• 한국게임학회 논문지
• /
• 제18권1호
• /
• pp.105-114
• /
• 2018

고객 유형 분석에 쓰이는 다양한 데이터 분석 방법은 고객들을 위한 맞춤형 콘텐츠를 기획하고, 보다 편리한 서비스를 제공하기 위하여 고객들의 유형과 특성을 정확히 파악하는 것이 매우 중요하다. 본 논문에서는 정보의 손실을 줄이기 위한 일환으로 정보 엔트로피를 확장하여 속성의 불확실성을 이용한 k-modes 군집분석 알고리즘을 제안한다. 따라서 속성에 대한 유사도의 측정은 두 가지의 측면에서 고려되어진다. 하나는 각 분할의 중심에 대한 각 속성간의 불확실성을 측정하는 것이고, 다른 하나는 각 속성이 가지는 불확실성에 대한 확률적 분포에 대한 불확실성을 측정하는 것이다. 특히 속성내의 불확실성은 속성의 엔트로피를 확률적 정보로 변환하여 불확실성을 측정하기 때문에 최종적인 불확실성은 비확률적인 척도와 확률적인 척도에서 고려되어 진다. 여러 실험과 척도를 통하여 제안한 알고리즘의 정확도가 최적의 초기치를 기반으로 군집분석을 수행한 결과에 준수함을 보인다.

• 디지털융복합연구
• /
• 제13권9호
• /
• pp.235-242
• /
• 2015

소셜 네트워크 기술이 발달하면서 빅 데이터 서비스에 대한 관심이 증가하고 있다. 그러나, 중앙 서버가 아닌 분산 서버에 저장된 데이터를 손쉽게 검색 및 추출하기 위한 기술은 부족한 실정이다. 본 논문에서는 빅 데이터 서비스를 제공하는 컨텐츠 서버와 관리 서버에서 사용자가 원하는 정보의 처리시간을 최소화하기 위한 빅 데이터 관리 기법을 제안하다. 제안 기법은 빅 데이터의 종류, 기능, 특성에 따라 데이터를 그룹으로 분류한 후 분류된 그룹내 데이터를 속성정보와 연계하여 해쉬체인에 적용한다. 또한, 분산 서버에 저장된 데이터를 최단 시간에 추출하기 위해서 데이터 인덱스 정보(DII, Data Index Information)를 그룹화하여 데이터에 부여된 다중의 속성 정보를 분류하여 데이터의 처리 속도를 향상시킨다. 실험 결과, 클러스터 그룹 수에 따른 데이터의 평균 검색 시간은 평균 14.6% 향상되었고, 키워드 수에 따른 데이터 처리시간은 평균 13% 단축되었다.

• 품질경영학회지
• /
• 제50권4호
• /
• pp.863-876
• /
• 2022

Purpose: The purpose of this study is to propose the product quality satisfaction index based on multiple linear regression using customer reviews. Methods: The proposed framework is composed of four steps. First, we collect online reviews and divide it into insight phrases. The insight phrases are classified using product attribute dictionary and sentiment analysis is conducted. Second, the importance of attributes is calculated in consideration of both regression coefficient and frequency. Third, the positive rate is calculated concerning sentiment analysis result. Therefore, the quality satisfaction index is measured by the weighted sum of importance and positive rate in the last step. Results: We conduct a case study using 2-years(2020, 2021) of Samsung TV reviews to confirm the effectiveness of the proposed methodology. As a result, we found that Picture quality is the most crucial attribute in TV evaluation. The importance of Gaming and content has grown up as the positive rate has also increased. Therefore, the overall satisfaction of TV has increased in 2021 compared to 2020. Conclusion: The result of this study shows that the proposed index reveals the customer's mind efficiently and can be explained by the importance and positive rate of each attribute. By using the proposed index, companies are able to improve and the priority of improvement can be determined.

