• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.615-643
• /
• 2019

Now is the time for IS scholars to demonstrate the added value of academic theory through its integration with text mining, clearly outline how to implement this for text mining experts outside of the academic field, and move towards establishing this integration as a standard practice. Therefore, in this study we develop a systematic theory-based text-mining framework (TTMF), and illustrate the use and benefits of TTMF by conducting a text-mining project in an actual business case evaluating and improving hotel service quality using a large volume of actual user-generated reviews. A total of 61,304 sentences extracted from actual customer reviews were successfully allocated to SERVQUAL dimensions, and the pragmatic validity of our model was tested by the OLS regression analysis results between the sentiment scores of each SERVQUAL dimension and customer satisfaction (star rates), and showed significant relationships. As a post-hoc analysis, the results of the co-occurrence analysis to define the root causes of positive and negative service quality perceptions and provide action plans to implement improvements were reported.

• 디지털융복합연구
• /
• 제10권5호
• /
• pp.67-78
• /
• 2012

최근 온라인 자동차보험에 대한 고객의 관심이 급증하고 있다. 그 이유는 경제성 측면에서 온라인 자동차보험이 소비자들에게 유용성을 제공해주기 때문이다. 오프라인에서 판매하는 자동차보험은 서비스 상품으로 온라인에서 판매하는 자동차보험 상품에 비해 상대적으로 높은 가격을 형성하고 있다. 이러한 특징에 힘입어 가격이 저렴한 온라인 자동차보험은 소비자들에게 큰 인기를 얻고 있다. 그렇기 때문에 소비자들은 온라인 자동차보험 상품 가격에 많은 관심을 가지고 있고, 자동차보험 상품 구입에 신중한 선택을 하고 있다. 본 연구에서는 소비자들이 온라인 자동차보험에 대해 느끼는 인지된 이익과 가격 수용성을 중심으로 $2{\times}2$ 매트릭스로 구성해 온라인 자동차보험 고객군을 온라인 수용형, 경제성 추구형, 편리 추구형, 신중 접근형으로 구분하였다. 이에 따라 본 연구에서는 온라인 자동차보험 웹사이트의 인지된 이용 용이성, 유용성, 태도, 구매의도에 사이의 관계를 분석하였다. 본 연구결과는 온라인에서 자동차보험 상품을 판매하는 기업들에게 소비자의 온라인 자동차보험 구매의도를 강화하기 위한 고객관계관리 전략 수립에 있어 유용한 시사점을 제공해 줄 것이다.

• 한국정보통신학회논문지
• /
• 제19권4호
• /
• pp.780-786
• /
• 2015

SNS 등과 같은 소셜 미디어는 실시간으로 자발적인 고객의 의견들을 대거 포함하고 있어 최근 기업들은 효율적인 경영을 위해 소셜 미디어상의 빅 데이터를 분석하는 시스템을 이용하여 고객피드백에 관한 정보를 수집하고 분석하고 있다. 그러나 온라인 사이트에서 수집한 데이터는 띄어쓰기와 철자 오류가 많아 기존의 형태소 분석기로는 정확한 분석을 할 수 없다. 또한 온라인 상의 문장은 짧다는 특징이 있어 상호 정보량, 카이제곱 통계량 등과 같은 기존의 의미 선택 방법을 이용하게 되면 문장 내 선택 할 수 있는 의미의 부재로 인해 정확한 감성 분류를 할 수 없다는 문제점이 있다. 이러한 문제점들을 해결하기 위해서 본 논문에서는 초/중성 및 어절 패턴 사전을 이용해서 보정할 수 있는 모듈과 문장 내 품사의 우선순위를 이용한 의미 선택 방법을 제안한다. 이러한 방법으로 형태소 분석기에서 추출된 품사 정보를 기반으로 용언과 체언을 분리해서 분석 해당 품사에 종속적인 속성 DB 구축 한 후 학습에 의해 누적된 속성 DB를 사용하여 보다 정확한 긍/부정 감성을 추출한다.

• 패션비즈니스
• /
• 제22권3호
• /
• pp.122-142
• /
• 2018

In the virtual fitting system, the use of a 3D avatar is not a simple garment model, but it should be able to reproduce the size and shape of the customer using a fitting system. Although various virtual fitting systems have their own 3D avatar sizing systems and provide 3D avatars that match the size of the customer, there are limitations in realizing the actual body shape in actual use by the consumer. The purpose of this study is to realize a 3D avatar with excellent size and conformity for customer use. Therefore, this study aims to provide basic data for the formation of a 3D standard avatar of Korean women aged in their 20's, by comparing and analyzing the degree of the consumer user friendly system change of a body type, and the consumer's ability in selecting a consumer representative body type. Based on the survey data of 'Size Korea' conducted from 2004 to 2015 at three times, we examined the change of body shape over 10 years. Then, based on the results of 6th and 7th data, 4 factors of the concurrent body shape change of women of the consumer demographic studied were selected through the use of a factor analysis. Following this analysis, the 4 extracted factors were clustered again and finally released 7 representative body types, which were obtained based on height and weight. The size of each representative figure is derived by the use of a regression analysis, and it is used as a basic data for 3D avatar formation of the virtual fitting system.

