• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• Journal of Information Technology Services
• /
• v.18 no.2
• /
• pp.123-141
• /
• 2019

The goal of this study is to review the major research trend on the convergence studies of AI and healthcare technologies. For the study, 15,260 English articles on AI and healthcare related topics were collected from Scopus for 55 years from 1963, and text mining techniques were conducted. As a result, seven key research topics were defined : "AI for Clinical Decision Support System (CDSS)", "AI for Medical Image", "Internet of Healthcare Things (IoHT)", "Big Data Analytics in Healthcare", "Medical Robotics", "Blockchain in Healthcare", and "Evidence Based Medicine (EBM)". The result of this study can be utilized to set up and develop the appropriate healthcare R&D strategies for the researchers and government. In this study, text mining techniques such as Text Analysis, Frequency Analysis, Topic Modeling on LDA (Latent Dirichlet Allocation), Word Cloud, and Ego Network Analysis were conducted.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.11a
• /
• pp.152-152
• /
• 2017

• Journal of Korean Elementary Science Education
• /
• v.39 no.2
• /
• pp.255-267
• /
• 2020

Students' engagement is important for meaningful learning and it has multifaceted aspects for their science learning. This study investigated elementary students' perceptions of science learning engagement. The subjects of this study were 341 4^th to 6^th elementary students. The survey questionnaires were 5-Likert scale questions and free response questions on science learning engagement. The results showed that elementary students' perceptions of behavioral engagement were higher than emotional and cognitive engagement. Keyword network analysis with NetMiner program showed that the frequent key words of science learning engagement were 'experiment', 'listening', and 'teachers' explanation', which were mostly the behavioral types of engagement. The degree centrality and eigenvector centrality of these key words appeared high. 'Interest', which is emotional engagement, were also one of the frequent key words, but the centralities of this word were relatively low. The Frequent key words of science learning disengagement were mostly related with off-tasks, not doing expected behaviors and negative emotions about science and science learning. Educational implications on science learning engagement were discussed.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.24-44
• /
• 2014

This study explores the political meaning of candidate's speech and statement who run for the 18th presidential election in the viewpoint of communication. The visibility of the words and the connectivity between the words are analyzed in the viewpoint of structural aspect and the vision, policy. The visibility of the words is analyzed based on the frequency of the words mentioned in the speech or the statement. The connectivity between the words are analyzed based on the network analysis and expressed by graph. In the case of candidate Park, the key word is the happiness of the people and appointment. The key word for candidate Moon is regime change and the Korean Peninsula and the key word for candidate Ahn is the people and change. This study contributes positively to the study of candidate's discourse in the viewpoint of methodology by using network analysis and exploring scientifically the connectivity of the words. In the theoretical aspect this study uses the results of network analysis for revealing what is the leadership components in the speech and the statement. In conclusion, this study highlights the extension of the communication studies.

• The Research Journal of the Costume Culture
• /
• v.25 no.1
• /
• pp.1-15
• /
• 2017

Social commerce is a kind of internet shopping mall in which consumers purchase the products with other consumers through mutual interactions including the development of SNS(social network service). Social commerce has expanded rapidly as a mainstream online shopping mall over the past five years driving consumers to purchase more fashion products providing the cheaper prices than open market internet shopping mall. The purpose of this study is to identify the important parameters of social commerce characteristics and consumer characteristics that affect repurchase intention and word-of-mouth intention. A 221 survey questionnaire was distributed to men in their 20's and 30's who live in Seoul metropolitan area. The data were analyzed utilizing Cronbach's ${\alpha}$, factor analysis, and regression analysis using the SPSS 18.0 program. The results revealed, first, that in terms of social commerce characteristics, three variables(website reputation, interactivity, and product scarcity) influenced repurchase intention. Among them, website reputation identified as the most important factor influencing repurchase intention and word-of-mouth intention. Second, with regard to consumer characteristics, interest and a tendency toward impulse buying affected the repurchase intention, and interest and internet shopping experience have influenced the word-of-mouth intention. Among three variables interest in social commerce identified as the key factor affecting both repurchase intention and word-of-mouth intention. The results of the study provide the practical implications and suggest the business strategies to enhance social commerce in the future by identifying the key social commerce characteristics and consumer characteristics that influence male consumers' buying behaviors.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.3
• /
• pp.413-426
• /
• 2020

This study researches the association between associative vocabulary and fashion image language in order to extract ideas that can be used as basic data for design ideas. Classic - avant-garde imaged language were chosen as theme words and each 70 questionnaires per a final image word were used for analysis. We obtained the following results by researching keywords that explained classic image words through a word cloud technique. It was found to have high central representation in the order of suit, classical, basic, music, Chanel, black and traditional. The core key words explaining avant-garde image language were found to have a central representation in the order of : peculiar, huge, Comme des Garçons, artistic, creative, deconstruction and individuality. We extracted the necessary idea dimensions needed for design ideas through associative network graph analysis. In the case of classical image language, it was named as the Mannish Item, Music, Modern Color, and the Traditional Classicality dimensions. In the case of avant-garde image language, it was named as the Key Image, Artistic Aura, Key Design and Designers dimensions.

• Journal of the Korean Society of Earth Science Education
• /
• v.9 no.1
• /
• pp.65-87
• /
• 2016

The purpose of this study is to examine Korean journals related to science education in order to analyze research trends into Nature of science in Korea. The subject of the study is the level of Korean Citation Index (KCI-listed, KCI listing candidates), that can be searched by the key phrase, "Nature of science" in Korean language through the RISS service. In this study, the Descriptive Statistical Analysis Method is utilized to discover the number of research articles, classifying them by year and by journal. Also, the Sementic Network Analysis was conducted to Word Cloud Analysis the frequency of key words, Centrality Analysis, co-occurrence and Cluster Dendrogram Analysis throughout a variety of research articles. The results show that 91 research papers were published in 25 journals from 1991 to 2015. Specifically, the 2 major journals published more than 50% of the total papers. In relation to research fields., In addition, key phrases, such as 'Analysis', 'recognition', 'lessons', 'science textbook', 'History of Science' and 'influence' are the most frequently used among the research studies. Finally, there are small language networks that appear concurrently as below: [Nature of science - high school student - recognize], [Explicit - lesson - effect], [elementary school - science textbook - analysis]. Research topic have been gradually diversified. However, many studies still put their focus on analysis and research aspects, and there have been little research on the Teaching and learning methods.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.1036-1047
• /
• 2013

In this study, we applied the time series analysis to the randomized controlled trial (RCT) researches related to insomnia for finding international trends. The data used in the analysis of 379 of ClinicalTrials, Web of Science was the of 132 by several keyword related with 'Insomnia' and 'Randomized Clinical Trial'. In ClinicalTials, RCT studies for insomnia, drug, cognitive behavioral therapy, depression were the key words make up the main network. In WOS, 'melatonin' key word was added in the main network. In addition to, we found the characteristic that the elderly and female subjects were steady studied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.