• 인터넷정보학회논문지
• /
• 제17권3호
• /
• pp.107-113
• /
• 2016

소셜 네트워크 서비스(SNS)의 활성화로 웹상에는 방대한 양의 온라인 리뷰들이 생산되고 있으며, 이러한 온라인 리뷰들은 다양한 콘텐츠들에 대한 의견 데이터로써 콘텐츠 이용자와 제공자들에게 가치 있는 정보로 활용되고 있다. 한편, 온라인 리뷰에 대한 중요도가 높아짐에 따라 온라인 리뷰를 분석하여 글쓴이의 의견이나 평가, 태도, 감정 등을 추출해 내는 오피니언마이닝에 대한 연구가 활발하게 진행되고 있다. 그러나 기존의 오피니언마이닝 연구들에서는 리뷰의 의견 분류에만 초점을 맞추어 감성 분석 기법을 설계하였기 때문에 리뷰 속에 내포되어있는 작성자의 자세한 만족도까지는 알 수 없었으며, 감성 분석 기법이 특정 콘텐츠에 한정되어있어 도메인이 같지 않은 다른 콘텐츠들에는 적용될 수 없다는 문제점이 있었다. 이에 본 연구에서는 기존 의견 분류 방법에 강도를 주어 좀 더 세밀한 감성 분석을 수행하고, 이 결과를 통계적 척도에 적용하여 리뷰에 내포되어 있는 작성자의 자세한 만족도를 도출 할 수 있는 감성 분석 기법을 제안한다, 그리고 제안한 기법을 바탕으로 도메인에 상관없이 다양한 콘텐츠에 적용되어 콘텐츠의 만족도를 분석 할 수 있는 시스템을 설계하였다. 또한 방대한 양의 리뷰 데이터들을 빠르고 효율적으로 처리하기 위해 빅 데이터 처리도구인 하둡을 기반으로 시스템을 구축하였다. 본 시스템을 통해 콘텐츠 이용자는 보다 효율적인 의사결정을, 제공자들은 빠른 반응분석을 할 수 있어 본 시스템은 사용자의 의견을 필요로 하는 다양한 분야에 매우 실용적으로 활용 될 것으로 기대한다.

• 지능정보연구
• /
• 제26권2호
• /
• pp.57-78
• /
• 2020

인터넷의 발달로, 소비자들은 이커머스에서 손쉽게 상품 정보를 확인한다. 이때 활용되는 상품 리뷰는 사용자 경험을 토대로 작성되어 구매의사결정의 효율성을 높일 뿐만 아니라 상품 개발에 도움을 주기도 한다. 하지만, 방대한 양의 상품 리뷰에서 관심있는 평가차원의 세부내용을 파악하는 데에는 많은 시간과 노력이 소비된다. 예를 들어, 노트북을 구매하려는 소비자들은 성능, 무게, 디자인과 같은 평가차원에 대해 각 차원별로 비교 상품의 평가를 확인하고자 한다. 따라서 본 논문에서는 상품 리뷰에서 다차원 상품평가 점수를 자동적으로 생성하는 방안을 제안하고자 한다. 본 연구에서 제시하는 방안은 크게 2단계로 구성된다. 사전준비 단계와 개별상품평가 단계로, 대분류 상품군 리뷰를 토대로 사전에 생성된 차원분류모델과 감성분석모델이 개별상품의 리뷰를 분석하게 된다. 차원분류모델은 워드임베딩과 연관분석을 결합함으로써 기존 연구에서 차원과 단어들의 관련성을 찾기 위한 워드임베딩 방식이 문장 내 단어의 위치만을 본다는 한계를 보완한다. 감성분석모델은 정확한 극성 판단을 위해 구(phrase) 단위로 긍부정이 태깅된 학습데이터를 구성하여 CNN 모델을 생성한다. 이를 통해, 개별상품평가 단계에서는 구 단위의 리뷰에 준비된 모델들을 적용하고 평가차원별로 종합함으로써 다차원 평가점수를 얻을 수 있다. 본 논문의 실험에서는 대분류 상품군 리뷰 약 260,000건으로 평가모델을 구성하고, S사와 L사의 노트북 리뷰 각 1,011건과 1,062건을 실험데이터로 활용한다. 차원분류모델은 구로 분해한 개별상품 리뷰를 6개 평가차원으로 분류했고, 기존 워드임베딩 방식보다 연관분석을 결합한 모델의 정확도가 13.7% 증가했음을 볼 수 있었다. 감성분석모델은 문장보다 구 단위로 학습한 모델이 평가차원을 면밀히 분석함으로써 29.4% 더 높은 정확도를 보임을 확인했다. 본 연구를 통해 판매자, 소비자 모두가 상품의 다차원적 비교가 가능하다는 점에서 구매 및 상품 개발에 효율적인 의사결정을 기대할 수 있다.

