• Smart Media Journal
• /
• v.10 no.2
• /
• pp.76-83
• /
• 2021

With the development and use of smart devices such as smartphones and tablets increases, the mobile application market based on mobile devices is growing rapidly. Mobile application users write reviews to share their experience in using the application, which can identify consumers' various needs and application developers can receive useful feedback on improving the application through reviews written by consumers. However, there is a need to come up with measures to minimize the amount of time and expense that consumers have to pay to manually analyze the large amount of reviews they leave. In this work, we propose to collect delivery application user reviews from Google PlayStore and then use machine learning and deep learning techniques to classify them into four categories like application feature advantages, disadvantages, feature improvement requests and bug report. In the case of the performance of the Hugging Face's pretrained BERT-based Transformer model, the f1 score values for the above four categories were 0.93, 0.51, 0.76, and 0.83, respectively, showing superior performance than LSTM and GRU.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.197-200
• /
• 2018

The aim of current research is to suggest a interface for movie reviews at a glance through semantic network analysis. The implication of this study is to systematically investigate the structure of eWoM. Specifically, by visualizing semantic networks of movie reviews this study attempts to provide a prototype of a possible review system that can check the response of movie viewer at a glance.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.596-599
• /
• 2023

본 연구는 브랜드가 시장 트렌드를 파악하고 이를 활용하여 경쟁 우위를 확보하고 성장하는 방법을 탐구하고 있다. 이를 위해 세 가지 핵심 요소를 고려하였다. 첫째, 시장의 트렌드 정보를 파악하기 위해 검색 포털 사이트의 검색어 랭킹 정보를 활용하였다. 둘째, 브랜드 상품과 트렌드의 연관성을 분석하기 위해 상품 타이틀과 리뷰 데이터를 활용하였다. 셋째, 각 상품의 브랜드 중요성을 추정하기 위해 리뷰 수, 리뷰 길이, 표현의 다양성 등을 고려했다. 연구 결과, 브랜드는 시장 트렌드를 더욱 정확하게 이해하고 파악함으로써 경쟁 우위를 확보하고 성장할 수 있는 기회를 제공함을 확인하였다. 더불어, 이를 통해 브랜드는 소비자의 요구를 더욱 효과적으로 충족시키고 고객 경험을 개선하는데 기여할 수 있을 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.13-16
• /
• 2024

온라인상에 인간의 감성을 담은 리뷰 데이터가 꾸준히 축적되어왔다. 이 텍스트 데이터를 분석하고 활용하는 일은 마케팅에 있어서 중요한 자산이 될 것이다. 이와 관련된 Aspect-Based Sentiment Analysis(ABSA) 연구는 한글에 있어서는 데이터 부족을 이유로 거의 선행연구가 없는 실정이다. 본 연구에서는 최근 공개된 데이터 셋을 바탕으로 하여 화장품 도메인에 대한 소비자들의 리뷰 텍스트와 사전 라벨링 된 속성, 감성 극성을 기반으로 ABSA를 진행한다. Klue RoBERTa base 모델을 활용하여 데이터를 학습시키고, Python Kiwipiepy 등으로 전처리한 결과를 대시보드로 시각화하여 분석하기 쉬운 환경을 마련하는 방법을 제시한다.

• Journal of Korea Game Society
• /
• v.17 no.3
• /
• pp.33-44
• /
• 2017

With the development of the Internet environment, various types of online reviews are being generated and exchanged among consumers to share their opinions. In line with this trend, companies are making efforts to analyze online reviews and use the results in various business activities such as marketing, sales, and product development. However, research on online review in industry related to 'Video Game' which is representative experience goods has not been performed enough. Therefore, this study analyzed STEAM community review data using machine learning techniques. We analyzed the factors affecting the opinion of other users' game review. We also propose managerial implications to incease user loyalty and usability.

