• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.21-41
• /
• 2019

Thanks to the rapid development of information technologies, the data available on Internet have grown rapidly. In this era of big data, many studies have attempted to offer insights and express the effects of data analysis. In the tourism and hospitality industry, many firms and studies in the era of big data have paid attention to online reviews on social media because of their large influence over customers. As tourism is an information-intensive industry, the effect of these information networks on social media platforms is more remarkable compared to any other types of media. However, there are some limitations to the improvements in service quality that can be made based on opinions on social media platforms. Users on social media platforms represent their opinions as text, images, and so on. Raw data sets from these reviews are unstructured. Moreover, these data sets are too big to extract new information and hidden knowledge by human competences. To use them for business intelligence and analytics applications, proper big data techniques like Natural Language Processing and data mining techniques are needed. This study suggests an analytical approach to directly yield insights from these reviews to improve the service quality of hotels. Our proposed approach consists of topic mining to extract topics contained in the reviews and the decision tree modeling to explain the relationship between topics and ratings. Topic mining refers to a method for finding a group of words from a collection of documents that represents a document. Among several topic mining methods, we adopted the Latent Dirichlet Allocation algorithm, which is considered as the most universal algorithm. However, LDA is not enough to find insights that can improve service quality because it cannot find the relationship between topics and ratings. To overcome this limitation, we also use the Classification and Regression Tree method, which is a kind of decision tree technique. Through the CART method, we can find what topics are related to positive or negative ratings of a hotel and visualize the results. Therefore, this study aims to investigate the representation of an analytical approach for the improvement of hotel service quality from unstructured review data sets. Through experiments for four hotels in Hong Kong, we can find the strengths and weaknesses of services for each hotel and suggest improvements to aid in customer satisfaction. Especially from positive reviews, we find what these hotels should maintain for service quality. For example, compared with the other hotels, a hotel has a good location and room condition which are extracted from positive reviews for it. In contrast, we also find what they should modify in their services from negative reviews. For example, a hotel should improve room condition related to soundproof. These results mean that our approach is useful in finding some insights for the service quality of hotels. That is, from the enormous size of review data, our approach can provide practical suggestions for hotel managers to improve their service quality. In the past, studies for improving service quality relied on surveys or interviews of customers. However, these methods are often costly and time consuming and the results may be biased by biased sampling or untrustworthy answers. The proposed approach directly obtains honest feedback from customers' online reviews and draws some insights through a type of big data analysis. So it will be a more useful tool to overcome the limitations of surveys or interviews. Moreover, our approach easily obtains the service quality information of other hotels or services in the tourism industry because it needs only open online reviews and ratings as input data. Furthermore, the performance of our approach will be better if other structured and unstructured data sources are added.

• Proceedings of the Technology Innovation Conference
• /
• 2009.02a
• /
• pp.3-24
• /
• 2009

본 논문은 온라인 커뮤니티를 통해 사용자들이 정보교류와 의사소통을 활발히 전개하여 사용자혁신 (User Innovation)을 촉진하는 사례들과 이와 관련된 현안 이슈들, 그리고 기업의 사용자혁신 활용 전략을 다루고 있다. 특히 인터넷의 보급과 확산을 통해 사용자들이 온라인 커뮤니티를 형성하고 상호 교류할 수 있는 장이 마련되어 사용자혁신이 더욱 활성화 될 수 있으므로, 휴대기기 산업에서 이러한 사례를 발굴하여 분석하였다. 특히 본 연구에서는 MP3 플레이어 산업에서 기업이 온라인 커뮤니티를 통해 고객정보를 어떻게 획득/처리/활용하는지, 그리고 스마트폰인 블랙잭 제품에서 어떤 과정을 통해 사용자혁신이 이루어지는 지를 사례연구 하였다. 본 연구의 결과는 1)온라인 커뮤니티에서 사용자의 역할과 (정보공유, 아이디어 창출, 문제해결, 정보취합, 제품테스트, 사용의견 제시, 제품홍보 등) 기업의 대응전략, 2)기업과 고객간 커뮤니케이션 패턴 (질문/불평/사용후기 및 피드백/시제품/공지 등) 특성, 3)온라인 커뮤니티 내에서 사용자간 커뮤니케이션 패턴과 현안, 4)온라인 커뮤니티 활성화를 통한 신제품개발 촉진방안 등으로 구분하여 제시되었다. 마지막으로 이러한 사용자혁신 사례를 바탕으로, 사용자혁신을 촉진하고 신제품개발과정에서 사용자의 참여를 강화할 수 있는 정책적 함의를 정리하였다. 특히 개방형 혁신이 강조되는 상황에서 사용자혁신은 개방형 혁신의 한 형태도서도 의미가 있으며, 향후 더 많은 사례연구와 실증분석이 요구된다.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.113-127
• /
• 2021

