• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.1-18
• /
• 2016

Owing to the extensive use of Web media and the development of the IT industry, a large amount of data has been generated, shared, and stored. Nowadays, various types of unstructured data such as image, sound, video, and text are distributed through Web media. Therefore, many attempts have been made in recent years to discover new value through an analysis of these unstructured data. Among these types of unstructured data, text is recognized as the most representative method for users to express and share their opinions on the Web. In this sense, demand for obtaining new insights through text analysis is steadily increasing. Accordingly, text mining is increasingly being used for different purposes in various fields. In particular, issue tracking is being widely studied not only in the academic world but also in industries because it can be used to extract various issues from text such as news, (SocialNetworkServices) to analyze the trends of these issues. Conventionally, issue tracking is used to identify major issues sustained over a long period of time through topic modeling and to analyze the detailed distribution of documents involved in each issue. However, because conventional issue tracking assumes that the content composing each issue does not change throughout the entire tracking period, it cannot represent the dynamic mutation process of detailed issues that can be created, merged, divided, and deleted between these periods. Moreover, because only keywords that appear consistently throughout the entire period can be derived as issue keywords, concrete issue keywords such as "nuclear test" and "separated families" may be concealed by more general issue keywords such as "North Korea" in an analysis over a long period of time. This implies that many meaningful but short-lived issues cannot be discovered by conventional issue tracking. Note that detailed keywords are preferable to general keywords because the former can be clues for providing actionable strategies. To overcome these limitations, we performed an independent analysis on the documents of each detailed period. We generated an issue flow diagram based on the similarity of each issue between two consecutive periods. The issue transition pattern among categories was analyzed by using the category information of each document. In this study, we then applied the proposed methodology to a real case of 53,739 news articles. We derived an issue flow diagram from the articles. We then proposed the following useful application scenarios for the issue flow diagram presented in the experiment section. First, we can identify an issue that actively appears during a certain period and promptly disappears in the next period. Second, the preceding and following issues of a particular issue can be easily discovered from the issue flow diagram. This implies that our methodology can be used to discover the association between inter-period issues. Finally, an interesting pattern of one-way and two-way transitions was discovered by analyzing the transition patterns of issues through category analysis. Thus, we discovered that a pair of mutually similar categories induces two-way transitions. In contrast, one-way transitions can be recognized as an indicator that issues in a certain category tend to be influenced by other issues in another category. For practical application of the proposed methodology, high-quality word and stop word dictionaries need to be constructed. In addition, not only the number of documents but also additional meta-information such as the read counts, written time, and comments of documents should be analyzed. A rigorous performance evaluation or validation of the proposed methodology should be performed in future works.

• Knowledge Management Research
• /
• v.23 no.4
• /
• pp.315-338
• /
• 2022

In 1986, Korea established legal systems to support small and medium-sized start-ups, which becomes the main pillars of national development. The legal systems have stimulated start-up ecosystems to have more than 1 million new start-up companies founded every year during the past 30 years. To analyze the trend of Korea's start-up ecosystem, in this study, we collected 1.18 million news articles from 1991 to 2020. Then, we extracted news articles that have the keywords "start-up", "venture", and "start-up". We employed network analysis and topic modeling to analyze collected news articles. Our analysis can contribute to analyzing the government policy direction shown in the history of start-up support policy. Specifically, our analysis identifies the dynamic characteristics of government influenced by external environmental factors (e.g., society, economy, and culture). The results of our analysis suggest that the start-up ecosystems in Korea have changed and developed mainly by the government policies for corporation governance, industrial development planning, deregulation, and economic prosperity plan. Our frequency keyword analysis contributes to understanding entrepreneurial productivity attributed to activities among the networked components in industrial ecosystems. Our analyses and results provide practitioners and researchers with practical and academic implications that can help to establish dedicated support policies through forecast tasks of the economic environment surrounding the start-ups. Korean entrepreneurial productivity has been empowered by growing numbers of large companies in the mobile phone industry. The spectrum of large companies incorporates content startups, platform providers, online shopping malls, and youth-oriented start-ups. In addition, economic situational factors contribute to the growth of Korean entrepreneurial productivity the economic, which are related to the global expansions of the mobile industry, and government efforts to foster start-ups. Our research is methodologically implicative. We employ natural language processes for 30 years of media articles, which enables more rigorous analysis compared to the existing studies which only observe changes in government and policy based on a qualitative manner.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.4
• /
• pp.815-826
• /
• 1994

Skew bridges are found frequently in new bridge construction due to geographical conditions when new constructing bridges are put across the existing highways, railroads or rivers. This study is to investigate the static behaviors of the steel deck plates of skew bridges which are increasingly used in bridges due to outstanding quality of structural steels, development of welding techniques, in order to reduce dead loads and period of constructions. The static behaviours of steel deck plates are analyzed using general purpose FE code SAP90 by modeling the skewed deck plates with rigorous finite elements, as the skew angles vary. The results of finite element analysis for the behaviors of steel deck plates and concrete slabs in acute, obtuse corners and center of decks are compared and discussed as the skew angles vary from $90^{\circ}$ to $30^{\circ}$. Two types of decks are treated, as isotropic plates and orthotropic plates, respectively. From the results of finite element analysis, it is found that more moments, reactions, and deflections occur at the obtuse corners than at the center of skewed decks regardless of isotropy or orthotropy. Especially, in case of the skewed deck plates with skew angles less than 45 degrees, significantly large discrepancies for the values of those internal forces are shown between the skewed and right deck plates. This study estimates the characteristics of deck behaviors according to skew angles, and proposes limitations of skew angles and the ciritical regions of decks.

• Journal of Korean Society of Forest Science
• /
• v.102 no.1
• /
• pp.82-89
• /
• 2013

Harvest is one of the major disturbances affecting the soil carbon (C) dynamics in forests. However, researches on the long-term impact of periodic harvest on the soil C dynamics are limited since they requires rigorous control of various factors. Therefore, we adopted a modeling approach to determine the long-term impacts of harvest interval, harvest intensity and post-harvest residue management on soil C dynamics by using the Korean Forest Soil Carbon model (KFSC model). The simulation was conducted on Pinus densiflora S. et Z. stands in central Korea, and twelve harvest scenarios were tested by altering harvest intervals (50, 80, and 100-year interval), intensities (partial-cut harvest: 30% and clear-cut harvest: 100% of stand volume), and the residue managements after harvest (collection: 0% and retention: 100% of aboveground residue). We simulated the soil carbon stock for 400 years for each scenario. As a result, the soil C stocks in depth of 30 cm after 400 years range from 50.3 to 55.8 Mg C $ha^{-1}$, corresponding to 98.1 to 108.9% of the C stock at present. The soil C stock under the scenarios with residue retention was 2.5-11.0% higher than that under scenarios with residue collection. However, there was no significant impact of harvest interval and intensity on the soil C stock. The soil C dynamics depended on the dead organic matter dynamics derived from the amount of dead organic matter and growth pattern after harvest.