• 한국IT서비스학회지
• /
• 제13권1호
• /
• pp.43-55
• /
• 2014

More and more people are gravitating to reading products reviews prior to making purchasing decisions. As a number of reviews that vary in usefulness are posted every day, much attention is being paid to measuring their helpfulness. The goal of this paper is to investigate firstly various determinants of the helpfulness of reviews, and intends to examine the moderating effect of product type, i.e., search or experience goods on the product sales, helpfulness and helpfulness votes of online reviews. The determinants include product data, review characteristics, and textual characteristics of reviews. The results indicate that the direct effect exists for the determinants of product sales, helpfulness, and helpfulness votes. Further, the moderating effects of product type exist for these determinants on three dependent variables. The results of study will identify helpful online review and design review sites effectively.

• Asia pacific journal of information systems
• /
• 제34권2호
• /
• pp.372-399
• /
• 2024

Online reviews play a significant role in consumer purchase decisions on e-commerce platforms. To address information overload in the context of online reviews, factors that drive review helpfulness have received considerable attention from scholars and practitioners. The purpose of this study is to explore the differential effects of discrete emotions (anger, disgust, fear, joy, sadness, and surprise) on perceived review helpfulness, drawing on cognitive appraisal theory of emotion and expectation-confirmation theory. Emotions embedded in 56,157 hotel reviews collected from TripAdvisor.com were extracted based on a transfer learning model to measure emotion variables as an alternative to dictionary-based methods adopted in previous research. We found that anger and fear have positive impacts on review helpfulness, while disgust and joy exert negative impacts. Moreover, hotel star-classification significantly moderates the relationships between several emotions (disgust, fear, and joy) and perceived review helpfulness. Our results extend the understanding of review assessment and have managerial implications for hotel managers and e-commerce vendors.

• 유통과학연구
• /
• 제18권10호
• /
• pp.65-75
• /
• 2020

Purpose: This study aims to examine how to review contents of experiential and utilitarian products (e.g., skincare products) and how to affect review helpfulness by applying natural language processing techniques. Research design, data, and methodology: This study uses 69,633 online reviews generated for the products registered at Amazon.com by 13 Korean cosmetic firms. The authors identify key topics that emerge about consumers' use of skincare products such as skin type and skin trouble, by applying bigram analysis. The review content variables are included in the review helpfulness model, including other important determinants. Results: The estimation results support the positive effect of review extremity and content on the helpfulness. In particular, the reviewer's skin type information was recognized as highly useful when presented together as a basis for high-rated reviews. Moreover, the content related to skin issues positively affects review helpfulness. Conclusions: The positive relationship between extreme reviews and helpfulness of reviews challenges the findings from prior literature. This result implies that an in-depth study of the effect of product types on review helpfulness is needed. Furthermore, a positive effect of review content on helpfulness suggests that applying big data analytics can provide meaningful customer insights in the online retail industry.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권3호
• /
• pp.133-150
• /
• 2023

Purpose This study aims to develop classification models using a decision tree algorithm to identify core keywords and rules influencing online consumer review evaluations for the robot vacuum cleaner on Amazon.com. The difference from previous studies is that we analyze core keywords that affect the evaluation results by dividing the subjects that evaluate online consumer reviews into self-evaluation (star ratings) and peer evaluation (helpfulness votes). We investigate whether the core keywords influencing star ratings and helpfulness votes vary across different products and whether there is a similarity in the core keywords related to star ratings or helpfulness votes across all products. Design/methodology/approach We used random under-sampling to balance the dataset. We progressively removed independent variables based on decreasing importance through backwards elimination to evaluate the classification model's performance. As a result, we identified classification models that best predict star ratings and helpfulness votes for each product's online consumer reviews. Findings We have identified that the core keywords influencing self-evaluation and peer evaluation vary across different products, and even for the same model or features, the core keywords are not consistent. Therefore, companies' producers and marketing managers need to analyze the core keywords of each product to highlight the advantages and prepare customized strategies that compensate for the shortcomings.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권3호
• /
• pp.203-225
• /
• 2018

Purpose This study investigated the impact of review language style (affective vs. cognitive) on review helpfulness and the moderating effects of the types of attractions in the relationships between the review language and its helpfulness. Design/methodology/approach This study investigates the impact of review language style (affective vs. cognitive) on review helpfulness and the moderating effects of the types of attractions in the relationships between the review language and its helpfulness. This study selected two hedonic and utilitarian attractions (Hedonic: Brandenburg Gate, Utilitarian: Peragamon Museum) located in Berlin. A total of 3,320 reviews was collected from TripAdvisor. We divided online reviews posted for these places into reviews with more affective language and with more cognitive language by using the LIWC. Then, we investigated the impact of language effect on review helpfulness across the attraction type. Findings The findings suggest that peers tend to judge more helpful toward cognitive language in attraction reviews regardless of attraction type. This study found that peers tend to perceive more helpful toward cognitive review in utilitarian attractions. Even though there was an interaction effect between review language and attraction type, in hedonic attractions, the influence of cognitive language was reduced, but still cognitive reviews would get more helpful votes.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권4호
• /
• pp.161-187
• /
• 2022

Purpose This study analyzed the topic of game review contents and how the characteristics of game reviews affect the reviews helpfulness. In addition, this study explore the content of game reviews according to the game's sales strategy such as early access strategy and releasing without early access. Design/methodology/approach We collected a list of 3,572 action genre games released in 2020. 58,336 online reviews were collected by random sampling 50 reviews in each games, and topic modeling was performed on those reviews. We dynamized the results of topic modeling and analyzed the effect on review helpfulness with multiple regression analysis. Findings The results of analysis indicate that the longer the review is or the shorter the time it is written, the more helpful the review is. In addition the topic with positive and negative review has a significant effect on the review helpfulness. As a result of exploratory analysis, games from early access had relatively fewer reviews of story-related topics than games that were released without early access. These findings can present direct guidelines for collecting specific opinions from customers in the game industry when releasing games.

