• 지능정보연구
• /
• 제25권3호
• /
• pp.179-200
• /
• 2019

구전(Word-of-Mouth) 활동은 오래 전부터 기업의 마케팅 과정에서 중요성을 인식하고 특히 마케팅 분야에서 많은 주목을 받아왔다. 최근에는 인터넷의 발달에 따라 온라인 뉴스, 온라인 커뮤니티 등에서 사람들이 지식과 정보를 주고 받는 방식이 다양해지면서 구전은 후기, 평점, 좋아요 등으로 입소문의 양상이 다각화되고 있다. 이러한 현상에 따라 구전에 관한 다양한 연구들이 선행되어왔으나, 이들을 종합적으로 분석한 메타 분석 연구는 부재하다. 본 연구는 학술 빅데이터를 활용해 구전 관련 연구동향을 알아내기 위해서 텍스트 마이닝 기법을 적용하여 주요 연구들을 추출하고 시기별로 연구들의 주요 쟁점을 파악하는 기법을 제안하였다. 이를 위해서 1941년부터 2018년까지 인용 데이터베이스인 Scopus에서 'Word-of-Mouth'라는 키워드로 검색되는 총 4389건의 문헌을 수집하였고, 영어 형태소 분석과 불용어 제거 등 전처리 과정을 통해 데이터를 정제하였다. 본 연구는 학문 분야의 발전 궤적을 추적하는 데 활용되는 주경로 분석기법을 적용해 구전과 관련된 핵심 연구들을 추출하여 연구동향을 거시적 관점에서 제시하였고, 단어동시출현 정보를 추출하여 키워드 간 네트워크를 구축하여 시기별로 구전과 관련된 연관어들이 어떻게 변화되었는지 살펴봄으로써 연구동향을 미시적 관점에서 제시하였다. 수집된 문헌 데이터를 기반으로 인용 네트워크를 구축하고 SPC 가중치를 적용하여 키루트 주경로를 추출한 결과 30개의 문헌으로 구성된 주경로가 추출되었고, 연관어 네트워크 분석을 통해서는 시기별로 온라인 시대, 관광 산업 등 다양한 산업군 등 산업 변화가 반영돼 시대적 변화와 더불어 발전하고 있는 학술적 영역의 변화를 확인할 수 있었다.

• Smart Structures and Systems
• /
• 제11권1호
• /
• pp.19-34
• /
• 2013

The objective of this paper is to develop on-line system parameter estimation and damage detection technique from the response measurements through using the Recursive Covariance-Driven Stochastic Subspace identification (RSSI-COV) approach. To reduce the effect of noise on the results of identification, discussion on the pre-processing of data using recursive singular spectrum analysis (rSSA) is presented to remove the noise contaminant measurements so as to enhance the stability of data analysis. Through the application of rSSA-SSI-COV to the vibration measurement of bridge during scouring experiment, the ability of the proposed algorithm was proved to be robust to the noise perturbations and offers a very good online tracking capability. The accuracy and robustness offered by rSSA-SSI-COV provides a key to obtain the evidence of imminent bridge settlement and a very stable modal frequency tracking which makes it possible for early warning. The peak values of the identified $1^{st}$ mode shape slope ratio has shown to be a good indicator for damage location, meanwhile, the drastic movements of the peak of $2^{nd}$ mode slope ratio could be used as another feature to indicate imminent pier settlement.

• 정보관리학회지
• /
• 제23권2호
• /
• pp.167-183
• /
• 2006

본 연구는 이메일에 나타난 감성정보 메타데이터 추출에 있어 자연언어처리에 기반한 방식을 적용하였다. 투자분석가와 고객 사이에 주고받은 이메일을 통하여 개인화 정보를 추출하였다. 개인화란 이용자에게 개인적으로 의미 있는 방식으로 콘텐츠를 제공함으로써 온라인 상에서 관계를 생성하고, 성장시키고, 지속시키는 것을 의미한다. 전자상거래나 온라인 상의 비즈니스 경우, 본 연구는 대량의 정보에서 개인에게 의미 있는 정보를 선별하여 개인화 서비스에 활용할 수 있도록, 이메일이나 토론게시판 게시물, 채팅기록 등의 텍스트를 자연언어처리 기법에 의하여 자동적으로 메타데이터를 추출할 수 있는 시스템을 구현하였다. 구현된 시스템은 온라인 비즈니스와 같이 커뮤니케이션이 중요하고, 상호 교환되는 메시지의 의도나 상대방의 감정을 파악하는 것이 중요한 경우에 그러한 감성정보 관련 메타데이터를 자동으로 추출하는 시도를 했다는 점에서 연구의 가치를 찾을 수 있다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• 한국언론정보학보
• /
• 제42권
• /
• pp.249-279
• /
• 2008

본 연구에서는 최근 사회적 학문적 관심사로 떠오른 댓글의 읽기 효과를 살펴보고자 하였다. 이를 위해, 피험자로 하여금 기사와 댓글을 읽게 하여 기사주제에 대한 태도가 댓글에 의해 변화하는가, 또한 이러한 태도 변화에 영향을 주는 요인들은 무엇인가 실험을 통해 알아보았다. 연구결과 기사에 첨부된 댓글을 읽는 것만으로도 피험자가 기사주제에 대한 태도변화를 일으키는 것을 발견하였다. 또한 댓글을 읽은 후 태도가 긍정적 혹은 부정적으로 변화하도록 하는 별도의 요인들이 존재함을 발견하였다. 즉 댓글에 대한 신뢰도와 주제에 대한 효능감이 높을수록 댓글을 읽은 후 태도가 부정적으로 변하였으며 정보추구 성향과 댓글 이용동기가 높을수록 사후 태도가 긍정적으로 변함이 발견되었다.

