampling. This demonstrates that our approach may improve maintenance efficiency by monitoring military assets more effectively and for extended periods.

PDF Citaion Towards a Collective Approach of Immersive 3D Servicescape in the Metaverse Experience: Insights from Thematic Content Analysis

Lee Tae Hee ; Kwon, Gyu Hyun ; Jieun Han pp.46-56

초록보기

Abstract

This study synthesizes the current landscape of servicescape research within the context of the metaverse, identifying future academic challenges for the evolution of immersive 3D servicescapes. The research highlights key trends, gaps, and emerging themes in the field by utilizing a comprehensive thematic content analysis of existing literature review data and insights from focus group interviews with metaverse experts. Findings reveal that metaverse-related research in the field of servicescape has been proposed in five directions: (a) dynamics between physical and virtual servicescapes, (b) redefining servicescape measurements for the metaverse, (c) evolving the s-o-r framework, (d) personalization and adaptation of extended reality environment, and (e) necessity of domain-specific approach. The study proposes a roadmap for future investigations, contributing to the academic discourse by providing a nuanced understanding of immersive 3D servicescapes and suggesting strategic directions for further research.

PDF Citaion Retail Hoarding Behavior during COVID-19: Indirect Effects of Pandemic Stress via Mediating Factors and Online Consumer Trust

Sujin Min(Electronics and Telecommunications Research Institute (ETRI)) ; Yuna Ro ; Boram Kwon pp.57-73

초록보기

Abstract

After the outbreak of the coronavirus disease (COVID-19) pandemic, retailers have faced an unusual situation in which consumers hoard daily necessities amid a sharp increase in the proportion of online sales in several countries. scholars recently investigated consumers' pandemic-induced hoarding behavior, but studies examining hoarding behavior concerning online commerce are insufficient. This study investigates how pandemic-related stress has led to the daily necessities hoarding model. Next, we explore whether consumers' trust in online commerce strengthens the hoarding mechanism. The results show that pandemic-related stress affects hoarding behavior through perceived scarcity of necessities, anticipated regret, and the urge to buy. In this process, the relationship between anticipated regret and the urge to buy is and more substantial in those who highly trust online commerce. The results of this study promote an understanding of the theory by expanding the existing hoarding behavior model. In addition, by confirming that consumers' trust in online commerce strengthens the hoarding mechanism, the result suggests that it would be helpful for online commerce providers to build trust with customers during the pandemic.

PDF Citaion Fashion Product Review Analysis of C2C Second-hand Trading Platforms Using Topic Modeling: Focusing on Bungaejangter

Hyun Hee Park pp.74-87

초록보기

Abstract

This study aimed to identify key topics related to the consumption of second-hand fashion products by analyzing reviews of fashion products on a C2C second-hand trading platform. Reviews of second-hand fashion stores in Bungaejangter were collected and analyzed using text mining and Latent Dirichlet Allocation (LDA), a topic modeling technique. The topic modeling analysis resulted in the extraction of eight topics: customer service and satisfaction, wearing experience and satisfaction, product condition and customer expectations, interaction in the transaction process, gap between expectations and reality, seller friendliness and trust, overall satisfaction, quality and value assessment. The findings of this study provide valuable guidelines for developing strategies to meet customer expectations and demands in C2C-based online secondhand fashion transactions. They will contribute to enabling secondhand fashion sellers and platform operators to deliver customer-centric services and pursue sustainable growth.

PDF Citaion Statistical Analyses of Cross-Entropy Error Function with Probabilistic Target Encoding for Training Neural Networks

SANG HOON OH pp.88-92

초록보기

Abstract

Training neural networks with softmax outputs requires assigning target values to output nodes. Due to its simplicity, we often use one-hot encoding, which adopts “one” or “zero” as the desired output values. However, when training neural networks to minimize the cross-entropy error function between the desired and actual output node values, overfitting of neural networks to training samples becomes a significant issue. A probabilistic target encoding has been proposed to mitigate the overfitting. In this paper, we derive the optimal solutions for output nodes that minimize the cross-entropy error function using the probabilistic target encoding. In the extreme case of the probabilistic target encoding, the analysis corresponds to the cross-entropy error function with one-hot encoding. The statistical analyses conducted to derive the optimal solutions provide considerable insights, including the interval of target values for the Bayes classifier.

PDF Citaion Development of a Program to Predict Canine Diseases through Changes in Canine Behavior Patterns and Health Monitoring Questionnaires: A Pilot Study

KIM SEON CHIL pp.93-104

초록보기

Abstract

Although canine and humans have interacted for centuries, human understanding of canine health remains limited. Several canine -health-monitoring systems have been developed in recent times. However, several factors, such as the canine breed, age, size, and weight, make data estimation challenging. In this study, activity sensors were installed on the necks of 30 canines of six breeds, ages, and weights, and a novel disease-inference program was developed to track changes in their scratching, licking, swallowing, and sleeping behaviors. Further, health questionnaires were created for similar diseases based on the observed abnormal canine behavior. In addition, a software program was developed and verified to predict canine diseases based on these data and recommend check-ups accordingly. The sensitivity and specificity of decision-making were verified by comparing the data on behavioral pattern changes and disease predictions collected via questionnaires with the results of veterinarian diagnoses. The average sensitivity and specificity of disease predictions (digestive and skin), estimated by the changes in behavioral patterns and the owner questionnaire, were 82% and 81%, respectively. Cohen's kappa coefficient was 0.79 in the diagnostic area, demonstrating diagnosis consistency. Therefore, the results show that canine’s' abnormal scratching, licking, swallowing, and sleeping patterns can be used for health monitoring. This study contributes to the development of canine health status monitoring systems.

