• The Journal of Asian Finance, Economics and Business
• /
• 제6권3호
• /
• pp.173-183
• /
• 2019

This study aims to utilize big data contents of news and social media for developing a corporate strategy of multinational enterprises and their global decision-making through the data mining technique, especially text mining. In this paper, the data of 2 news media (BBC and CNN) and 2 social media (Facebook and Twitter) were collected for the three global leading Korean companies (Samsung, Hyundai Motor Company, and LG) from April, 2018 to April, 2019. The findings of this paper have shown that traditional news media and also modern social media have become devastating tools to extract global trends or phenomena for businesses. Moreover, this presents that a company can adopt a two-track strategy through two different types of media by deriving the key issues or trends from news media channels and also grasping consumers' sentiments, preference or issues of interest such as battery or design from social media. In addition, analyzing the texts of those media and understanding the association rules greatly contribute to the comparison between two different types of media channels to see the difference. Lastly, this provides meaningful and valuable data empowered insights to find a future direction comprehensively and develop a global strategy for sustainability of business.

• 한국주거학회:학술대회논문집
• /
• 한국주거학회 2011년도 춘계학술발표대회 논문집
• /
• pp.285-289
• /
• 2011

he purpose of this study is to assess the effects of real estate policy on apartment price index in Seoul. To meet the research goal, this research reviewed real estate policy of the government from January of 1986 to August of 2010, and then it collected monthly apartment price index in 25 local districts of Seoul from January of 2003 to August of 2010. After 25 districts were grouped into 2 areas (14 districts in Gangnam and 11 districts in Gangbuk), the data of two areas were analyzed by using the SAS program, Cluster analysis with Ward method showed 3 clusters on each area, and with 6 clusters in total, the effects of real estate policy in the period were examined by using residual analysis. The analysis indicated two major shocks (one was from May to October of 2003, and the other was from March of 2006 to January of 2007), and the results showed that the intervention of government in the market had the asymmetric effects in bullish and bearish times. It implies that the market volatility is substantially influenced by irrational sentiments. Thus, it's suggested to devise the consumer sentiment index suitable in real estate market.

• 한국식생활문화학회지
• /
• 제18권3호
• /
• pp.211-225
• /
• 2003

This present study suggests a wider view of our ancestors' food culture by examining the generality and peculiarity of the food culture of the Chosun Period by associating the culture with genre paintings made in the $18th{\sim}19th$ century in Korea. People in the Chosun Period outwardly advocated the Confucian idea reflecting the life philosophy of Chinese. However, the vitality of common people's frank and simple lifestyles saturate genre paintings and display Korean food culture and sentiments of the age. Initially this paper examines the history of food sociology through Namjong literary artists' paintings. The meaning and philosophy of drinks are considered in relation to the trend of declining tea culture among scholars in the mid-Chosun Period with the policy of promoting Confucianism and oppressing Buddhism. Secondly, this paper investigates the background of genre paintings in the late Chosun Period, and examines the unique food culture of Koreans appearing in paintings, particularly with regard to the abundance and variety of seasoned vegetables appearing in genre paintings, our ancestors' sentiment appearing in milk-gathering painting, humanity in guest reception, food culture and view of nature in farm villages, fishing life history, food distribution culture, soybean-curd culture, etc.

• 한국IT서비스학회지
• /
• 제17권1호
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• 한국산업정보학회논문지
• /
• 제23권3호
• /
• pp.59-71
• /
• 2018

Social media has immense popularity among all services today. Data from social network services (SNSs) can be used for various objectives, such as text prediction or sentiment analysis. There is a great deal of Korean and English data on social media that can be used for sentiment analysis, but handling such huge amounts of unstructured data presents a difficult task. Machine learning is needed to handle such huge amounts of data. This research focuses on predicting Korean and English sentiment using deep forward neural network with a deep learning architecture and compares it with other methods, such as LDA MLP and GENSIM, using logistic regression. The research findings indicate an approximately 75% accuracy rate when predicting sentiments using DNN, with a latent Dirichelet allocation (LDA) prediction accuracy rate of approximately 81%, with the corpus being approximately 64% accurate between English and Korean.

