• 대한소아치과학회지
• /
• 제33권4호
• /
• pp.728-737
• /
• 2006

연구 목적은 근거중심 소아치과학 연구의 기본이 되는 체계적 고찰의 방법과, 체계적 고찰의 통계적 방법이 되는 메타분석에 대하여 소개하는 것이었다. 연구 자료로서 Cochrane Handbook for Systematic Reviews of Interventions 등을 참고하였다. 체계적 고찰의 첫 단계이자 가장 중요한 것은 잘 규정된, 초점이 또렷한 질문을 만드는 것이고, 다음에 자료의 검색을 하고 선정된 자료에 대한 타당도 평가를 한 후, 변수의 종류에 따라 자료를 분석하고 결과를 해석하여 결론을 도출한다. 자료 분석의 통계학적 방법인 메타분석의 필요성과 원리 및 변수의 종류에 따른 자료별 메타분석 방법에 대하여 요약 기술하였다.

• 한국IT서비스학회지
• /
• 제16권3호
• /
• pp.113-125
• /
• 2017

Customers have been affected by others' opinions when they make a purchase. Thanks to the development of technologies, people are sharing their experiences such as reviews or ratings through online or social network services, However, although ratings are intuitive information for others, many reviews include only texts without ratings. Also, because of huge amount of reviews, customers and companies can't read all of them so they are hard to evaluate to a product without ratings. Therefore, in this study, we propose a methodology to predict ratings based on reviews for a product. In a methodology, we first estimate the topic-review matrix using the Latent Dirichlet Allocation technic which is widely used in topic modeling. Next, we predict ratings based on the topic-review matrix using the artificial neural network model which is based on the backpropagation algorithm. Through experiments with actual reviews, we find that our methodology can predict ratings based on customers' reviews. And our methodology performs better with reviews which include certain opinions. As a result, our study can be used for customers and companies that want to know exactly a product with ratings. Moreover, we hope that our study leads to the implementation of future studies that combine machine learning and topic modeling.

• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.75-90
• /
• 2022

From the past to the present, reviews have had much influence on consumers' purchasing decisions. Companies are making various efforts, such as introducing a review incentive system to increase the number of reviews. Recently, as various types of reviews can be left, reviews have begun to be recognized as interesting new content. This way, reviews have become essential in creating loyal customers. Therefore, research and utilization of reviews are being actively conducted. Some studies analyze reviews to discover customers' needs, studies that upgrade recommendation systems using reviews, and studies that analyze consumers' emotions and attitudes through reviews. However, research that predicts the future using reviews is insufficient. This study used a dataset consisting of two reviews written in pairs with differences in usage periods. In this study, the direction of consumer product evaluation is predicted using KoBERT, which shows excellent performance in Text Deep Learning. We used 7,233 reviews collected to demonstrate the excellence of the proposed model. As a result, the proposed model using the review text and the star rating showed excellent performance compared to the baseline that follows the majority voting.

• 복식문화연구
• /
• 제25권6호
• /
• pp.831-846
• /
• 2017

Considering that the effectiveness of ads varies according to the credibility of consumers, it is necessary to establish data regarding consumer credibility in relation to online reviews. To conduct a successful study on the marketing strategies of online reviews, it is also necessary to analyze the relationship between credibility and the various factors that influence the purchase intentions of consumers. Therefore, this study attempted to examine the relationship between consumer trust of on-line reviews, brand preference, ads credibility, and purchase intentions in relation to cosmetics. The study was conducted through a normative descriptive survey method using stimuli and a self-administered questionnaire. Analysis of the structural equation model was conducted for the data analysis. The results revealed that consumer reliance on online reviews of cosmetics influences brand preference, credibility of brand ads and purchase intentions. The results also revealed that consumers' on-line reviews, brand preference, and trust of brand ads are important factors for increasing the purchase intentions. The mediation effect of brand preference and brands' ads credibility were found in the process where on-line reviews exercise an influence on the purchase intentions. It was also found that brand preference has a stronger influence on purchase intention than credibility of brand ads. It was discovered that the credibility of on-line reviews directly influences purchase intentions more than indirectly influences. Considering the results of this study, programs that encourage customers to post on-line reviews, and strategies to promote brand preference by targeting groups that exhibit high trust in online reviews would be recommended.

• 스마트미디어저널
• /
• 제9권2호
• /
• pp.69-77
• /
• 2020

지상파에 한정되어 방영되었던 과거와는 달리 현재는 케이블 채널과 인터넷 웹에서도 수많은 드라마가 방영되고 있다. 드라마를 보고난 후 시청자들은 리뷰를 통해 적극적으로 자신의 의견을 표현하고 이러한 리뷰의 분석에 관련된 연구들이 활발하게 진행되고 있다. 드라마의 특성상 장르가 뚜렷하지 않고 시청자의 다양한 연령층으로 인해 다른 시청자들의 리뷰와 평가는 어떤 드라마를 볼 것인지 결정하는데 도움이 된다. 하지만 많은 리뷰를 시청자가 일일이 확인하고 분석하는 것은 어렵기 때문에 자동으로 분석하기위한 데이터 분석 기법이 필요하다. 이에 본 논문에서는 드라마 선택에 중요한 영향을 미치는 리뷰의 토픽을 분류하고 단어의 의미 유사도에 따라 의미적 토픽으로 재분류한다. 그리고 리뷰를 의미적 토픽에 따른 문장으로 분류한 다음 감성단어를 통해 감성을 분석하는 모델을 제안한다.