• Journal of Information Technology Applications and Management
• /
• 제30권2호
• /
• pp.1-18
• /
• 2023

Recently, as technology development has accelerated and product life cycles have been shortened, it is necessary to derive key product features from customers in the R&D planning and evaluation stage. More companies want differentiated competitiveness by providing consumer-tailored products based on big data and artificial intelligence technology. To achieve this, the need to correctly grasp the required quality, which is a requirement of consumers, is increasing. However, the existing methods are centered on suppliers or domain experts, so there is a gap from the actual perspective of consumers. In other words, product attributes were defined by suppliers or field experts, but this may not consider consumers' actual perspective. Accordingly, the demand for deriving the product's main attributes through reviews containing consumers' perspectives has recently increased. Therefore, we propose a review data analysis-based required quality methodology containing customer requirements. Specifically, a pre-training language model with a good understanding of Korean reviews was established, consumer intent was correctly identified, and key contents were extracted from the review through a combination of KeyBERT and topic modeling to derive the required quality for each product. RevBERT, a Korean review domain-specific pre-training language model, was established through further pre-training. By comparing the existing pre-training language model KcBERT, we confirmed that RevBERT had a deeper understanding of customer reviews. In addition, all processes other than that of selecting the required quality were linked to the automation process, resulting in the automation of deriving the required quality based on data.

• 만화애니메이션 연구
• /
• 통권16호
• /
• pp.21-32
• /
• 2009

본 연구는 2003년부터 2008년까지 한국에서 개봉된 애니메이션 영화들을 분석대상으로 하여 해당 영화의 흥행성과에 영향을 미치는 요인들을 고찰하고자 한다. 종속변수는 전국 총관객수이다. 총관객수에 영향을 미치는 요인이 무엇인지 고찰하기 위해 독립변인은 배급사 파워, 개봉스크린 규모, 개봉시점, 속편형태, 수상실적, 영화의 국적 및 등급, 그리고 전문가 평점과 네티즌의 온라인평점으로 설정되었다. 회귀분석 결과에서 전국 관객수에 유의미한 영향력을 미치는 변수는 개봉스크린 규모, 할리우드직배사의 배급, 여름시즌 개봉, 그리고 네티즌 평점이다. 본 연구는 한국 영화시장에서 애니메이션 흥행성과에 대한 분석을 시도했다는 점에서 의의를 찾을 수 있을 것이다.

• 한국산학기술학회논문지
• /
• 제14권3호
• /
• pp.1422-1427
• /
• 2013

본 논문에서는 사용자가 작성한 영화평으로부터 추출한 감정어휘에 기반한 영화검색시스템을 제안한다. 먼저, 사용자의 영화평을 형태소분석하고 수작업으로 감정어휘사전을 구축한다. 그 다음, 검색의 대상이 되는 영화별로 감정어휘사전에 포함되어 있는 감정어휘들의 가중치를 TF-IDF를 이용하여 계산한다. 이러한 결과를 이용하여 제안 시스템은 영화의 감정 분류를 결정하고, 랭킹하여 사용자에게 보여주게 된다. 사용자들은 영화평을 읽지 않고도, 감정 어휘로 구성된 질의어를 입력하여 원하는 영화를 찾을 수 있게 된다.

• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.650-664
• /
• 2022

Mobile applications can be easily downloaded and installed via markets. However, malware and malicious applications containing unwanted advertisements exist in these application markets. Therefore, smartphone users install applications with reference to the application review to avoid such malicious applications. An application review typically comprises contents for evaluation; however, a false review with a specific purpose can be included. Such false reviews are known as fake reviews, and they can be generated using artificial intelligence (AI)-based text-generating models. Recently, AI-based text-generating models have been developed rapidly and demonstrate high-quality generated texts. Herein, we analyze the features of fake reviews generated from Generative Pre-Training-2 (GPT-2), an AI-based text-generating model and create a model to detect those fake reviews. First, we collect a real human-written application review from Kaggle. Subsequently, we identify features of the fake review using natural language processing and statistical analysis. Next, we generate fake review detection models using five types of machine-learning models trained using identified features. In terms of the performances of the fake review detection models, we achieved average F1-scores of 0.738, 0.723, and 0.730 for the fake review, real review, and overall classifications, respectively.