• 한국해양환경ㆍ에너지학회지
• /
• 제9권2호
• /
• pp.65-71
• /
• 2006

본 연구는 부산지역내에 어촌 및 어항을 방문하는 방문객과 어촌 및 어항개발에 직접적 또는 간접적으로 관련이 있는 지역주민을 대상으로 설문조사를 수행하였다. 설문 내용은 어촌 및 어항개발이 지역사회에 미치는 영향, 어촌 및 어항개발 시 고려/개선사항, 투자우선순위 어촌 및 어항 개발방향에 대한 것으로 초점을 두었다. 설문조사 결과를 바탕으로 향후 부산지역에서의 어촌 어항개발 방향을 모색하고자 하였다.

• 한국주거학회논문집
• /
• 제22권1호
• /
• pp.11-23
• /
• 2011

The purpose of this study is to explore cohort changes in first-time homeownership in Korea. The study collected qualitative data from individual interviews to explore the housing trajectories of different birth cohorts. As a result, Individual interviews facilitated an exploration of the decision making process of first-time homeowner with in a cohort context. The cohorts born in the 1950s seek a sense of security through homeownership, and have strong Korean sentiments of ownership. They tried various means to buy a house, and real estate market boom at that time played a role in the driving force. The cohorts born in the 1960s have less insecurity of tenure than the previous cohorts, but they still feel the need for homeownership. Since the currency crisis in 1997 caused the fluctuation of housing price, the 1960s cohort experienced a dramatic decline and rebound of assets while the previous cohorts had experienced a steady rise in housing prices. Finally, the attitude towards housing in the group of 1970s cohorts has changed from ownershiporiented to use-oriented.

• Child Health Nursing Research
• /
• 제8권1호
• /
• pp.20-31
• /
• 2002

The purpose of this study was to understand and analyze the subjective structure of attitude, opinion of infant and todder's mother, regarding the massage intervention in order to yield fundamental data for the activation scheme of the massage intervention. This research was based on a Q-Methodological approach. According to the results of this study, there were four categories of mothers' opinion about the massage intervention. The first type accepts the wholistic effect of massage intervention very positively that it improves infant's health in various aspects: prevention of diseases, promotion of the growth, settlement of sentiments, etc. The second type describes the effect of the intervention in the emotional aspect, such that the intimacy plays a very significant role in the intervention. The third type explains the complementary effect of the intervention that it eases symptoms rather than actually cures diseases. The fourth type emphasizes the healing effect of the intervention that it is required to go through professional training to utilize the effect. For example, a Kyongrak massage is very effective for curing diseases. In consideration of various types of massage intervention, it is very necessary to have a specialty for the massage intervention and develop unique mothers education programs depending upon different applications of the massage intervention in order to reorganize and activate the massage intervention as a nursing intervention for infant and toddlers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5120-5142
• /
• 2018

Social media enables customers to share their views, opinions and experiences as product reviews. These product reviews facilitate customers in buying quality products. Due to the significance of online reviews, fake reviews, commonly known as spam reviews are generated to mislead the potential customers in decision-making. To cater this issue, review spam detection has become an active research area. Existing studies carried out for review spam detection have exploited feature engineering approach; however limited number of features are considered. This paper proposes a Feature-Centric Model for Review Spam Detection (FMRSD) to detect spam reviews. The proposed model examines a wide range of feature sets including ratings, sentiments, content, and users. The experimentation reveals that the proposed technique outperforms the baseline and provides better results.

• 한국컴퓨터정보학회논문지
• /
• 제19권12호
• /
• pp.49-56
• /
• 2014

본 논문에서는 대용량의 문서, 인터넷 댓글, 소셜 데이터, 메시지 텍스트 등으로부터 표준, 일상적 언어, 및 은어(隱語), 비속어, 약어, 이모티콘 등을 감성 분석함으로써, 복합적인 감성 중 근간이 되는 주 감성들을 측정하고 평가하는 방법을 제안한다. 제안된 방법론은 IRLBA(Implicitly Restarted Lanczos Bidiagonalization Algorithm)을 활용하여 규모가 큰 희소행렬에 대한 주성분분석을 실시하며, 데이터 취합, 메시지 분석, 감성 평가, 감성 분석 및 통합 그리고 결과물 시각화 모듈로 구성된다. 본 연구를 통해 제안된 방법론은 소셜 데이터의 감성분석의 정확도를 향상시키고 감성분석의 활용범위를 확장시키는데 있어 도움을 줄 수 있을 것으로 기대된다.