This study classifies review attributes into ratings, number of comments and image information in online shopping mall to verify their impact on brand attitude and purchase decision and e-WOM intention. Use SPSS 23.0 for frequency analysis, factor analysis and regression analysis. The results showed that review attributes have a positive effect on brand attitudes, purchase decision and e-WOM intention, but the number of comments has not affect on purchase decision. Brand attitude has a positive effect on purchase decision and e-WOM intention. Brand attitude has media effect in the relationship between ratings, image information and purchase decision, and in the relationship between review attributes and e-WOM intention. As these results, consumers don't always like to have a lot of comments. and should allow to focus on high ratings and photo reviews as much as possible when writing reviews.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.1
• /
• pp.136-146
• /
• 2021

This study is a descriptive research to determine the degree of self-esteem, menopausal symptom, spousal support of middle-aged women and investigate the factors affecting aging anxiety. For 3 weeks from May 23 to June 13, 2020, data total of 110 people were collected using online questionnaires for late middle-aged women. As a result of date analysis, factors affecting aging anxiety in late middle-aged women were menopausal symptoms(B=17.943, p<.001), self-esteem(B=-.585, p=.001) and the explanatory power of the regression model was 41.4%. Therefore, in order to lower againg anxiety, active intervention for menopausal symptoms of late middle-aged women is required, and measures should be taken to increase self-esteem.

• Information Systems Review
• /
• v.17 no.3
• /
• pp.95-111
• /
• 2015

The recommendation system automatically provides the predicted items which are expected to be purchased by analyzing the previous customer behaviors. This recommendation system has been applied to many e-commerce businesses, and it is generating positive effects on user convenience as well as the company's revenue. However, there are several limitations of the existing recommendation systems. They do not reflect specific criteria for evaluating products or the factors that affect customer buying decisions. Thus, our research proposes a collaborative recommendation model algorithm that utilizes each customer's online product reviews. This study deploys topic modeling method for customer opinion mining. Also, it adopts a kernel-based machine learning concept by selecting kernels explaining individual similarities in accordance with customers' purchase history and online reviews. Our study further applies a multiple kernel learning algorithm to integrate the kernelsinto a combined model for predicting the product ratings, and it verifies its validity with a data set (including purchased item, product rating, and online review) of BestBuy, an online consumer electronics store. This study theoretically implicates by suggesting a new method for the online recommendation system, i.e., a collaborative recommendation method using topic modeling and kernel-based learning.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.387-390
• /
• 2009

인터넷의 생활화를 통해 우리 생활 패턴이 크게 변화하였다. 특히 상품 구매의 경우 온라인 시장의 성장과 상품 정보의 범람으로 소비자들의 구매 의사결정은 더욱 어려워졌다. 따라서 효율적인 상품 구매 의사결정을 위해서는 소셜 네트워크 분석(Social Network Analysis)을 기반으로 한 더 가치있는 정보를 선별하여 제공해 줄 수 있는 서비스가 필요하다. 따라서 본 논문에서는 온라인 소셜 네트워크 요소 분석을 통해 상품 후기에 대한 개인화된 가치 측정값 정보를 제공함으로써 소비자의 보다 효율적인 상품 구매가 가능하도록 도와주는 '가치 측정 알고리즘'을 제안한다.

