• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.91-106
• /
• 2021

With the recent rapid development of deep learning technology, the demand for analyzing huge text documents in the national R&D field from various perspectives is rapidly increasing. In particular, interest in the application of a BERT(Bidirectional Encoder Representations from Transformers) language model that has pre-trained a large corpus is growing. However, the terminology used frequently in highly specialized fields such as national R&D are often not sufficiently learned in basic BERT. This is pointed out as a limitation of understanding documents in specialized fields through BERT. Therefore, this study proposes a method to build an R&D KoBERT language model that transfers national R&D field knowledge to basic BERT using further pre-training. In addition, in order to evaluate the performance of the proposed model, we performed classification analysis on about 116,000 R&D reports in the health care and information and communication fields. Experimental results showed that our proposed model showed higher performance in terms of accuracy compared to the pure KoBERT model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.651-660
• /
• 2021

This study examined the trend of standards established in the United States and to find points that can be applied to Korean defense standards. The titles of various United States defense standard documents registered on the web were selected for this research. The wordcloud was created after analyzing the frequency of words appearing in the title using text mining. The trend of words appearing in MIL-STD by era was obtained. This study identified words that appear often due to the format of the document itself, words that appear regularly throughout the era, words that are used frequently in the past but are not used much in the present, and words that did not receive attention in the past but appeared recurrently in the present. In addition, the characteristics of each document were derived through the wordcloud produced for various defense documents. In conclusion, Korean defense standards also require a consideration of safe and efficient management, transport, and load design of hazardous materials. Furthermore, the quality of defense standards can be expected to improve if the defense standard document system can be established, focusing on efficient management.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.1
• /
• pp.143-165
• /
• 2023

This study aims to propose a scaffolding strategy that can be applied to the information search process by using Kuhlthau's ISP model, which presented a design and implementation strategy for the mediation role in the learning process. To this end, the relevant literature was reviewed to categorize scaffolding strategies, and impressions were collected from the students surveys after providing 150 middle school students in the Daejeon area with the project class to which the scaffolding strategy based on the ISP model was applied. The collected data were processed into a form suitable for analysis through data preprocessing for word frequencies to be extracted, and topic analysis was performed using STM (Structural Topic Modeling). First, after determining the optimal number of topics and extracting topics for each stage of the ISP model, the extracted topics were classified into three types: cognitive domain-macro perspective, cognitive domain-micro perspective, and emotional domain perspective. In this process, we focused on cognitive verbs and emotional verbs among words extracted through text mining, and presented a scaffolding strategy model related to each topic by reviewing representative document cases. Based on the results of this study, if an appropriate scaffolding strategy is provided at the ISP model stage, a positive effect on learners' self-directed task solving can be expected.

• Journal of The Korean Association For Science Education
• /
• v.44 no.3
• /
• pp.231-248
• /
• 2024

This study developed a chatbot for first-year high school students, employing open-source software and the Korean Sentence-BERT model for AI-powered document classification. The chatbot utilizes the Sentence-BERT model to find the six most similar Q&A pairs to a student's query and presents them in a carousel format. The initial dataset, built from online resources, was refined and expanded based on student feedback and usability throughout over the operational period. By the end of the 2023 academic year, the chatbot integrated a total of 30,819 datasets and recorded 3,457 student interactions. Analysis revealed students' inclination to use the chatbot when prompted by teachers during classes and primarily during self-study sessions after school, with an average of 2.1 to 2.2 inquiries per session, mostly via mobile phones. Text mining identified student input terms encompassing not only science-related queries but also aspects of school life such as assessment scope. Topic modeling using BERTopic, based on Sentence-BERT, categorized 88% of student questions into 35 topics, shedding light on common student interests. A year-end survey confirmed the efficacy of the carousel format and the chatbot's role in addressing curiosities beyond integrated science learning objectives. This study underscores the importance of developing chatbots tailored for student use in public education and highlights their educational potential through long-term usage analysis.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of the Korea Society for Simulation
• /
• v.31 no.3
• /
• pp.35-44
• /
• 2022