• 보건교육건강증진학회지
• /
• 제32권4호
• /
• pp.13-23
• /
• 2015

Objectives: his study was performed to examine whether a community organization strategy had been driven by core values explicit in Ottawa Charter and to give some suggestions for using values in health promotion practice in Korea. Methods: We searched literature online with key words of 'values', 'health promotion', and/or 'Ottawa Charter', etc, and reviewed published papers on design, implementation, and evaluation of Health Plus Happiness Plus Projects in Gyeongsangnam-Do, a community organization strategy. Results: Evident core values since Ottawa Charter had been holistic definition of health, empowerment, community participation, addressing the impact of broader determinants of health, reducing social inequities and injustice, and intersectoral collaboration. A community organization strategy was good at realization of most values. Some ways for value-driven health promotion practice were suggested. Conclusions: More discussion and debate on values in health promotion are needed in Korea.

• Journal of Information Science Theory and Practice
• /
• 제2권3호
• /
• pp.29-39
• /
• 2014

In recent years, several studies have proposed making use of the Twitter micro-blogging service to track various trends in online media and discussion. In this study, we specifically examine the use of Twitter to track discussions of food safety in the Korean language. Given the irregularity of keyword use in most tweets, we focus on optimistic machine-learning and feature set selection to classify collected tweets. We build the classifier model using Naive Bayes & Naive Bayes Multinomial, Support Vector Machine, and Decision Tree Algorithms, all of which show good performance. To select an optimum feature set, we construct a basic feature set as a standard for performance comparison, so that further test feature sets can be evaluated. Experiments show that precision and F-measure performance are best when using a Naive Bayes Multinomial classifier model with a test feature set defined by extracting Substantive, Predicate, Modifier, and Interjection parts of speech.

• Asia pacific journal of information systems
• /
• 제19권4호
• /
• pp.1-28
• /
• 2009

Banking industries have continuously innovated through technology-enhanced products and services. Many studies have recognized the importance of the Internet in banking industries, arguing that it has been widely adopted. Many studies published on the Internet banking in specific countries are mostly related with such issues as internet banking adoption and acceptance, security and risks of online banking system, and interface design. Several studies have been done to examine the differences and similarities between other banking channels and the Internet banking. However, to the best of our knowledge, only a limited number of studies has examined the differences and similarities between two specific countries in order to create a new customer satisfaction model. In this research, we studied the internet banking satisfaction model by comparing two countries: South Korea and Indonesia. We conducted an empirical study based on the data collected in both two countries. In this research, we found that countries which have adopted electric banking services, particularly between a country with high ICT adoption and a country with low ICT adoption, show different satisfaction trends. Based on the study results, herein we provide discussion, managerial, and practical implications.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권1호
• /
• pp.169-175
• /
• 2019

Service quality has been a point of discussion from the decades as it is important for customer satisfaction, loyalty and retention. Various models have been proposed to measure the quality in the service sector. Models are modified in accordance with context and geography to assess the quality of service better. This study aims to investigate the impact of the modified e-SERVQUAL model on the customer perception about the existing relation and potential scope of doing business with a bank which in-turn will decide the performance of the bank. Statistical data was analyzed through various tests like reliability analysis, correlation and regression analysis using SPSS 25.0. The primary data of e-SQ and performance was gathered from 721 internet banking users using 32 item questionnaire, representing 72% response rates, of four selected Islamic banks of Malaysia. E-SERQUAL was modified by adding Shariah Compliance information about banks and products for Islamic banking customers. The finding specified that efficient & reliable services, fulfillment, security/trust, and Shariah compliance information have a significant association with the performance of Islamic banks. The research is original and its implications will be helpful for Islamic banks across the world to enhance the online experience of customers, which will help them to retain the customers in the rapid changing virtual environment.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권4호
• /
• pp.45-56
• /
• 2020

Purpose The purpose of this study is to present the direction of efficient e-learning education through the importance and satisfaction survey of learners of non-face-to-face video lectures. Therefore, by grasping the degree of satisfaction of the importance ratio through the IPA analysis method, we try to present improvement measures for insufficient education methods. Design/methodology/approach For IPA analysis, we conducted an online survey of four universities and analyzed 154 samples. The analysis method used SPSS, and through the wordcloud analysis method of R, the suggestions for the non-face-to-face lecture method felt by learners were analyzed to derive implications for improving the quality of education. Findings As a result of the overall satisfaction survey for the entire non-face-to-face class, the factors with the greatest dissatisfaction are listed as follows. Complaints about the adequacy of learning materials and activities (quiz, discussion, assignments, etc.), Complaints about how to use the produced content, and complaints about announcements about class management (lecture schedule, lecture method) were identified in order. The factors of dissatisfaction were clear in the non-face-to-face class where interactive communication was impossible or insufficient. In addition to the lack of quick Q&A, there seems to have been a phenomenon of some neglect.