• 한국콘텐츠학회논문지
• /
• 제18권6호
• /
• pp.564-573
• /
• 2018

최근 들어 기업의 외부 환경은 글로벌 경쟁, 원가 절감과 이윤 확보에 대한 압박 및 신기술의 급격한 발전 등에 의해 매우 급속하게 변화하고 있다. 특히, 고객 요구 사항의 빈번한 변화는 제조 기업에게 심각한 도전이 되고 있다. 이러한 도전에 대응하기 위해서는, 고객 서비스 향상과 운영 효율성 제고를 위해 여러 관리 기능 중에서 생산계획 기능이 우선적으로 정립되어야 한다. 생산계획은 전체 공급망 관리 중에서 생산 프로세스에서의 단기적 의사결정을 다루며, 그 역할은 고객 주문과 제한된 자원 사이에서 균형을 찾는 것이다. 본 논문의 목적은 공급망 관리 관점에서 생산계획의 기능성과 시스템 아키텍처를 분석하고, 이를 기반으로 생산계획 솔루션들 간의 비교를 가능케 하기 위한 분류 프레임워크를 제시하는 것이다.

• 산경연구논집
• /
• 제10권7호
• /
• pp.83-89
• /
• 2019

Purpose - It is a very important issue for the Korean tourism industry to increase tourism revenue by attracting foreign tourists. Although Japanese tourists have been an important part of the Korean tourism industry for a long time, the level of tourist satisfaction including accommodation has been at the worst compared to other foreign visitors, which strongly requires concrete solutions. Therefore, this study focuses on improving the satisfaction level of Japanese visitors in the use of accommodation, and find out the influence of the managerial response. Research design, data, and methodology - In this study, customer review and managerial response of hotels in Seoul were collected from "Rakuten Travel" which is the most representative online travel agency in Japan. As a result of collecting data from 2016 to 2018, 6,190 customer reviews and 1,241 managerial responses from 120 hotels were used for analysis. In addition, information on the properties of 120 hotels, such as the number of rooms, classification, types of hotel facilities, types of room facilities, accessibility and prices, were collected. To test the hypotheses, moderated multiple regression analysis was conducted with SPSS 22.0. Results - It was found that only 25 sites, 20.8% of the total 120 sites, were implementing managerial response and average response rate was 66.42% among them. As a result of examining the main effects of the hotel attributes on the ratings, accessibility and price are confirmed as effective variables. We also found that the response rate has a significant moderate effect in both the accessibility and price. In other words, there was a significant difference in the influence of accessibility and price on the ratings depending on the response rate. Also, it was confirmed that the response rate is not a pure moderator variable but a quasi moderator variable. Overall, the evidences partially supported the hypothesis. Conclusion - It was possible to provide important suggestions to the hotel managers who were concerned about managing tourist satisfaction with accessibility problems. It was found that the accessibility problem could be overcome by increasing the response rate. It was also confirmed that high ratings can be more effectively achieved for high priced hotels by increasing the response rate.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 추계학술대회 논문집 전력기술부문
• /
• pp.122-124
• /
• 2003

In recent, the various electric & electronic machines are newly developed everyday and the electricity supply system & environment on the process from generation to consumption of electricity also is being changed. In other words, both supplier and consumer of electricity are required to be responsible for their interruption costs. So, it is very important and meaningful work for evaluating the interruption costs in quantitative. Additionally, since the restructuring of electric industry is on going in world wide, after restructuring, most of all electric utilities and consumer have to consider the supply reliability and quality as a important element of the calculating the related costs and contract because it takes costs to keep the supply reliability and quality highly. Especially, the interruption or the supply reliability will have influence on the bilateral contract between supplier and customer as a key point to determine the once in competitive electric market. Therefore, it has very important moaning to calculate the interruption costs in the present that it is prepared to open the competitive electric market. In this paper, international standards, i.e. IEC, IEEE, are applied to the analysis on the interruption costs used in the questionnaires which are newly designed including short duration interruption by the authors instead of traditional interruption criteria. Firstly, using the questionnaires, the authors got related data from industries according to the standard industry classification which are being used in electric utility and other national statistics in Korea. However, analysis results are hard to say typical value because of the not so many samples. So, the authors are going to survey and focus on not all kinds of industry but a few kinds of them that their facilities are effected or stop by short duration interruptions, so there are large economical damages. Finally, the authors hope to find the reliable and meaningful model in interruption costs of industrial customer.

