• Korea Trade Review
• /
• v.45 no.3
• /
• pp.55-69
• /
• 2020

This study examines the research trends and knowledge structure of international trade studies using topic modeling method, which is one of the main methodologies of text mining. We collected and analyzed English abstracts of 1,868 papers of three Korean major journals in the area of international trade from 2003 to 2019. We used the Latent Dirichlet Allocation(LDA), an unsupervised machine learning algorithm to extract the latent topics from the large quantity of research abstracts. 20 topics are identified without any prior human judgement. The topics reveal topographical maps of research in international trade and are representative and meaningful in the sense that most of them correspond to previously established sub-topics in trade studies. Then we conducted a regression analysis on the document-topic distributions generated by LDA to identify hot and cold topics. We discovered 2 hot topics(internationalization capacity and performance of export companies, economic effect of trade) and 2 cold topics(exchange rate and current account, trade finance). Trade studies are characterized as a interdisciplinary study of three agendas(i.e. international economy, International Business, trade practice), and 20 topics identified can be grouped into these 3 agendas. From the estimated results of the study, we find that the Korean government's active pursuit of FTA and consequent necessity of capacity building in Korean export firms lie behind the popularity of topic selection by the Korean researchers in the area of int'l trade.

• 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.

• Knowledge Management Research
• /
• v.23 no.3
• /
• pp.129-152
• /
• 2022

As a key infrastructure for digital transformation, the spread of data, network, artificial intelligence (D.N.A.) fields and the emergence of promising industries are laying the groundwork for active digital innovation throughout the economy. In this study, by applying the text mining methodology, major topics were derived by using the abstract, publication year, and research field of the study corresponding to the SCIE, SSCI, and A&HCI indexes of the WoS database as input variables. First, main keywords were identified through TF and TF-IDF analysis based on word appearance frequency, and then topic modeling was performed using g-DMR. With the advantage of the topic model that can utilize various types of variables as meta information, it was possible to properly explore the meaning beyond simply deriving a topic. According to the analysis results, topics such as business intelligence, manufacturing production systems, service value creation, telemedicine, and digital education were identified as major research topics in digital transformation. To summarize the results of topic modeling, 1) research on business intelligence has been actively conducted in all areas after COVID-19, and 2) issues such as intelligent manufacturing solutions and metaverses have emerged in the manufacturing field. It has been confirmed that the topic of production systems is receiving attention once again. Finally, 3) Although the topic itself can be viewed separately in terms of technology and service, it was found that it is undesirable to interpret it separately because a number of studies comprehensively deal with various services applied by combining the relevant technologies.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2907-2915
• /
• 2018

Journal of the Korean Data Analysis Society founded in 1998 has played the role of a major application journal. In this study, we checked the objective of this journal by checking the abstracts for 10 years. Abstract data was crawled from the online journal site (kdas.jems.or.kr) and analyzed by topic model. As a result, we found 18 topics from 2680 abstracts that had several contents, for example, nursing, marketing, economics, regression, factor analysis, data mining and statistical inferences. Topic1 (regression) is most frequent with 460 documents and we found the usefulness of regression in the applied science area. We confirmed the significant 10 association rules using by Fisher's exact test. Also, for exploring the trend of topics, we conducted the topic analysis for two periods which are 2006-2011 period and 2012-2016 period. We found that the control study was more frequent than survey study over time and regression and factor analysis were frequent regardless of time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.1
• /
• pp.81-98
• /
• 2013

Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.170-185
• /
• 2023

The advent of big data has brought about the need for analytics. Natural language processing (NLP), a field of big data, has received a lot of attention. Topic modeling among NLP is widely applied to identify key topics in various academic journals. The Korean Society of Industrial and Systems Engineering (KSIE) has published academic journals since 1978. To enhance its status, it is imperative to recognize the diversity of research domains. We have already discovered eight major research topics for papers published by KSIE from 1978 to 1999. As a follow-up study, we aim to identify major topics of research papers published in KSIE from 2000 to 2022. We performed topic modeling on 1,742 research papers during this period by using LDA and BERTopic which has recently attracted attention. BERTopic outperformed LDA by providing a set of coherent topic keywords that can effectively distinguish 36 topics found out this study. In terms of visualization techniques, pyLDAvis presented better two-dimensional scatter plots for the intertopic distance map than BERTopic. However, BERTopic provided much more diverse visualization methods to explore the relevance of 36 topics. BERTopic was also able to classify hot and cold topics by presenting 'topic over time' graphs that can identify topic trends over time.

• Journal of the Korean Society for information Management
• /
• v.26 no.2
• /
• pp.105-126
• /
• 2009

In this study, research topic areas in Korean and American medical schools were analyzed to detect each nation's major research areas. CLINICAL NEUROLOGY was identified as the Korean researchers' major subject area by the total number of journals and 'RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING' was the most major area by the total number of articles. On the other hand, American researchers' top major subject area was the one same area according to all analysis, BIOCHEMISTRY & MOLECULAR BIOLOGY. In addition, Korean researchers showed publishing tendency related to journal preference in several subject areas.

• Knowledge Management Research
• /
• v.17 no.2
• /
• pp.165-185
• /
• 2016

Though Korea has received attention through an exceptional economic growth and the big K-POP fever all over the world, its happiness level is not so high. Therefore, this research aims to find not only the Korean' s condition of the happiness and unhappiness, but also the way to enhance their happiness. We collected various web data(89,127 cases from 2013/01 to 2014/12) through searching our own 26 keywords based on Alderfer's ERG Theory. Also, we tried to analyze the subjects related to happiness and unhappiness by using LDA topic modeling. As the result, the condition of happiness and unhappiness were the top topics extracted from each field. We conducted the second detailed analysis based on the data of condition of the happiness and unhappiness which are the top topics of the previous analysis. From the second analysis result, we proposed several ways to enhance happiness from the perspective of government, corporate, family, education, social welfare.This paper is meaningful because it catches the condition of happiness and unhappiness based on a real web data as well as transform the data into the knowledge. Also, this paper provides the practical methods from the view from all walks of life that may enhance happiness and relieve unhappiness.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.423-434
• /
• 2019

An important issues in Korea society in 2018 was the revision of the university entrance examination system. Among the discussions, in order to grasp what the issue of admission officer system is, attention was focused on the function of media such as monitoring and criticism as well as the tried topic analysis of related news articles. As a result, the reorganization of the College Scholastic Ability Test (CSAT) was derived and showed the sensitivity of Korean society towards the CSAT. Topics directly related to the admission officer system were the selection factor and fairness of the university entrance examination system in relation to the selection factor.

• The Journal of Information Systems
• /
• v.31 no.2
• /
• pp.239-261
• /
• 2022

Purpose The purpose of this study is to explore and compare changes in tourist opinion during the COVID-19 pandemic. Since the COVID-19 outbreak has caused changes in all areas of our lives, the conditions related to confinement during a lockdown have led to changes in tourists' habits and behaviors. Design/methodology/approach To analyze opinion changes about tourist attractions, this study performed topic modeling by summarizing topics into five dimensions: management, scenery, price, suggestion, and safety; then, based on the topic modeling results, sentiment analysis and emotion analysis were conducted to explore the change of tourists' opinion during the COVID-19 pandemic. Findings According to the results, this study confirmed the pandemic's positive effect on tourists' opinions about attractions after the COVID 19 outbreak. Presumably due to the absence of lines and crowed. Moreover, the dimension 'Safety' started to appear in US tourists' attractions reviews only in the period after the outbreak and during the mass vaccination. These results mean that tourists started to care more about safety due to the impact of the COVID-19 pandemic.