• International Journal of Contents
• /
• 제14권2호
• /
• pp.16-23
• /
• 2018

Although there have been studies regarding the influence of customer reviews on consumer decision making at online shopping sites, research on factors affecting the perceived customer review quality for online shopping sites is limited. This study posits that sociability, which is one of the environmental factors of an online shopping site, can affect the quality of customer reviews. Sociability is a key factor in building a collaborative environment online, but studies have been limited to applying sociability to customer reviews that are the result of a collaborative environment. This study expects that sociability affects the performance of online shopping sites through the perceived information quality of customer reviews, and customers' efficacy. More specifically this study investigates the structural relationship between sociability, self-efficacy, collective efficacy, and the perceived information quality of the reviews in an online shopping context, regarding the patronage intention of customers. This study was conducted using a survey of 361 college students. The structural equation model results indicate that user perception of sociability increases self-efficacy and collective efficacy. The improved efficacy enhances the perceived information quality of reviews for online shopping sites, which increases patronage intention of customers. This study found that online shopping sites require a platform for customers to engage in social interaction to enhance their customers' loyalty and lifetime value.

• Asia pacific journal of information systems
• /
• 제25권4호
• /
• pp.763-783
• /
• 2015

Online customer reviews (i.e., electronic word-of-mouth) has gained considerable interest over the past years. However, a knowledge gap exists in explaining the mechanisms among the factors that determine the product sales in online retailing environment. To fill the gap, this study adopts a principal-agent perspective to investigate the effect of customer reviews and customer incentives on product sales in online retail stores. Two customer review factors (i.e., average review ratings and the number of reviews) and two customer incentive factors (i.e., price discounts and special shipping offers) are used to predict product sales in regression analysis. The sales ranking data collected from the video game titles at Amazon.com are used to analyze the direct effects of the four factors and the interaction effects between customer review and customer incentive factors to product sales. Result reveals that most relationships exist as hypothesized. The findings support both the direct and interaction effects of customer reviews and incentive factors on product sales. Based on the findings, discussions are provided with regard to the academic and practical contributions.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.85-97
• /
• 2021

Online consumer activities have increased considerably since the COVID-19 outbreak. For the products and services which have an impact on everyday life, online reviews and recommendations can play a significant role in consumer decision-making processes. Thus, to better serve their customers, online firms are required to build online-centric marketing strategies. Especially, it is essential to define core value of customers based on the online customer reviews and to propose these values to their customers. This study discovers specific perceived values of customers in regard to a certain product and service, using online customer reviews and proposes a customer value proposition methodology which enables online firms to develop more effective marketing strategies. In order to discover customers value, the methodology employs a text-mining technology, which combines a sentiment analysis and topic modeling. By the methodology, customer emotions and value factors can be more clearly defined. It is expected that online firms can better identify value elements of their respective customers, provide appropriate value propositions, and thus gain sustainable competitive advantage.

• 지능정보연구
• /
• 제17권3호
• /
• pp.115-130
• /
• 2011

온라인 스토어들은 다양한 방식으로 사용자들에게 신뢰감을 가져다 줄 수 있는 요인들을 제공하려고 한다. 대표적인 방식이 고객이 좋아할 만한 제품의 추천과 고객제품리뷰의 제공이다. 각각의 제공을 통해 신뢰의 선행요인이 되는 사회적 실재감을 향상시킬 수 있다는 연구들이 있어왔다. 따라서 본 연구에서는 추천 상황에 따른 사회적 실재감에 미치는 영향과 추천 상황과 제품군의 유형, 고객제품리뷰의 제공여부에 따라 사회적 실재감의 증가에 미치는 영향을 실험을 통해 분석하였다. 개인화 추천을 통해 사회적 실재감을 증대시킬 수 있었으며, 쾌락재에서는 고객제품리뷰의 제공을 통해 어떤 추천 상황에서든 사회적 실재감이 증대되나 유의한 차이를 보이지는 않았다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권9호
• /
• pp.259-266
• /
• 2020

본 논문에서는 온라인 고객 리뷰를 활용하여 건강 보조제, 화장품 등 현재의 상태를 개선하기 위해 사용되는 제품을 대상으로 그 효과를 알아보기 위한 제품 효과 분석 기법을 제시하였다. 제안하는 제품 효과 분석 기법은 블로그 포스팅에 존재하는 광고를 자동 제거하고, 효과 분석을 위한 증상, 효과, 증가, 및 감소로 이루어진 단어 사전을 구축하며, 제안하는 알고리즘을 통해 제품의 효과를 측정한다. 제품 효과 분석 기법을 검증하기 위해 정답 레이블이 존재하는 네이버 쇼핑 리뷰 데이터셋을 대상으로 성능평가를 실시하였으며, 전통적인 긍부정 사전과 RNN 모델과 성능을 비교하였다. 실험 결과, 본 논문에서 제안하는 효과 분석 기법이 다른 두가지 방법보다 정확도가 뛰어남을 보여주었다. 또한, 아토피 피부염, 여드름 치료제에 제안하는 기법을 적용하여 소셜 미디어에 나타난 효과적인 치료법을 소개하였다. 본 논문에서 제시한 알고리즘은 블로그를 포함한 여러 매체의 리뷰로부터 제품의 효과를 점수화할 수 있으므로 다양한 제품군과 소셜 미디어에 적용될 수 있을 것으로 보인다.