• 지능정보연구
• /
• 제11권2호
• /
• pp.175-195
• /
• 2005

사례기반추론(case-based reasoning)은 사례간 유사도를 평가하여 유사한 이웃사례를 찾아내고, 이웃사례의 결과를 이용하여 새로운 사례에 대한 예측결과를 생성하는 전통적인 인공지능기법 중 하나다. 이러한 사례기반추론이 최근 적용이 쉽고 간단하다는 장점과 모형의 갱신이 실시간으로 이루어진다는 점 등으로 인해, 온라인 환경에서의 고객관계관리를 위한 도구로 학계와 실무에서 주목을 받고 있다 하지만, 전통적인 사례기반추론의 경우, 타 인공지능기법에 비해 정확도가 상대적으로 크게 떨어진다는 점이 종종 문제점으로 제기되어 왔다. 이에, 본 연구에서는 사례기반추론의 성과를 획기적으로 개선하기 위한 방법으로 유전자 알고리즘을 활용한 사례기반추론의 동시 최적화 모형을 제안하고자 한다. 본 연구가 제안하는 모형에서는 기존 연구에서 사례기반추론의 성과에 중대한 영향을 미치는 요소들로 제시된 바 있는 사례 특징변수의 상대적 가중치 선정(feature weighting)과 참조사례 선정(instance selection)을 유전자 알고리즘을 이용해 최적화함으로서, 사례간 유사도를 보다 정밀하게 도출하는 동시에 추론의 결과를 왜곡할 수 있는 오류사례의 영향을 최소화하고자 하였다. 제안모형의 유용성을 검증하기 위해, 본 연구에서는 국내 한 전문 인터넷 쇼핑몰의 구매예측모형 구축사례에 제안모형을 적용하여 그 성과를 살펴보았다. 그 결과, 제안모형이 지금까지 기존 연구에서 제안된 다른 사례기반추론 개선모형들은 물론, 로지스틱 회귀분석(LOGIT), 다중판별분석(MDA), 인공신경망(ANN), SVM 등 다른 인공지능 기법들에 비해서도 상대적으로 우수한 성과를 도출할 수 있음을 확인할 수 있었다.

• 한국IT서비스학회지
• /
• 제19권6호
• /
• pp.1-13
• /
• 2020

Recently, 80% of big data consists of unstructured text data. In particular, various types of documents are stored in the form of large-scale unstructured documents through social network services (SNS), blogs, news, etc., and the importance of unstructured data is highlighted. As the possibility of using unstructured data increases, various analysis techniques such as text mining have recently appeared. Therefore, in this study, topic modeling technique was applied to the Korea Highway Corporation's voice of customer (VOC) data that includes customer opinions and complaints. Currently, VOC data is divided into the business areas of Korea Expressway Corporation. However, the classified categories are often not accurate, and the ambiguous ones are classified as "other". Therefore, in order to use VOC data for efficient service improvement and the like, a more systematic and efficient classification method of VOC data is required. To this end, this study proposed two approaches, including method using only the latent dirichlet allocation (LDA), the most representative topic modeling technique, and a new method combining the LDA and the word embedding technique, Word2vec. As a result, it was confirmed that the categories of VOC data are relatively well classified when using the new method. Through these results, it is judged that it will be possible to derive the implications of the Korea Expressway Corporation and utilize it for service improvement.

• Asia pacific journal of information systems
• /
• 제22권4호
• /
• pp.125-149
• /
• 2012

As the smart phone is propagating rapidly, the importance of mobile advertisement has also grown. One of the main characteristics of the Internet and smart phone advertising is that they can deliver personalized advertisements to each customer. The smart phone enables the identification of additional personalized information such as the customer's location and the accessibility to the site at any place any time. As the Internet platform becomes richer, firms that offer the ad services via the wired PC Internet and wireless smart phone are seeking various types of personalized ads. However, their service platform and Information and Communication Technology (ICT) platform should be suitable to the characteristics of personalized ads. This research explores various types of personalized ad methods and evaluates their adequacy encompassing four types of ad service platforms (such as search portal, news portal, e-mall servers, and SNS) and two types of ICT platforms (PC Internet and smart phone). To this end, we classified the personalized ads into seven types: three basic types and four composite types. The basic types of ad methods are identified by considering the current activity that the customer is engaged, the individual profile and log history, and the customer's current location or planning location. Four composite types of ad methods are constructed as the combination of these basic types. For those types of ad methods, we evaluate whether each ad method adequately maps with four types of ad service platforms and two types of ICT platforms. We proposed a metric of evaluation and demonstrated the concept with illustrative numbers. Specifically, we analyze and compare personalized ad methods in three ways. Firstly, the possibility of implementing a personalized ad method on the platform is analyzed to confirm the degree of suitability. Secondly, the value of personalized ad method is analyzed based on the customer accessibility. Lastly, expected effectiveness for each personalized ad method is computed by multiplying the possibility and the value. Through this kind of analysis, the ad service providers as well as advertising companies can evaluate what kinds of personalized ad methods and platforms are possible and suitable to maximize their ad effectiveness on the Internet and smart phone platforms.