• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.91-93
• /
• 2020

일상의 데이터를 감성 분석에 사용할 때, 데이터 개수가 부족하거나 불균형한 문제가 발생한다. 이에 대해, 본 논문은 데이터 수집 카테고리를 확장하는 방법으로 기존의 문제들을 해결한다. 나아가 확장된 카테고리로 수집한 데이터를 이용해 감성 분석 모델을 만들고, 해당 카테고리에 속하는 타겟 제품에 대한 감성 분석을 시도한다.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.29-56
• /
• 2021

Recently, various types of products have been launched with the rapid growth of the e-commerce market. As a result, many users face information overload problems, which is time-consuming in the purchasing decision-making process. Therefore, the importance of a personalized recommendation service that can provide customized products and services to users is emerging. For example, global companies such as Netflix, Amazon, and Google have introduced personalized recommendation services to support users' purchasing decisions. Accordingly, the user's information search cost can reduce which can positively affect the company's sales increase. The existing personalized recommendation service research applied Collaborative Filtering (CF) technique predicts user preference mainly use quantified information. However, the recommendation performance may have decreased if only use quantitative information. To improve the problems of such existing studies, many studies using reviews to enhance recommendation performance. However, reviews contain factors that hinder purchasing decisions, such as advertising content, false comments, meaningless or irrelevant content. When providing recommendation service uses a review that includes these factors can lead to decrease recommendation performance. Therefore, we proposed a novel recommendation methodology through CNN-based review usefulness score prediction to improve these problems. The results show that the proposed methodology has better prediction performance than the recommendation method considering all existing preference ratings. In addition, the results suggest that can enhance the performance of traditional CF when the information on review usefulness reflects in the personalized recommendation service.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.05a
• /
• pp.49-50
• /
• 2011

• The Optical Journal
• /
• s.145
• /
• pp.47-50
• /
• 2013

Reed Exhibitions Japan이 주최하는 일본 최대의 광 레이저 종합 기술 전시회 'Photonix 2013'이 지난 4월 10일부터 12일까지 사흘간 도쿄 빅사이트 전시장에서 성황리에 개최됐다. 이번 전시회는 전 세계에서 광 레이저 관련 첨단 제품과 기술이 한데 집결한 가운데 진행돼 수많은 광학 업계 종사자들을 불러 모았다.

• The Journal of the Korea Contents Association
• /
• v.15 no.8
• /
• pp.53-68
• /
• 2015

This study analyzed online word-of-mouth information using content analysis to help practical categorization of two-sided eWOM. A total of 402 online consumer reviews on search goods and experience goods were collected. Descriptive characteristics(information direction, length of review line) and content structural characteristics(product benefit types, information presentation methods) were used as analysis criteria. The study results are as follows. First, the types of two-sided e-WOM direction were made of positive/negative, negative/positive, positive/negative/ positive, and negative/positive/negative. Second, the length of two-sided eWOM was longer than the length of one-sided eWOM and blended type accounted for the highest proportion both one-sided and two-sided eWOM at the aspect of product benefit. Third, holistic presentation method was overwhelmingly high in one-sided eWOM, whereas blended and analytic presentation methods were somewhat high in two-sided eWOM. Fourth, holistic presentation method was high in search goods, whereas blended and analytic presentation methods were high in experience goods. Based on these results, implications for two-sided e-WOM study and further research issues were discussed.

• The Journal of the Korea Contents Association
• /
• v.10 no.11
• /
• pp.30-37
• /
• 2010

It is very important to analyze online customer reviews, which are small documents of writing opinions or experiences about products or services, for both customers and companies because the customers can get good informations and the companies can establish good marketing strategies. In this paper, we did not propose only dependency network model which is tool for analyzing online customer reviews, but also designed and implemented the system based on the dependency network model. The dependency network model analyzes both subjective and objective sentences, so that it can represent relative importance and relationship between the nouns in the sentences. In the result of implementing, we recognized that relative importance and relationship between the features of products or services, which can not be mined by opinion mining, can be represented by the dependency network model.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.661-666
• /
• 2007