• 한국유통학회지:유통연구
• /
• 제17권3호
• /
• pp.25-57
• /
• 2012

본 연구에서는 인터넷 점포에서 의류상품 구매후기를 작성하는 동기의 유형을 규명하는 한편 작성 동기 유형에 따라 인터넷 점포 고객들을 범주화하고, 각 집단의 작성행동, 인터넷 구매 행동, 인구사회적 특성의 차이를 규명하였다. 초점집단 면접과 온라인 서베이를 통해 연구되었으며, 정량적 연구에서는 의류상품 구매후기를 읽은 경험과 작성한 경험이 많은 국내 인터넷 점포 여성 고객 252명을 대상으로 자료가 수집되었다. 연구결과, 인터넷 점포에서 구매후기를 작성하는 동기 유형은 이타적 정보 공유, 불만해소 및 보복, 경제적 보상 추구, 상품 개발 지원, 감동 표현으로 나타났다. 특히, 작성행동에 대한 영향력이 큰 동기는 이타적 정보 공유 동기와 경제적 보상 추구 동기였다. 인터넷 점포 고객은 작성동기 유형에 따라 소비자 옹호 집단, 이익 추구 집단, 중도적 집단으로 범주화되었으며, 세 집단은 구매후기 작성행동, 인터넷 구매빈도, 인구사회적 요인들에서 차별적 특성을 보였다. 소비자 옹호 집단과 이익 추구 집단을 대상으로 인터넷 점포 구전 채널 관리 방안이 제시되었다.

• 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.

• 한국컴퓨터정보학회논문지
• /
• 제26권8호
• /
• pp.39-46
• /
• 2021

프랜차이즈 스토어를 대상으로 소셜 빅데이터 분석을 수행할 경우, 프랜차이즈에 속한 여러 분점의 리뷰들이 함께 수집될 수 있어 분석 결과가 왜곡될 수 있다. 이 경우 분석 정확도를 높이기 위해서는 분석 대상이 아닌 타 분점의 리뷰들을 적절히 필터링할 수 있어야 한다. 본 논문에서는 프랜차이즈 스토어들의 특성을 반영한 소셜 빅데이터 분석 방법을 제안한다. 제안 방법은 검색어 설정 방법과 리뷰 필터링 방법을 포함한다. 검색어 설정을 위해, 소상공인진흥공단에서 제공하는 공공데이터를 기반으로 검색에 필요한 지역명을 추출한다. 그리고 리뷰 필터링을 위해, 네이버 및 카카오 등에서 제공하는 검색 API를 이용하여 프랜차이즈 분점 정보를 알아내고, 분석 대상이 아닌 타 분점의 리뷰들을 필터링하는데 이용한다. 제안 방법의 검증을 위해 온라인에서 수집된 실제 리뷰를 대상으로 실험을 수행하였으며, 제안 방법의 리뷰 필터링 정확도는 평균 93.6%로 조사되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2137-2156
• /
• 2024

Customer reviews are the second-most reliable source of information, followed by family and friend referrals. However, there are many existing customer reviews. Some online shopping platforms address this issue by ranking customer reviews according to their usefulness. However, we propose an alternative method to rank customer reviews, given that this system is easily manipulable. This study aims to create a ranking model for reviews based on their usefulness by combining product and seller service aspects from customer reviews. This methodology consists of six primary steps: data collection and preprocessing, aspect extraction and sentiment analysis, followed by constructing a regression model using random forest regression, and the review ranking process. The results demonstrate that the ranking model with service considerations outperformed the model without service considerations. This demonstrates the model's superiority in the three tests, which include a comparison of the regression results, the aggregate helpfulness ratio, and the matching score.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권2호
• /
• pp.159-177
• /
• 2022

Purpose Online reviews are critical for sales of online shopping platforms because they provide useful information to consumers. As the eCommerce market grows rapidly, the role of online reviews is becoming more important. The purpose of this study is to analyze how online reviews written by domestic consumers affect product sales by classifying the types of products. Design/methodology/approach This study analyzed how the effects of review characteristics(reviewer reputation, reviewer exposure, review length, time, rating, image, and emotional score) on the usefulness of online reviews differ depending on the product types. Subsequently, how the impact of review attributes (review usefulness, number of reviews, ratings, and emotional scores) on product sales differs according to each product type was compared. Based on the FCB Grid model, the product type was classified into high involvement-rational, high involvement-emotional, low involvement -rational, and low involvement-emotional product types. Findings According to the analysis result, the characteristics of reviews useful to consumers were different for each product type, and the review attributes affecting product sales were also different for each product type. This study confirmed that it revealed that product characteristics are major consideration in evaluating the review usefulness and the factors affecting product sales.