• Asia pacific journal of information systems
• /
• 제26권3호
• /
• pp.449-476
• /
• 2016

This study examines how an initially perceived product value affects consumer's purchase intention after reading online reviews with various tones. The study proposes that associations among initially perceived overall product value, degree of confirmation resulting from reading the reviews, and final purchase intention differ across review tones such that 1) when the tone is favorable, the effect of an initially perceived product value is stronger than when the tone is critical, and 2) when the tone is extreme, the effect of confirmation is stronger than when the tone is moderate. The survey was conducted with 276 online shopping mall users in Korea, and most of the hypotheses were supported. This study asserts that the effects of online reviews should be considered together with customer's level of expectation formed prior to reading online reviews, which resulted from extensive search and screening processes that the customer went through before reading online reviews.

• 한국IT서비스학회지
• /
• 제14권4호
• /
• pp.159-169
• /
• 2015

Customer reviews are one of the important sources for purchase decision makings in online stores. Online stores have tried to provide useful reviews in product pages to customers. To assess the usefulness of customer reviews before other users have voted enough on the reviews, diverse aspects of reviews were utilized in prevous studies. Style and semantic information were utilized in many studies. This study aims to test diverse alogrithms and datasets for identifying a proper classification method and threshold to classify useful reviews. In particular, most researches utilized ratio type helpfulness index as Amazon.com used. However, there is another type of usefulness index utilized in TripAdviser.com or Yelp.com, count type helpfulness index. There was no proper threshold to classify useful reviews yet for count type helpfulness index. This study used reivews and their usefulness votes on restaurnats from Yelp.com to devise diverse datasets and applied text mining approaches to classify useful reviews. Random Forest, SVM, and GLMNET showed the greater values of accuracy than other approaches.

• 한국IT서비스학회지
• /
• 제17권2호
• /
• pp.165-177
• /
• 2018

Recently, online commerces are becoming more common due to factors such as mobile technology development and smart device dissemination, and online review has a big influence on potential buyer's purchase decision. This study presents a set of analytical methodologies for understanding the meaning of customer reviews of products in online transaction. Using techniques currently developed in deep learning are implemented Hierarchical Attention Network for analyze meaning in online reviews. By using these techniques, we could solve time consuming pre-data analysis time problem and multiple topic problems. To this end, this study analyzes customer reviews of laptops sold in domestic online shopping malls. Our result successfully demonstrates over 90% classification accuracy. Therefore, this study classified the unstructured text data in the semantic analysis and confirmed the practical application possibility of the review analysis process.

• 유통과학연구
• /
• 제17권5호
• /
• pp.85-94
• /
• 2019

Purpose - The purpose of this study is to analyze the impact of customer's communication on sales performance in the online market. Research design, data, and methodology - This study uses linear regression analysis to examine the effects of product review characteristics which are the result of customer's communication, on sales performance by using product reviews of online marketplace Amazon. Result - The increase in the number of product reviews positively affected sales performance. An increase in extreme opinions in the product review has a positive effect on sales performance. The product review length has a negative effect on sales performance. Conclusions - This study has shown the online marketplace customers' communication can influence sales performance using product review big data. This study contributed to the theoretical completeness by analyzing all the products of the book category in Amazon online market. This research will complement the theories regard to the customer behavior affecting sales performance. We expect the empirical analysis result will provide empirical help to sellers, online marketplace operators, and customers. In particular, the number of letters in the product may negatively affect sales performance, so sellers need to consider this effect carefully when exposing product reviews.

• 한국콘텐츠학회논문지
• /
• 제9권8호
• /
• pp.272-284
• /
• 2009

본 논문에서는 텍스트마이닝 기술을 이용하여 온라인 고객리뷰를 분석하기 위한 방법론을 제안하였다. 온라인 고객리뷰를 보다 효율적이고 효과적으로 분석할 수 있도록 시장세분화의 개념을 도입하였다. 즉, 제안한 방법론은 텍스트마이닝 분야에서 시장세분화의 개념에 부응하는 기술들이라 할 수 있는 범주화와 정보추출 기법의 사용을 포함한다. 특히, 통계적으로 보다 견고한 분석결과를 도출할 수 있도록 전통적 통계분석기법중의 하나인 교차분석방법을 제안하는 방법론에 포함하였다. 제안한 방법론의 타당성을 확인하기 위하여 양질의 온라인 고객리뷰가 있는 웹사이트를 선정하여 실제로 온라인 고객리뷰들을 분석하여 보았다.