• Educational Technology International
• /
• v.25 no.1
• /
• pp.1-25
• /
• 2024

This study aims to analyze the impact of learners' usability perceptions of topic modeling-based visual feedback and generative AI interpretation on reflection levels in online discussions. To achieve this, we asked 17 students in the Department of Korean language education to conduct an online discussion. Text data generated from online discussions were analyzed using LDA topic modeling to extract five clusters of related words, or topics. These topics were then visualized in a network format, and interpretive feedback was constructed through generative AI. The feedback was presented on a website and rated highly for usability, with learners valuing its information usefulness. Furthermore, an analysis using the non-parametric Mann-Whitney U test based on levels of usability perception revealed that the group with higher perceived usability demonstrated higher levels of reflection. This suggests that well-designed and user-friendly visual feedback can significantly promote deeper reflection and engagement in online discussions. The integration of topic modeling and generative AI can enhance visual feedback in online discussions, reinforcing the efficacy of such feedback in learning. The research highlights the educational significance of these design strategies and clears a path for innovation.

• The Journal of Information Systems
• /
• v.29 no.2
• /
• pp.221-242
• /
• 2020

Purpose This study collects data of the recently activated online black market and analyzes it to present a specific method for preparing for a hacking attack. This study aims to make safe from the cyber attacks, including hacking, from the perspective of individuals and businesses by closely analyzing hacking methods and tools in a situation where they are easily shared. Design/methodology/approach To prepare for the hacking attack through the online black market, this study uses the routine activity theory to identify the opportunity factors of the hacking attack. Based on this, text mining and social network techniques are applied to reveal the most dangerous areas of security. It finds out suitable targets in routine activity theory through text mining techniques and motivated offenders through social network analysis. Lastly, the absence of guardians and the parts required by guardians are extracted using both analysis techniques simultaneously. Findings As a result of text mining, there was a large supply of hacking gift cards, and the demand to attack sites such as Amazon and Netflix was very high. In addition, interest in accounts and combos was in high demand and supply. As a result of social network analysis, users who actively share hacking information and tools can be identified. When these two analyzes were synthesized, it was found that specialized managers are required in the areas of proxy, maker and many managers are required for the buyer network, and skilled managers are required for the seller network.

• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.635-648
• /
• 2006

As the advances of Internet infra structure and the support of console and mobile for network games, the industry of online game has been growing rapidly, and the online game traffic in the Internet has been increasing steadily. For design and simulation of game network, the analysis of online game traffic have to be preceded. Therefore a number of papers have been proposed for the purpose of analyzing the traffic data of network games and providing the models. We make and use GameNet Analyzer as a dedicated tool for game traffic measurement and analysis in this paper. We measure the traffic of FPS Quake 3, RTS Starcraft and MMORPG World of Warcraft (WoW), and analyze the packet size, packet IAT(inter-arrival time), data rate and packet rate according to the number of players and in-game behaviors. We also present the traffic models using measured traffic data. These analysis and models of game traffic can be used for effective network simulation, performance evaluation of game network and the design of online games.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06d
• /
• pp.105-108
• /
• 2007

Bayesian learning network is employed for diverse applications. This paper discusses the Bayesian learning network algorithm structure which can be applied in the wireless sensor network environment for various online applications. First, this paper discusses Bayesian parameter learning, Bayesian DAG structure learning, characteristics of wireless sensor network, and data gathering in the wireless sensor network. Second, this paper discusses the important considerations about the online Bayesian learning network and the conceptual structure of the learning network algorithm.

• Journal of Digital Convergence
• /
• v.10 no.1
• /
• pp.423-428
• /
• 2012

By shifting web2.0 users who share information from passive consumption and create their own information and exchange in the form of an active and visible appearance was changing. Most simply and easily with features that can be accessed. SNS is native to Korea me2day, Cyworld, (c) Logs and foreign SNS of Facebook, Twitter and a surge in user FramVille, Mafia War's Game, and many users use to SNG are. SNG's compared to the foreign national is active and not yet is a step. The domestic market, the benefits of this game online games and SNS in vogue these days to incorporate the concept in the market for a new form of the domestic game that the game, SNOG (Social Network Online Game, social networks, online games) to the expansion of flexible development direction, Expand accessibility, expansion of social skills is to present to the three.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.61-71
• /
• 2024

The dynamic nature of Online Social Networks (OSNs), especially on platforms like Twitter, presents challenges in identifying and responding to community attacks, particularly within Arabic content. The proposed integrated system addresses these challenges by achieving 91% accuracy in detecting real-time community event attacks while efficiently managing computational costs. This is accomplished through the use of specialized integrated approach clustering to detect both major and minor attacks. Additionally, the system leverages clustering algorithms, temporal modules, and social network graphs to identify events, map communities, and analyze online dynamics. An extensive parameter sensitivity analysis was conducted to fine-tune the algorithm, and the system's effectiveness was validated using a benchmark dataset, demonstrating substantial improvements in event detection.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.370-379
• /
• 2012

This study is identifying a social standing on adolescents' social network in offline and how the social standing influence to online social activity. For the purpose, we explore two research questions. First, How the adolescents' social standing present in their offline social network? Second, How the adolescents' social standing influence to online social activity? Using data, we first visualized 5 social network of adolescents, and deducted each ego networks and global network. Also we investigated causality between social standing and social activities. The result showed adolescents' social tie and social gregariousness influence to social activity width and depth in ego network. Based on these findings, we discussed some implications, limitations, and future direction.

• The Journal of the Korea Contents Association
• /
• v.10 no.11
• /
• pp.30-37
• /
• 2010

It is very important to analyze online customer reviews, which are small documents of writing opinions or experiences about products or services, for both customers and companies because the customers can get good informations and the companies can establish good marketing strategies. In this paper, we did not propose only dependency network model which is tool for analyzing online customer reviews, but also designed and implemented the system based on the dependency network model. The dependency network model analyzes both subjective and objective sentences, so that it can represent relative importance and relationship between the nouns in the sentences. In the result of implementing, we recognized that relative importance and relationship between the features of products or services, which can not be mined by opinion mining, can be represented by the dependency network model.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.12
• /
• pp.885-893
• /
• 2006

The Bayesian network(BN) has emerged in recent years as a powerful technique for handling uncertainty iii complex domains. Parameter learning of BN to find the most proper network from given data set has been investigated to decrease the time and effort for designing BN. Off-line learning needs much time and effort to gather the enough data and since there are uncertainties in real world, it is hard to get the complete data. In this paper, we propose an online learning method of Bayesian network parameters from incomplete data. It provides higher flexibility through learning from incomplete data and higher adaptability on environments through online learning. The results of comparison with Voting EM algorithm proposed by Cohen at el. confirm that the proposed method has the same performance in complete data set and higher performance in incomplete data set, comparing with Voting EM algorithm.

• Journal of Digital Convergence
• /
• v.8 no.1
• /
• pp.71-79
• /
• 2010

Impact of online social network to cyber community has increased much attention recently. The biggest challenge in fostering a social network is to the extent whether it helps to build human capital network or social community. We propose what critical factors influence the formation of online capital network. The study uses three independent factors as motivation, self disclosure, and interactivity and two dependent factors as knowledge sharing and strengthening relationships to create virtual capital connection. Data collected from 256 university students to test the proposed model. The results of the study shows that all hypothesis are supported except one with strengthening relationship. Implications and limitations of this research are discussed.