• Asia Marketing Journal
• /
• v.13 no.3
• /
• pp.209-231
• /
• 2011

Internet is having strong impact on the consumer's decision making process. Information search has been done actively through internet today. The online reviews can be crucial information cue to evaluate the alternarive products. The online WOM(Word-Of-Mouth) effect depends on the characteristics of information sender, receiver, and WOM. This study is to examine the influence of the online word of mouth on the consumer purchase intention and the moderating role of product involvement, consumer regulatory focus and self-efficacy. Positive customer reviews on the products influence the purchase intention positively and negative customer reviews influence it negatively. Moderating role of involvement in the causal relation between the valence of online reviews and purchase intention is tested. In case of positive WOM, it is predicted that purchase intention for high involvement products is higher than that of low involvement. In case of negative WOM, purchase intention for high involvement product is lower than that of low involvement product. And this study invetigate the moderating role of regulatory focus. In case of positive WOM, it is predicted that promotion focus oriented consumers have higher purchase intention than prevention focus oriented consumers. In case of negative WOM, prediction is that prevention focus oriented consumers have lower purchase intention than promotion focus oriented consumers. Then we examine the moderating role of self efficacy in the causal relation between the valence of online reviews and purchase intention. In case of positive WOM, it is predicted that consumers with low self efficacy have higher purchase intention than consumers with high self efficacy. In case of negative WOM, it is predicted that consumers with low self efficacy have lower purchase intention than consumers with high self efficacy. Emprical results support our prediction and four hypotheses derived from our conceptual framework are all accepted. This study suggest that the level of product involvement, consumer regulatory focus and the level of self-efficacy influence the consumer responses of the valence of online reviews. Therefore marketers need to manage online reviews based on the level of product involvement, regulatory focus orientation and the level of self-efficacy of target consumers.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.73-82
• /
• 2013

The purpose of this study is to explore attributes of trusted blog product-reviews and to examine the weight of each attribute. First, the attributes of trusted blog product-reviews were collected through consumer interviews. Second, the trust attributes were examined in terms of their relative importance. The results are: 1) Thirty-five of trust attributes were discovered and categorized into 'popularity', 'presence', 'attractiveness', 'trustworthiness', and 'expertise'. 2) In general, attributes reflecting usefulness, trustworthiness and attractiveness seemed the most important trust factors. 3) 'presence', which have not been highlighted so far in trust research, was emerged as an important trust factor in the web blog context. Theoretical and practical implications were discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.265-267
• /
• 2009

디지털 제품 구매자는 일반적으로 온라인을 통하여 제품 웹사이트에서 제품의 특징이나 사용 후기를 충분히 보고 제품을 구입한다. 그리고 제품을 구입 후에 사용자는 온라인에서 제품의 매뉴얼을 통하여 익힌다. 이러한 과정에서 본 연구자는 사용자들의 온라인상에서 제품 구매 전, 후에서 문제점을 발견하고 확실히 어떠한 요구사항이 존재할 것이라는 의문을 가졌다. 따라서 다양한 일반인 연령대를 구성한 340명을 대상으로 디지털 제품의 전달 매체 사용에 대한 온라인 설문조사를 실시하였다. 설문문항 내용에서 우선적 대안으로 예상한 것들은 '데스크탑 가상현실'과 '멀티미디어 동영상' 매체들이다. 그리고 사용자들이 이것들을 새로운 매체로서 가장 요구하는 사항일 것이라는 추측을 하고 현황을 파악한다. 최종적으로는 사용자가 요구하는 제품에서 매체의 기능과 만족도를 조사하고 개선점을 파악하며 문제점에 대한 해결 대안의 기초 자료로서 제시하고자 한다.

• Economic Analysis
• /
• v.25 no.2
• /
• pp.54-95
• /
• 2019

The purpose of this study is to analyze quantitatively and qualitatively the effects of the increase in online shopping and its effects on real-world commercial outlets. The empirical analysis of this study is based on the results of "Census on Establishments" and "Online Shopping Survey" that cover 15 years, from 2002 to 2016. According to the results of this study, the increase in the number of online transactions affects the decrease in the number of stores in the real-world retail sector. However, non-specialized large stores and chain convenience stores showed an increase in the number of stores. In addition, the number of F&B stores increased the most in line with the increase in online transactions. This is because the increase in online transactions and in internet users led to the use of more delivery applications and the introduction of popular places on blogs or through social media. Street-level rents for medium and large-sized locations increased. In other words, it is seen that the demand for differentiated real-world stores that provide a good user experience increases, even though online transactions also increase. These results suggest that real-world stores should provide good user experiences in their physical locations with a certain size and assortment of goods.