• Journal of Environmental Impact Assessment
• /
• v.31 no.5
• /
• pp.310-320
• /
• 2022

This study aimed to identify the change in the public perception of "bats" after the outbreak of the coronavirus (COVID-19) infection. Text mining and network analysis were conducted for blog posts, the largest social network in Korea. We collected 9,241 Naver blog posts from 2019 to 2020 just before the outbreak of COVID-19 in Korea. The data were analyzed with Python and NetMiner 4.3.2, and the public's perception of bats was examined through the relationship of keywords by period. Findings indicated that the frequency of bat keywords in 2020 increased more than 25 times compared to 2019, and the centrality value increased more than three times. The perception of bats changed before and after the outbreak of the pandemic. Prior to COVID-19, bats were highly recognized as a species of wildlife while in the first half of 2020, they were strongly considered as a threat to human society in relation to infectious diseases and health. In the second half of 2020, it was confirmed that the area of interest in bats expanded as the proportion of ecological and cultural types ofresearch increased. This study seeks to contribute to the expansion and direction of future research in bats by understanding the public's interest in the potential impact of the species as disease hosts post the COVID-19 pandemic.

• 한국노년학
• /
• v.41 no.4
• /
• pp.505-525
• /
• 2021

Purpose. The purpose of this study is to examine how the phrase "old person" are expressed and used in the online sphere. Based on the theoretical concept of stigma, this study investigates the images and attitudes in society toward the elderly, and the characteristics of hate speech aimed at the elderly. Method. This study conducted text mining based on social big data using anonymous conversations. Results. It was confirmed that the elderly images shared online were generally negative. The attitudes expressed toward them also tended to be negative due to the negative images that are propagated of the elderly. The hate speech relating to the elderly, in usages such as 'Teul-ttag' and 'Kon-dae', were mainly identified in comments that negatively evaluate the elderly, and these expressions demonstrate the depth of hate and discrimination towards the elderly who are considered burdensome by young people. Interestingly, the hateful expressions towards the elderly were found more with regard to issues related to politics and economics and not just any content about the elderly. Conclusions. This study discussed the ways and means to enhance inter-generational understanding and solidity.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• Journal of Service Research and Studies
• /
• v.13 no.1
• /
• pp.96-107
• /
• 2023

The objective of this study is to explore future issues that Chinese users, who have the highest mobile payment service usage rate in the world, will be most interested in. For this purpose, after collecting text data from a Chinese SNS site, it classifies major keywords into 4 types of future signals by using Keyword Emergence Map (KEM) and Keyword Issue Map (KIM). Furthermore, to understand the four types of signals in detail, it performs the qualitative analysis on text related to each signal keyword. As a result, it finds that the strong signal, which is rapidly growing in keyword appearance frequency during this research period, includes the keywords related to the daily life of Chinese people, such as buses, subways, and household account books. Additionally, it find that the signal that appears frequently now, but with a low increase rate, includes various services that can replace cash payment, such as hongbao (cash payment) and bank cards. The weak signal and latent signal, which appear less often than other two signals, includes the keywords related to promotion events or changes in service regulations. Its result shows that the mobile payment services greatly have changed user's daily life beyond providing convenience. Furthermore, it shows that, in the Chinese market, in which card payment is not common, the mobile payment services have the great potential to completely replace cash payment.

• Journal of Environmental Impact Assessment
• /
• v.32 no.3
• /
• pp.187-194
• /
• 2023

This study identified how users of Gwanghwamun Square perceive the space and derived the spatial attributes of Gwanghwamun Square. There are four spatial attributes of Gwanghwamun Square: preservation of the historical environment, beauty of the surrounding landscape, suitability as a resting place, and activation of recreation. The first attribute, preservation of the historical environment, refers to the spaces that reflect the unique characteristics of Gwanghwamun Square and resonate with culture, including the Blue House, Bukaksan Mountain, Gyeongbok Palace, Yukjo Street, King Sejong, and Yi Sun-sin. The second attribute, beauty of the surrounding landscape, is related to the provision of abundant greenery and natural environment without disturbing the surrounding landscape, and includes landscape, sky, and greenery. The third attribute, suitability as a resting place, refers to various landscape facilities and services to enhance visitor comfort, including tables, chairs, shade, planters, rest areas, and fountains. Finally, recreational activation. This is the provision of various experiences, including exhibitions, performances, experiences, and sightseeing. Utilizing the attributes of Gwanghwamun Plaza derived from this study, it will provide important implications for the reconstruction of Gwanghwamun Plaza if future studies on valuation and estimation of Gwanghwamun Plaza are conducted to verify the differences in preferences by type.