최근들어 제품을 개발하는 과정 중, 디자이너와 개발자, 의사 결정권자들이 FEM, CFD 시뮬레이션 결과를 리뷰할 때에 가상현실기술을 도입하는 사례가 늘고 있다. 몰입감을 높여주는 가상현실환경은 모델에 대한 해석 결과물을 정확하고 효과적으로 분석할 수 있도록 돕는다. 데이터의 실제 크기와 같게 혹은 그보다 더 크고 자세한 이미지를 제공하는 가상현실 몰입환경은 사용자가 데스크탑 환경만을 사용할 때 경험할 수 없는 높은 사실감을 제공함으로써 사용자에게 시각적인 만족감을 줄 수 있다. 하지만 데스크탑 환경에 비해 해상도가 낮고, 어두운 곳에서 스테레오 안경이나 HMD(Head Mounted Display), Data glove등을 착용해야 하는 불편함과 멀미, 시각적인 피로, 방향감각 상실로 대표되는 가상멀미 등으로 인해 장시간 사용에 어려움이 있다. 데스트탑 환경에서의 데이터 리뷰는 고해상도 이미지 분석은 가능하지만, 입체감이 떨어지기 때문에 리뷰 데이터의 실제감이 떨어진다. 이와 같은 문제점들을 보완하기 위해서 본 논문에서는 데스크탑 환경과 가상현실 환경 간의 협업이 가능한 FEM/CFD 가시화 시스템을 제시한다. 본 시스템은 가상현실 몰입환경에서 해석 데이터를 단순히 가시화하는 것뿐만이 아니라, 데스크탑 시스템과 동일한 3D 인터페이스 구조를 제공한다. 따라서, 해석 결과 분석을 위한 동일한 post-processing 작업이 네트워크로 연결된 원격 공간의 사용자들이 사용하는 시스템들 사이에서 실시간으로 진행될 수 있다.

• The Journal of Society for e-Business Studies
• /
• v.16 no.4
• /
• pp.125-137
• /
• 2011

Product reviews in online shopping sites can serve as a useful guideline to buying decisions of customers. However, due to the massive amount of such reviews, it is almost impossible for users to read all the product reviews. For this reason, e-commerce sites provide users with useful reviews or statistics of ratings on products that are manually chosen or calculated. Opinion mining or sentiment analysis is a study on automating above process that involves firstly analyzing users' reviews on a product to tell if a review contains positive or negative feedback, and secondly, providing a summarized report of users' opinions. Previous researches focus on either providing polarity of a user's opinion or summarizing user's opinion on a feature of a product that result in relatively low usage of information that a user review contains. Actual user reviews contains not only mere assessment of a product, but also dissatisfaction and flaws of a product that a user experiences. There are increasing needs for effective analysis on such criteria to help users on their decision-making process. This paper proposes a model that stores various types of user reviews in a data warehouse, and analyzes integrated reviews dynamically. Also, we analyze reviews of an online application shopping site with the proposed model.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.115-130
• /
• 2011

Many online stores bring features that can build trust in their customers. More so, the number of products or content services on online stores has been increasing rapidly. Hence, personalization on online stores is considered to be an important technology to companies and customers. Recommender systems that provide favorable products and customer product reviews to users are the most commonly used features in this purpose. There are many studies to that investigated the relationship between social presence as an antecedent of trust and provision of recommender systems or customer product reviews. Many online stores have made efforts to increase perceived social presence of their customers through customer reviews, recommender systems, and analyzing associations among products. Primarily because social presence can increase customer trust or reuse intention for online stores. However, there were few studies that investigated the interactions between recommendation type, product type and provision of customer product reviews on social presence. Therefore, one of the purposes of this study is to identify the effects of personalized recommender systems and compare the role of customer reviews with product types. This study performed an experiment to see these interactions. Experimental web pages were developed with $2{\times}2$ factorial setting based on how to provide social presence to users with customer reviews and two product types such as hedonic and utilitarian. The hedonic type was a ringtone chosen from Nate.com while the utilitarian was a TOEIC study aid book selected from Yes24.com. To conduct the experiment, web based experiments were conducted for the participants who have been shopping on the online stores. Participants were a total of 240 and 30% of the participants had the chance of getting the presents. We found out that social presence increased for hedonic products when personalized recommendations were given compared to non.personalized recommendations. Although providing customer reviews for two product types did not significantly increase social presence, provision of customer product reviews for hedonic (ringtone) increased perceived social presence. Otherwise, provision of customer product reviews could not increase social presence when the systems recommend utilitarian products (TOEIC study.aid books). Therefore, it appears that the effects of increasing perceived social presence with customer reviews have a difference for product types. In short, the role of customer reviews could be different based on which product types were considered by customers when they are making a decision related to purchasing on the online stores. Additionally, there were no differences for increasing perceived social presence when providing customer reviews. Our participants might have focused on how recommendations had been provided and what products were recommended because our developed systems were providing recommendations after participants rating their preferences. Thus, the effects of customer reviews could appear more clearly if our participants had actual purchase opportunity for the recommendations. Personalized recommender systems can increase social presence of customers more than nonpersonalized recommender systems by using user preference. Online stores could find out how they can increase perceived social presence and satisfaction of their customers when customers want to find the proper products with recommender systems and customer reviews. In addition, the role of customer reviews of the personalized recommendations can be different based on types of the recommended products. Even if this study conducted two product types such as hedonic and utilitarian, the results revealed that customer reviews for hedonic increased social presence of customers more than customer reviews for utilitarian. Thus, online stores need to consider the role of providing customer reviews with highly personalized information based on their product types when they develop the personalized recommender systems.