• 아태비즈니스연구
• /
• 제14권2호
• /
• pp.17-31
• /
• 2023

Purpose - The purpose of this study is to verify the effects of attributes of personal media content and influencers on the cognitive and emotional trust of platform users. In addition, the structural relationships among cognitive trust, emotional trust, viewing commitment, and purchase intention were examined. Design/methodology/approach - For the empirical analysis of the study, a survey was conducted on 192 consumers who have recently experienced using personal media content. The Confirmatory Factor Analysis (CFA) and the Structure Equation Model (SEM) were hired in order to analyze the survey data. Findings - Findings of this study are 1) informativeness and expertise had a significant effect on cognitive and emotional trust. However, entertainment had no significant effect on both cognitive and emotional trust; 2) interactivity had a significant effect on emotional trust, but not on cognitive trust; 3) cognitive and emotional trust had a positive effect on the viewing commitment of the content; 4)content users' viewing commitment had a positive effect on their intention to purchase recommended products. Research implications or Originality - The theoretical and practical implications were discussed through the above empirical research results, and the limitations of the study and the direction of follow-up studies were presented.

• 한국식품조리과학회지
• /
• 제27권6호
• /
• pp.773-781
• /
• 2011

Coffee beans are processed from coffee cherries by either natural, pulped natural, or washing. The aim of the present study was to evaluate the physiochemical and sensory characteristics of espresso coffees processed by different methods. The color of the washed coffee sample presented the highest value of lightness while the natural coffee sample presented the highest value of redness and yellowness. The biggest difference in brewed coffee, whether natural, pulped natural, or washed, was in the TDS content, which was higher in natural coffee and lower in washed coffee. Sensory descriptive analysis and acceptance test for espresso coffee using a 15 cm line scale were carried out by 12 trained panelists. Natural coffee had the highest cherry-like flavor and sweetness taste while washed coffee had the highest citrus flavor and acidity taste. An important attribute of espresso coffee is body, and natural coffee presented strong body while washed coffee presented a low body attribute. In conclusion, significant differences were observed among the three processing methods of green coffee. Pulped natural coffees presented intermediate physiochemical and sensory characteristics compared to washed and natural coffee. Natural coffees are appreciated for their increased body, and washed coffees are appreciated for added citrus flavors and acidity espresso coffee blends.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권1호
• /
• pp.89-110
• /
• 2018

Purpose There is much information in customer reviews, but finding key information in many texts is not easy. Business decision makers need a model to solve this problem. In this study we propose a multi-topic sentiment analysis approach using Latent Dirichlet Allocation (LDA) for user-generated contents (UGC). Design/methodology/approach In this paper, we collected a total of 104,039 hotel reviews in seven of the world's top tourist destinations from TripAdvisor (www.tripadvisor.com) and extracted 30 topics related to the hotel from all customer reviews using the LDA model. Six major dimensions (value, cleanliness, rooms, service, location, and sleep quality) were selected from the 30 extracted topics. To analyze data, we employed R language. Findings This study contributes to propose a lexicon-based sentiment analysis approach for the keywords-embedded sentences related to the six dimensions within a review. The performance of the proposed model was evaluated by comparing the sentiment analysis results of each topic with the real attribute ratings provided by the platform. The results show its outperformance, with a high ratio of accuracy and recall. Through our proposed model, it is expected to analyze the customers' sentiments over different topics for those reviews with an absence of the detailed attribute ratings.

• 문화기술의 융합
• /
• 제6권2호
• /
• pp.419-428
• /
• 2020

SNS미디어가 디지털 기술의 혜택으로 물리적인 접근성의 편리와 콘텐츠가 갖는 오락성·상호작용성 등의 새로운 미디어의 특장점으로 미디어 점유율을 높이며, 이용자들의 생활의 일부로 자리잡아가고 있다. 미디어 콘텐츠 소비자들이 기존 전통 미디어에서 SNS로 대거 이동함에 따라 마케팅 커뮤니케이션 활동도 페이스북 등 앞서가는 SNS 플랫폼에 발빠르게 적응해 가는 중이다. 본 연구는 미디어 콘텐츠의 생성과 소비 시스템이 서로 비교적 유사한 페이스북, 인스타그램, 카카오스토리, 트위터를 중심으로, 사용자들이 각각의 SNS에서 네 가지 광고속성을 어떻게 인식하는지를 비교하고, 이 속성들이 구전의도에 미치는 영향력을 확인하였다. 또 이를 통한 효과적인 SNS 운용에 대해 논의하였다.

