통합 검색 | Korea Science

Lee, Jung;Lee, Jae-Nam;Tan, Bernard C.Y.
- Asia pacific journal of information systems
- /
- 제23권3호
- /
- pp.105-129
- /
- 2013
This study draws important factors in electronic Word-of-Mouth (eWOM) and examines how these influence the building of customer loyalty. eWOM is viewed as social communication between customers and sellers, and thus the communicative action theory is applied. With the theory, we identify reviewer and seller as influential players on customers, and derive important factors such as correctness and veracity of reviews from the reviewers' action, and information compactness and adequacy from the seller's action. We propose these constructs as antecedents of customer loyalty and further hypothesize their curvilinear impacts as follows: the marginal impacts of veracity and correctness will decrease as veracity and correctness increase, and the marginal impacts of compactness and adequacy will increase as compactness and adequacy increase. The result indicates that only the seller's action has a curvilinear impact, whereas the reviewer has proportional positive impact on customer loyalty. This study indentifies important factors in eWOM from a critical social theory perspective and validates them using the positivistic approach. For practitioners, it discusses the important factors in eWOM with the identification of the individuals who are responsible for these factors.
https://doi.org/10.14329/apjis.2013.23.3.105 인용 PDF

장은진;김정군
- 한국정보시스템학회지:정보시스템연구
- /
- 제20권4호
- /
- pp.233-254
- /
- 2011
Although e-commerce is growing fast, e-commerce consumers are still under higher risk and uncertainty in the comparison of the traditional commerce's. Consumer review boards of online shopping malls are good measures to help buyer's decision making, and should be managed effectively by sellers. We formulate the research model on consumer trust formation on seller managed web review boards on the background of previous literatures on e-WOM and trust. Our data analysis with 368 samples shows seller's reputation, e-service quality, perceived reviewer's benevolence and ability have significant positive effect on the trustworthiness of the board. Product involvement shows weak negative moderation effect on the relationship between perceived reviewer's benevolence and trustworthiness of review boards.
https://doi.org/10.5859/KAIS.2011.20.4.233 인용 PDF

신동훈;신우식;김희웅
- 한국정보시스템학회지:정보시스템연구
- /
- 제31권4호
- /
- pp.01-23
- /
- 2022
Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.
https://doi.org/10.5859/KAIS.2022.31.4.1 인용 PDF KSCI

Lin Li;Gang Ren;Taeho Hong;Sung-Byung Yang
- Asia pacific journal of information systems
- /
- 제29권2호
- /
- pp.181-202
- /
- 2019
The purpose of this study is to explore the effect of different types of simultaneous presentation (i.e., reviewer information, textual and visual content, and similarity between textual-visual contents) on review usefulness and review enjoyment in online restaurant reviews (ORRs), as they are interrelated yet have rarely been examined together in previous research. By using Latent Dirichlet Allocation (LDA) topic modeling and state-of-the-art machine learning (ML) methodologies, we found that review readability in textual content and salient objects in images in visual content have a significant impact on both review usefulness and review enjoyment. Moreover, similarity between textual-visual contents was found to be a major factor in determining review usefulness but not review enjoyment. As for reviewer information, reputation, expertise, and location of residence, these were found to be significantly related to review enjoyment. This study contributes to the body of knowledge on ORRs and provides valuable implications for general users and managers in the hospitality and tourism industries.
https://doi.org/10.14329/apjis.2019.29.2.181 인용 PDF