• 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.

• 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.

• 유통과학연구
• /
• 제22권3호
• /
• pp.113-124
• /
• 2024

Purpose: This study is a quantitative study and analyzes the effect of evaluating the extreme and usefulness of product reviews on sales performance by using text mining techniques based on product review big data. We investigate whether the perceived helpfulness of product reviews serves as a mediating factor in the impact of product review extremity on sales performance. Research design, data and methodology: The analysis emphasizes customer interaction factors associated with both product review helpfulness and sales performance. Out of the 8.26 million Amazon product reviews in the book category collected by He & McAuley (2016), text mining using natural language processing methodology was performed on 300,000 product reviews, and the hypothesis was verified through hierarchical regression analysis. Results: The extremity of product reviews exhibited a negative impact on the evaluation of helpfulness. And the helpfulness played a mediating role between the extremity of product reviews and sales performance. Conclusion: Increased inclusion of extreme content in the product review's text correlates with a diminished evaluation of helpfulness. The evaluation of helpfulness exerts a negative mediating effect on sales performance. This study offers empirical insights for digital market distributors and sellers, contributing to the research field related to product reviews based on review ratings.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.101-109
• /
• 2023

This paper discusses the use of sentiment analysis and text summarization techniques to extract valuable information from the large volume of user-generated content such as reviews, comments, and feedback on online platforms and social media. The paper highlights the effectiveness of sentiment analysis in identifying positive and negative reviews and the importance of summarizing such text to facilitate comprehension and convey essential findings to readers. The proposed work focuses on summarizing all positive and negative reviews to enhance product quality, and the performance of the generated summaries is measured using ROUGE scores. The results show promising outcomes for the developed methods in summarizing user-generated content.

• International Journal of Computer Science & Network Security
• /
• 제23권11호
• /
• pp.83-92
• /
• 2023

The majority of product users rely on the reviews that are posted on the appropriate website. Both users and the product's manufacturer could benefit from these reviews. Daily, thousands of reviews are submitted; how is it possible to read them all? Sentiment analysis has become a critical field of research as posting reviews become more and more common. Machine learning techniques that are supervised, unsupervised, and semi-supervised have worked very hard to harvest this data. The complicated and technological area of feature engineering falls within machine learning. Using deep learning, this tedious process may be completed automatically. Numerous studies have been conducted on deep learning models like LSTM, CNN, RNN, and GRU. Each model has employed a certain type of data, such as CNN for pictures and LSTM for language translation, etc. According to experimental results utilizing a publicly accessible dataset with reviews for all of the models, both positive and negative, and CNN, the best model for the dataset was identified in comparison to the other models, with an accuracy rate of 81%.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.177-181
• /
• 2023

User reviews posted in the application market show high relevance with the satisfaction of application users and its significance has been proven from numerous studies. User reviews are also crucial data as they are essential for improving applications after its release. However, as infinite amounts of user reviews are posted per day, application developers are unable to examine every user review and address them. Simply addressing the reviews in a chronological order will not be enough for an adequate user satisfaction given the limited resources of the developers. As such, the following research suggests a systematical method of analyzing user reviews with a cost-benefit analysis, in which the benefit of each user review is quantified based on the number of positive/negative words and the cost of each user review is quantified by using function point, a technique that measures software size.