• ETRI Journal
• /
• 제43권5호
• /
• pp.812-824
• /
• 2021

Recently, with an increase in Internet usage, users of online social networks (OSNs) have increased. Consequently, privacy leakage has become more serious. However, few studies have investigated the difference between privacy and actual behaviors. In particular, users' desire to change their privacy status is not supported by their privacy literacy. Presenting an accurate measurement of users' privacy status can cultivate the privacy literacy of users. However, the highly interactive nature of interpersonal communication on OSNs has promoted privacy to be viewed as a communal issue. As a large number of redundant users on social networks are unrelated to the user's privacy, existing algorithms are no longer applicable. To solve this problem, we propose a structural similarity measurement method suitable for the characteristics of social networks. The proposed method excludes redundant users and combines the attribute information to measure the privacy status of users. Using this approach, users can intuitively recognize their privacy status on OSNs. Experiments using real data show that our method can effectively and accurately help users improve their privacy disclosures.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.212-222
• /
• 2022

There has been a rapid increase in the use of cloud email services. As a result, email encryption has become more commonplace as concerns about cloud privacy and security grow. Nevertheless, this increase in usage is creating the challenge of how to effectively be searching and filtering the encrypted emails. They are popular technologies of solving the issue of the encrypted emails searching through searchable public key encryption. However, the problem of encrypted email filtering remains to be solved. As a new approach to finding and filtering encrypted emails in the cloud, we propose a ciphertext-based encrypted policy attribute-based encryption scheme and keyword search procedure based on hidden policy ciphertext. This feature allows the user of searching using some encrypted emails keywords in the cloud as well as allowing the emails filter-based server toward filter the content of the encrypted emails, similar to the traditional email keyword filtering service. By utilizing composite order bilinear groups, a hidden policy system has been successfully demonstrated to be secure by our dual system encryption process. Proposed system can be used with other scenarios such as searching and filtering files as an applicable method.

• 정보처리학회논문지D
• /
• 제9D권6호
• /
• pp.1009-1016
• /
• 2002

본 논문에서는 인터넷 컨텐츠 사이트에서 묵시적인 평가정보를 이용한 새로운 사례기반 추천시스템을 설계하고 구현하였다. 본 시스템은 크게 사용자 프로파일 생성 모듈, 유사도 계산 및 추천 모듈, 개인화된 메일링 모듈로 구성된다. 사용자 프로파일 생성 모듈에서는 사용자가 컨텐츠를 이용하면서 남긴 로그 기록을 이용하여 컨텐츠에 대한 개인별 선호도를 추출할 수 있는 속성내, 속성간 가중치를 제시하였다. 유사도 계산 및 추천 모듈에서는 사용자 프로파일과 새로운 컨텐츠간의 유사도를 측정하기 위한 유사도 계산식을 제시하였다. 개인화된 메일링 모듈에서는 개인별 선호도에 의해 구성된 추천 컨텐츠를 플렛폼-독립적인 XML 문서 형식으로 변환하여 발송한다. 제안된 모델에 대한 추천 효율을 검증하기 위해 평균절대오차(MAE)와 반응자작용특성(ROC) 값을 이용하여 제안한 추천 모델과 협동적 필터링 기법과 비교 실험하였다. 실험결과, 본 논문에서 제안한 모델의 추천 효율이 기존의 협동적 필터링 기법보다 우수함을 보였다.