• Journal of the Korean Regional Science Association
• /
• v.39 no.4
• /
• pp.91-110
• /
• 2023

The purpose of this study is to explore urban issues that have arisen in the urban growth process of the 1st New Town for about 34 years since its construction through newspaper articles. For this purpose, newspaper articles related to the 1st New Town were collected using web crawling, and content analysis was conducted based on text mining. The main findings of the study are as follows. First, in the early stages of the construction of the 1st New Town, issues were diverse in the following six sectors: living service facilities, real estate, transportation, urban development and maintenance, safety, and housing supply, but gradually narrowed down to those of real estate and urban development and maintenance. Second, during the new town construction and urban stabilization stages, the network structure centered on 'Seoul' was maintained, which can be explained by the fact that the 1st New Town was geographically located on the outskirts of Seoul, and many articles compared the issues to Seoul. Third, the issue of urban aging appeared from the 10th year after construction, and the discussion on urban reorganization due to urban aging began in earnest from the 30th year after construction. The significance of the study is that it explored the urban issues that occurred throughout the urban growth process of the 1st New Town, and can be used as a basis for preparing a plan to reorganize the 1st New Town.

• Information Systems Review
• /
• v.22 no.2
• /
• pp.167-199
• /
• 2020

The ICT-based curation as a series of experiences with the mobile exhibition-guide applications or guide programs in art galleries helps visitors fully immersed in the exhibition and allows them to have more informative and convenient guide experience at art galleries. This study aims to verify how the factors of ICT-based curation affects the commitment and satisfaction of visitors at art galleries, figure out whether the visitors' commitment has effects on their satisfaction, and then finally test the impact of their commitment and satisfaction on their revisit intention. In order to validate the cause-and-effect relationships between these factors, the ICT-based curation in this paper is categorized into five factors - gamification, quality of image/video information, quality of sound/text information, contextual offer, and instant connectivity. The main results of the study are as follows. First, only the gamification has significantly positive effects on the commitment of art gallery visitors, while other two factors - the instant connectivity, and the quality of sound/text information - have significantly positive effects on the satisfaction of visitors. Second, the commitment of visitors also has significantly positive effects on their satisfaction. Third, the commitment of the visitors don't have significantly positive relationship with their intention of revisit, but the satisfaction of the visitors have significantly positive relationship with their intention of revisit.

• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.69-94
• /
• 2024

With the development of cyberspace and its increasing interaction with our daily lives, cybercrime has been steadily increasing in recent years and has become more prominent as a serious social problem. Notably, the "four major malicious cybercrimes" - cyber fraud, cyber financial crime, cyber sexual violence, and cyber gambling - have drawn significant attention. In order to minimize the damage of cybercrime, it's crucial to delve into the specifics of each crime and develop targeted prevention and intervention strategies. Yet, most existing research relies on indirect data sources like statistics, victim testimonials, and public opinion. This study seeks to uncover the characteristics and factors of cybercrime by directly interviewing suspects involved in 'copyright infringement', 'gambling' related to illicit online content, and 'pornography crime'. Through coding analysis and text mining, the study aims to offer a more in-depth understanding of cybercrime dynamics. Furthermore, by suggesting preventative and remedial measures, the research aims to equip policymakers with vital information to reduce the repercussions of this escalating digital threat.

• Journal of Korean Society of Archives and Records Management
• /
• v.12 no.2
• /
• pp.29-50
• /
• 2012

This study aims to analyze electronic records research domains and trends and to suggest future direction of electronic records research in Korea. One hundred and sixty one articles published in seven domestic journals from 1999 to 2011 were statistically analysed to find out the productivity of electronic records research. Analysis of intellectual structure using descriptor profiling and author profiling as a technique of text mining were performed with those same papers. Some proposals on the future research direction in this field were made.

• 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.