• Annual Conference of KIPS
• /
• 2017.04a
• /
• pp.850-853
• /
• 2017

본 논문은, 크롤링을 통해 얻은 비정형 데이터를 'Python'의 'KoNLPy' 라이브러리를 사용해 형태소 분석한 후 텍스트 마이닝을 통한 감성사전 구축을 목표로 하고 있으며, 형태소들의 빈도수를 기반으로 가중치로 두어 선별된 단어들을 이용해 긍정과 부정으로 나누어 카테고리화 한다. 이후, 선별한 카테고리에 단어의 극성을 판단하여 감성사전을 모델링한다. 실험을 위하여, 온라인 쇼핑몰 리뷰를 크롤링하여 비정형 데이터를 수집하고, 수집한 데이터를 분석, 가공 과정을 거쳐 정형화된 단어를 추출한다. 그 후에, 리뷰에 자주 사용되는 단어를 바탕으로 카테고리를 구성하였다. 구성된 카테고리 별로 단어의 극성을 판단하여 소비자 성향을 분석한 결과, 단순히 긍정과 부정을 표현하는 범용 감성사전보다 더 세분화된 감성 사전을 구축 할 수 있었다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.636-638
• /
• 2023

Covid19의 세계적 유행 이래로 긴 일정의 해외여행이 감소하고 국내 여행의 수요가 꾸준히 증가하는 추세이다. 현재 다수의 국내 여행 숙박 플랫폼은 가성비 측면으로 이용자가 숙박업소를 선택하고 소비자와 업체를 연결해주는 과정에서 수수료를 얻는 상업적 모델이다. 본 논문에서는 가격 경쟁 중심의 기성 시스템이 아닌, 여행자 개인의 가치를 맞춤화하고 공익의 목적으로 업체를 홍보하는 시스템을 제안한다. 이 시스템은 웹 기반의 시스템을 구현하여 여행자에게 개인 가치에 맞는 업소를 맞춤형으로 추천하고 해당 업소에 대한 평가 지표를 시각화하여 제공한다. 본 시스템은 맞춤형 업소 추천과 평가 지표 제공을 위해 소비자의 리뷰 데이터를 사용한다. 텍스트 데이터를 분석하고 해당 데이터를 다중 분류를 통해 업소에 대한 평가 지표별 점수를 산정한다. 본 시스템은 여행자에게 다양한 관광지와 관광 업소를 추천함으로써 지역 관광을 유도하고 해당 여행지 업소와 지역 경제에 도움을 줄 것이라고 기대된다. 본 논문에서 제안된 기법은 오픈소스로 공개되었다[1].

• The Journal of the Korea Contents Association
• /
• v.19 no.9
• /
• pp.152-161
• /
• 2019

The purpose of this study was to research the relationships among utilitarian perceptions, hedonic perceptions, perceived usefulness and behavioral intention. Recently, consumers rely heavily on user-generated contents of social media channels to support their purchase decisions, such as electronic word-of-mouth. Electronic word-of-mouth helps consumers to evaluate items before making purchase, to reduce purchase risks and to support their purchase decisions. This study was based on both the analysis derived from a hypothesis and literature reviews and data collected from 255 travelers who had used travel review website at least once. The results of empirical analysis showed as follows. First, Utilitarian perceptions(information quality) has a significant impact on the perceived usefulness of a travel review website. Second, Enjoyment has a significant impact on the perceived usefulness of a travel review website. Third, Curiosity fulfilment has a significant impact on the perceived usefulness of a travel review website. Finally, Perceived usefulness of a travel review website has a significant impact on behavioral intention. Based on these findings, the implications and limitations of the study were presented including some directions for future studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.1-6
• /
• 2019

This study visualized users reaction about movies based on keywords with high frequency. For this work, we collected data of movie reviews on . A total of six movies were selected, and we conducted the work of data gathering and preprocessing. Semantic network analysis was used to understand the relationship among keywords. Also, NetDraw, packaged with UCINET, was used for data visualization. In this study, we identified the differences in characteristics of review contents regarding each movie. The implication of this study is that we visualized movie reviews made by sentence as keywords and explored whether it is possible to construct the interface to check users' reaction at a glance. We suggest that further studies use more diverse movie reviews, and the number of reviews for each movie is used in similar quantities for research.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.