In this study, we analyze and forecast quantum computer technology trends. Previous research has been mainly focused on application fields centered on technology for quantum computer technology trends analysis. Therefore, this paper analyzes important quantum computer technologies and performs future signal detection and prediction, for a more market driven technical analysis and prediction. As analyzing words used in news articles to identify rapidly changing market changes and public interest. This paper extends conference presentation of Cha & Chang (2022). The research is conducted by collecting domestic news articles from 2019 to 2021. First, we organize the main keywords through text mining. Next, we explore future quantum computer technologies through analysis of Term Frequency - Inverse Document Frequency(TF-IDF), Key Issue Map(KIM), and Key Emergence Map (KEM). Finally, the relationship between future technologies and supply and demand is identified through random forests, decision trees, and correlation analysis. As results of the study, the interest in artificial intelligence was the highest in frequency analysis, keyword diffusion and visibility analysis. In terms of cyber-security, the rate of mention in news articles is getting overwhelmingly higher than that of other technologies. Quantum communication, resistant cryptography, and augmented reality also showed a high rate of increase in interest. These results show that the expectation is high for applying trend technology in the market. The results of this study can be applied to identifying areas of interest in the quantum computer market and establishing a response system related to technology investment.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.627-635
• /
• 2022

As the non-face-to-face situation continues for a long time due to COVID-19, the underlying technologies of the 4th industrial revolution such as IOT, AR, VR, and big data are affecting the metaverse platform overall. Such changes in the external environment such as society and culture can affect the development of academics, and it is very important to systematically organize existing achievements in preparation for changes. The Korea Educational Research Information Service (RISS) collected data including the 'metaverse platform' in the keyword and used the text mining technique, one of the big data analysis. The collected data were analyzed for word cloud frequency, connection strength between keywords, and semantic network analysis to examine the trends of metaverse platform research. As a result of the study, keywords appeared in the order of 'use', 'digital', 'technology', and 'education' in word cloud analysis. As a result of analyzing the connection strength (N-gram) between keywords, 'Edue→Tech' showed the highest connection strength and a total of three clusters of word chain clusters were derived. Detailed research areas were classified into five areas, including 'digital technology'. Considering the analysis results comprehensively, It seems necessary to discover and discuss more active research topics from the long-term perspective of developing a metaverse platform.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.661-670
• /
• 2021

Research trends can be usefully used to determine the importance of research topics by period, identify insufficient research fields, and discover new fields. In this study, research trends of urban spaces, where various problems are occurring due to population concentration and urbanization, were analyzed by topic modeling. The analysis target was the abstracts of papers listed in the Korea Citation Index (KCI) published between 2002 and 2019. Topic modeling is an algorithm-based text mining technique that can discover a certain pattern in the entire content, and it is easy to cluster. In this study, the frequency of keywords, trends by year, topic derivation, cluster by topic, and trend by topic type were analyzed. Research in urban regeneration is increasing continuously, and it was analyzed as a field where detailed topics could be expanded in the future. Furthermore, urban regeneration is now becoming a regular research field. On the other hand, topics related to development/growth and energy/environment have entered a stagnation period. This study is meaningful because the correlation and trends between keywords were analyzed using topic modeling targeting all domestic urban studies.

• 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.

• Knowledge Management Research
• /
• v.25 no.1
• /
• pp.1-19
• /
• 2024

This study analyzed the changes in social media reactions of data subjects to major personal data breach incidents in South Korea from January 2014 to October 2022. We collected a total of 1,317 posts written on Naver Blogs within a week immediately following each incident. Applying the LDA topic modeling technique to these posts, five main topics were identified: personal data breaches, hacking, information technology, etc. Analyzing the temporal changes in topic distribution, we found that immediately after a data breach incident, the proportion of topics directly mentioning the incident was the highest. However, as time passed, the proportion of mentions related indirectly to the personal data breach increased. This suggests that the attention of data subjects shifts from the specific incident to related topics over time, and interest in personal data protection also decreases. The findings of this study imply a future need for research on the changes in privacy awareness of data subjects following personal data breach incidents.