• 패션비즈니스
• /
• 제14권6호
• /
• pp.134-145
• /
• 2010

The purpose of this study is 1) to investigate the contents of fashion brand applications and what differences and 2) to scrutinize the reviews of the applications uploaded on the app store in order to suggest strategies on how to apply them to fashion. For the study, twenty-nine free applications from different categories of the fashion brands and three hundred sixty-two reviews of these applications were investigated. The analysis of the study was conducted from June 20th to November 10th of 2010. The results showed that there are four important components for fashion brand applications: conventional information (product information and store information), the purchasing function, the fun element (social networking, blogging, music etc), and the augmented reality technique. These components are formulated based on the brand's marketing strategies. In order to know whether or not these components were successfully composed, user reviews were studied, which revealed that many users were satisfied, but the applications were insufficient to meet all of their needs.

• 한국벤처창업학회:학술대회논문집
• /
• 한국벤처창업학회 2022년도 춘계학술대회
• /
• pp.123-126
• /
• 2022

Online reviews offer valuable information to businesses by reflecting consumer experiences about their products and services. Two important aspects of online reviews are first, the topics consumers choose to address and second, the sentiments expressed in their reviews. Building upon previous literature that shows online reviews are context-dependent, we examine the impact of topic distribution on review sentiment in South Korea and the U.S. during pre-and post-pandemic periods. After performing topic modeling on Airbnb app review data, we measure the contribution of each topic on review sentiment using SHAP values. Our results indicate variations in topic distribution trends between 2018 and 2021. Also, the order and magnitude of topics' impact on review sentiment change between pre-and post-pandemic periods for both countries. This study can help businesses to understand how topics and sentiments associated with their products and services changed after pandemic, and also help them identify areas of improvement.

• Asia pacific journal of information systems
• /
• 제32권3호
• /
• pp.514-536
• /
• 2022

Online reviews offer valuable information to businesses by reflecting consumer experiences about their products and services. Two crucial aspects of online reviews are the topics consumers choose to address, and the sentiments expressed in their reviews. Building upon previous literature that shows online reviews are context-dependent, we employ the Expectation-Confirmation Theory (ECT) to examine the impact of topic distribution on review sentiment in South Korea and the U.S. during pre- and post-pandemic periods. After applying a topic modeling to Airbnb app review data, we measure the contribution of each topic on review sentiment using SHAP values. Our results indicate variations in topic distribution trends between 2018 and 2021. In addition, the order and magnitude of topics' impact on review sentiment change between pre- and post-pandemic periods for both countries. This study can help businesses understand how topics and sentiments associated with their products and services changed after the pandemic and thus identify areas of improvement.

• Asia pacific journal of information systems
• /
• 제18권3호
• /
• pp.67-90
• /
• 2008

Prior to making choices among online products and services, consumers often search online product reviews written by other consumers. Online product reviews have great influences on consumer behavior because they are believed to be more reliable than information provided by sellers. However, ever-increasing lists of product reviews make it difficult for consumers to find the right information efficiently. A customized search mechanism is a method to provide personalized information which fits the user's requirements. This study examines effects of a customized search mechanism and perceived similarity between consumers and product reviewers on consumer behaviors. More specifically, we address the following research questions: (1) Can a customized search mechanism increase perceived similarity between product review authors and readers? (2) Are product reviews perceived as more credible when product reviews were written by the authors perceived similar to them? (3) Does credibility of product reviews have a positive impact on acceptance of product reviews? (4) Does acceptance of product reviews have an influence on purchase intention of the readers? To examine these research questions, a lab experiment with a between-subject factor (whether a customized search mechanism is provided or not) design was employed. In order to enhance mundane realism and increase generalizability of the findings, the experiment sites were built based on a real online store, cherrya.com (http://www.cherrya.com/). Sixty participants were drawn from a pool that consisted of undergraduate and graduate students in a large university. Participation was voluntary; all the participants received 5,000 won to encourage their motivation and involvement in the experiment tasks. In addition, 15 participants, who selected by a random draw, received 30,000 won to actually purchase the product that he or she decided to buy during the experiment. Of the 60 participants, 25 were male and 35 were female. In examining the homogeneity between the two groups, the results of t-tests revealed no significant difference in gender, age, academic years, online shopping experience, and Internet usage. To test our research model, we completed tests of the measurement models and the structural models using PLS Graph version 3.00. The analysis confirmed individual item reliability, internal consistency, and discriminant validity of measurements. The results show that participants feel more credible when product reviews were written by the authors perceived similar to them, credibility of product reviews have a positive impact on acceptance of product reviews, and acceptance of product reviews have an influence on purchase intention of the readers. However, a customized search mechanism did not increase perceived similarity between product review authors and readers. The results imply that there is an urgent need to develop a better customized search tool in order to increase perceived similarity between product review authors and readers.