• 지식경영연구
• /
• 제23권3호
• /
• pp.193-212
• /
• 2022

많은 연구에서 온라인 리뷰 유용성에 영향을 미치는 다양한 요인을 발견하였다. 기존 연구에서는 주로 온라인 리뷰와 관련되는 정량적(예: 평점) 및 정서적(예: 감성점수) 요인이 리뷰 유용성에 미치는 영향을 조사했다. 온라인 리뷰는 제목과 내용을 동시에 포함하고 있지만, 기존 연구는 주로 리뷰 내용에 중점을 두고 있다. 그러나 리뷰 제목을 고려하지 않고 단순히 리뷰 내용만을 고려하면 리뷰 유용성에 영향을 미치는 요인을 조사할 때 한계가 존재한다. 이에 따라 리뷰 제목과 내용을 모두 고려하는 연구가 주목받고 있지만, 대부분의 연구는 리뷰 유용성에 대한 리뷰 내용과 제목의 영향을 독립적으로 조사하였다. 이는 리뷰 제목과 내용 간의 일치성이 리뷰 유용성에 미치는 잠재적인 영향을 간과할 수 있다. 따라서 본 연구에서는 단순 노출 효과 이론을 통해 리뷰 제목과 내용 간의 텍스트 일치성이 리뷰 유용성에 미치는 영향을 확인하고, 정보 선명성, 리뷰 길이 및 정보원 신뢰성의 역할도 고려하였다. 분석 결과, 리뷰 제목과 내용 간의 텍스트 일치성은 리뷰 유용성에 부정적인 영향을 미치는 것을 확인하였다. 또한, 정보 선명성과 정보원 신뢰성은 리뷰 유용성에 대한 텍스트 일치성의 부정적인 영향을 완화한다는 것을 발견했다.

• 한국전자거래학회지
• /
• 제16권3호
• /
• pp.93-112
• /
• 2011

최근 온라인 쇼핑 활동의 증가와 함께 소비자들은 온라인상에서의 제품에 대한 리뷰를 합리적인 구매 결정을 내리기 위한 중요한 정보로 활용하고 있다. 하지만 소비자들은 많은 양의 온라인 리뷰 중 그들의 구매 결정에 유익하게 활용될 리뷰를 선택하기가 쉽지 않다. 따라서 본 연구에서는 정교화 가능성 이론(elaboration likelihood model)을 바탕으로, 유익한 온라인 소비자 리뷰를 결정하는 요인이 무엇인지 알아보고, 구매하고자 하는 제품의 가격에 따라 유익한 리뷰를 결정짓는 요인이 어떻게 변화되는지를 분석하고자 한다. 본 분석을 위해 아마존 닷컴의 75,226개의 온라인 소비자 리뷰 데이터를 수집하고, 리뷰 메시지의 감정어 분석 (sentimental analysis)을 통해 메시지 내용에 대한 정량변수도 확보하였다. 다중회귀분석 결과, 리뷰 점수, 리뷰어에 대한 랭킹 정보를 포함하는 주변적 단서(peripheral cues)와 리뷰 메시지의 단어 수, 부정어 비율의 중심적 단서(central cues) 모두 리뷰의 유익성에 영향을 미치는 것으로 나타났다. 또한, 고가격 제품과 저가격 제품에서 유익한 리뷰를 결정하는 요인이 다르게 나타남을 확인하였다.

• 지능정보연구
• /
• 제29권4호
• /
• pp.309-323
• /
• 2023

온라인 리뷰의 역할이 중요해짐에 따라 유용한 리뷰를 선별하기 위해 많은 연구들이 이루어져 왔다. 유용한 리뷰는 고객들이 유용하다고 인지하는 리뷰이며, 평점, 리뷰길이, 리뷰내용 등에 영향을 받는 것으로 많은 연구에서 검증되었다. 유용한 리뷰는 소비자들의 투표에 의한 '좋아요' 수에 의해 결정되며 유용성 투표가 많을수록 소비자의 구매의사결정에 중요한 영향을 미치는 것으로 간주된다. 그러나 최근에 작성되어 많은 고객들에게 노출되지 않은 리뷰는 상대적으로 '좋아요' 수가 적을 수 있으며, 투표에 응하지 않아 '좋아요' 수가 없을 수도 있다. 따라서 유용한 리뷰를 판단하기 위해 '좋아요' 수에 의존하기 보다는 리뷰 내용을 기반으로 유용한 리뷰를 분류하고자 한다. 리뷰의 텍스트는 리뷰 유용성에 가장 큰 영향을 미치는 요인으로, 토픽 모델링, 감정분석 등 텍스트 마이닝 기법을 적용하여 리뷰 텍스트에 포함된 콘텐츠와 감정의 영향을 다양하게 분석하고 있다. 본 연구에서는 글로벌 영화정보 사이트인 IMDb의 영화리뷰를 활용하여 리뷰 콘텐츠 기반의 리뷰 유용성 예측모형을 제안한다. 설명가능한 그래프 신경망인 GNN(Graph Neural Network)을 적용하여 리뷰 유용성 예측모형을 구축하고, 설명가능한 인공지능을 통해 예측모형의 한계인 모형의 해석에 대한 문제를 해결한다. 설명가능한 그래프 신경망은 리뷰들 간의 연결관계도 확인할 수 있어 유용한 리뷰 또는 유용하지 않은 리뷰에 대해 보다 신뢰할 수 있는 정보를 제공할 수 있을 것이라 기대한다.

• 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.