PDF Citaion OTT Drama and News Portal: The Case of Juvenile Justice on Netflix

Jungah Ahn(Tsinghua University) pp.105-113

초록보기

Abstract

This study aims to analyze an over-the-top (OTT) platform drama, Juvenile Justice, featuring the “law-breaching minors” dispute, which will help explore how the issues of “law-breaching minors” and juvenile delinquency in Naver and Daum news portal reports are conveyed and understood. This study employed keyword frequency, centrality, cluster, and frame analyses through semantic network analysis. The results demonstrated that some frames were revealed differently in the Naver and in the Daum news portal reports of the drama, while having “conflict and responsibility,” “solutions,” and “information offering of a drama” frames in common for both news portals. A “causes and reasons” frame was added in the Naver report, and a “global popularity” subframe, as an independent cluster, was classified in the Daum report. This means that, in the Naver report, news articles in relation to “law-breaching minor” issues were more intensively reported than drama content with comparison to the Daum report, which indicates different standards of news values between news portals. Therefore, this study showed that the application of news frame analysis of news portal reports on a specific dispute, using semantic network analysis, displayed significant differences according to their different perspectives and contexts.

PDF Citaion The Impact of Consumer Perceptions of SMEs' ESG Activities: The Mediating Effect of Corporate Image and the Moderated Mediating Effect of Ethical Consumption Tendency

JUNG BUB YEON ; Cheongyeul, Park ; Thomas P. Huber(Franklin University) pp.114-134

초록보기

Abstract

The purpose of this study is to investigate the impact of consumer perceptions of the Environmental, Social, and Governance (ESG) activities conducted by Small and Medium Enterprises (SMEs) on purchase intention, focusing particularly on the mediating role of corporate image and the moderated mediating role of consumers’ ethical consumption tendency. Based on data collected from 350 general adult respondents, SPSS PROCESS macro 4.2 was utilized to analyze direct, mediating, moderating, and moderated mediation effects. The findings are as follows. First, consumers' perceptions of SMEs' ESG activities significantly enhance both corporate image and purchase intention. Second, corporate image has a positive and significant effect on purchase intention and plays a mediating role in the relationship between ESG perception and purchase intention. Third, the mediating effect of corporate image weakens when consumers possess a high tendency toward ethical consumption, indicating that ethical consumers may be more critical and hold higher expectations for ESG practices by SMEs. Fourth, while ethical consumption tendency moderated the indirect effect of ESG activities on purchase intention through corporate image, it did not significantly moderate the direct relationship between ESG activities and purchase intention. These results suggest that ESG activities by SMEs contribute to enhancing consumer purchase intentions by shaping a favorable corporate image, although the strength of this influence varies depending on the ethical orientation of consumers. Practical implications include the strategic communication of ESG initiatives and the development of tailored ESG approaches that consider consumer ethical values to maximize their effectiveness.

PDF Citaion The Importance of Career Development Programs for Korean Seafarers: Case Studies from Key Shipping Countries

Junghwan Choi(Dalian Maritime University Law School) ; Sangseop Lim ; Byungha Lee ; Ahra Kim ; Kim,SeokHun pp.135-146

초록보기

Abstract

This study examines the necessity of implementing Career Development Programs for seafarers(CDPs) in Korea, drawing insights from major shipping countries. The research highlights the mandatory nature of CDPs under the Maritime Labour Convention (MLC) and their potential economic benefits, including job creation for young people. Through CDP implementation, Korea could potentially create employment for an average of 4,613 maritime officers annually in the international merchant fleet and 1,450 in the domestic fleet from 2024 to 2034. The study analyzes CDP practices in countries like Norway, the UK, Germany, and Japan, revealing varying approaches to seafarer career development. It emphasizes the importance of CDPs in enhancing the competitiveness of the maritime industry, facilitating career transitions, and addressing the global shortage of qualified seafarers. The research also underscores Korea's unique national characteristics, including its reliance on maritime transport and the potential role of seafarers as a fourth military branch, which necessitate maintaining a strong national maritime workforce. The study concludes by advocating for government-led development and funding of CDPs as a crucial strategy for fostering senior maritime officers and encouraging long-term onboard service in Korea.

PDF Citaion Integrating Error Back-Propagation and Independent Component Analysis Algorithms to Enhance Neural Network Performance

SANG HOON OH pp.147-154

초록보기

Abstract

The EBP (Error Back-Propagation) Algorithm was initially proposed for training MLP’s (Multi-Layer Perceptrons) and is now widely used for training deep neural networks. This supervised learning algorithm minimizes the error function between the actual output values of MLP’s and their desired values. However, ICA (Independent Component Analysis) is an unsupervised learning algorithm that aims to maximize the independence among the outputs of neural networks. ICA has been shown to realize visual features in the V1 layer of the human brain by learning from natural scenes and cochlear features of the human ear by learning from auditory signals. In this paper, we propose merging the supervised EBP algorithm with the unsupervised ICA algorithm to enhance the performance of neural networks by training independent features in the initial learning stage. This approach mirrors the feature-learning process observed in mammals during the early stages of life. Furthermore, the proposed approach is verified through simulations on isolated-word recognition tasks, achieving improved classification performance with faster learning convergence. In detail, when the number of hidden nodes is 100, EBP with ICA reaches a misclassification ratio of 2.78% on the test data at 160 epochs, while EBP achieves 3.28% at 300 epochs.

바로가기메뉴