Mi-Nyeong Hwang

Ontology Construction of Technological Knowledge for R&D Trend Analysis

Researchers and scientists spend huge amount of time in analyzing the previous studies and their results. In order to timely take the advantageous position, they usually analyze various resources such as paper, patents, and Web documents on recent research issues to preoccupy newly emerging technologies. However, it is difficult to select invest-worthy research fields out of huge corpus by using the traditional information search based on keywords and bibliographic information. In this paper, we propose a method for efficient creation, storage, and utilization of semantically relevant information among technologies, products and research agents extracted from `big data` by using text mining. In order to implement the proposed method, we designed an ontology that creates technological knowledge for semantic web environment based on the relationships extracted by text mining techniques. The ontology was utilized for InSciTe Adaptive, a R&D trends analysis and forecast service which supports the search for the relevant technological knowledge.

Trend Analysis of Technical Terms Using Term Life Cycle Modeling

The trends of technical terms express the changes of particular subjects in a specific research field over time. However, the amount of academic literature and patent data is too large to be analyzed by human resources. In this paper, we propose a method that can detect and analyze the trends of terms by modeling the life cycle of the terms. The proposed method is composed of the following steps. First, the technical terms are extracted from academic literature data, and the TDVs(Term Dominance Values) of terms are computed on a periodic basis. Based on the TDVs, the life cycles of terms are modeled, and technical terms with similar temporal patterns of the life cycles are classified into the same trends class. The experiments shown in this paper is performed by exploiting the NDSL academic literature data maintained by KISTI.

Building issue-data maps to support the resolution of socio-national issues: Focusing on the issue of increase in domestic inflow of foreign infectious diseases

Owing to the development of big-data-related technology, interest on systematic methodology that determines policies has been increasing based on data in the public health field. In this study, a method is proposed to establish an issue data map required to discover main national and social issues based on the data and solve issues through cooperation with domain experts. First, main issues with socially high interest are selected through literature review and analysis on news and search trends. Next, the factors that influence these selected issues are analyzed, and specific monitoring items of each driving force are selected to investigate the related data. In addition, a map is established to interconnect researchers with considerable experience in issue domain research and policy decision organizations that have decision-making capacity to solve the issues. This study empirically shows the process of establishing an issue map on a main social issue, which is the “increase in domestic inflow of foreign infectious diseases.” Efficient policy decision making will be possible if an issue-detection system that enables constant monitoring based on this issue map is established.

Entity Resolution Approach of Data Stream Management Systems

Owing to the technological advancements in Semantic Web and sensor networks, a large amount of data has been produced in association with the open data policy. However, data stream management systems that process stream data have focused on the processing of a large amount of data with little priority on data identification, integration, and external linkage. Furthermore, entity resolution is focused mainly on static database-based technologies. In this study, a real-time stream data processing architecture that can perform the integration and entity resolution of streaming-type heterogeneous input data and interlink with external data is designed. To achieve this goal, a light adapter to integrate heterogeneous data into standard scheme and blocking technique to reduce comparison candidates are applied. The implemented data adapters shows 4 times higher throughput than open source data parsers and the entity resolution results with streaming data shows similar performance with the static data sets. The proposed streaming data entity resolution architecture is expected to form the basis of data integration research that can integrate various information sources of data efficiently, enrich internal data.

Translation of technical terminologies between English and Korean based on textual big data

A number of web applications provide completely automated machine translation services, allowing users to easily translate information of interest. However, these services still generate inaccurate results when translating technical terminologies. Therefore, we propose a new method that collects reliable pairs of English–Korean technical terms and translates the given English terminology to Korean. To collect the pairs, we utilize textual big data, such as Korean academic papers, and develop a new statistical model to determine appropriate characteristics. Our method is evaluated in terms of the reliability of English–Korean pairs and the precision of translation. We thus confirm that our method can produce highly reliable data and can positively influence the translation quality of technical terminologies. Copyright

Application of SNS for a Satisfaction Analysis of School Meals

Data from Social Networking Services (SNS) are extensively used to convey the users’ sentiments (positive or negative) and detailed opinions on issues promptly. In this paper, we use SNS data to conduct the satisfaction analysis of a school meal. We analyze approximately 15 million tweets in order to investigate students’ satisfaction level with the meals. Moreover, we divide the school meals into three categories – vegetables, meats, and seafood – and determine the satisfaction level of each category along with reasons for it by using 14 criteria.

Pathway construction and extension using natural language processing

Construction and maintenance of signaling pathway is a time-consuming and labor-intensive task. In addition, integration of various pathways is also ineffective since several markup languages are used to express pathways. To overcome these limitation, automatic pathway construction and extension with a standard format may provide a solution. The proposed approach has constructed a gold standard corpus that describes the signaling pathways, and it has been used to training and evaluating the automatic pathway construction and extension. Moreover, a standard format to express the signaling pathways has been developed and has been used to express the previous major 10 signaling pathways. An effective visualization tool has been also developed for the standardized format as well. The visualization tool can help to construct pathways and extend the current pathways using all articles in PubMed.

Application of Trend Detection of Technical Terms to Technology Opportunity Discovery

This paper proposes a new approach to trend detections for technical terms extracted from academic literature and also describes its application. Because the trends of technical terms can express the chages of particular subjects in a specific reserach field over time, it can be successfuly utilized for researchers to establish future research plan. The experiments shown in this paper is performed by exploiting the NDSL (National Discovery for Science Leaders) academic literature data maintained by KISTI. This paper also introduces how the proposed method can be applied to InSciTe, a service that supports technology opportunity discovery (TOD).