• Title/Summary/Keyword: 제품리뷰

Search Result 131, Processing Time 0.022 seconds

Sentiment Analysis of Movie Review Using Integrated CNN-LSTM Mode (CNN-LSTM 조합모델을 이용한 영화리뷰 감성분석)

  • Park, Ho-yeon;Kim, Kyoung-jae
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.4
    • /
    • pp.141-154
    • /
    • 2019
  • Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

Estimate Customer Churn Rate with the Review-Feedback Process: Empirical Study with Text Mining, Econometrics, and Quai-Experiment Methodologies (리뷰-피드백 프로세스를 통한 고객 이탈률 추정: 텍스트 마이닝, 계량경제학, 준실험설계 방법론을 활용한 실증적 연구)

  • Choi Kim;Jaemin Kim;Gahyung Jeong;Jaehong Park
    • Information Systems Review
    • /
    • v.23 no.3
    • /
    • pp.159-176
    • /
    • 2021
  • Obviating user churn is a prominent strategy to capitalize on online games, eluding the initial investments required for the development of another. Extant literature has examined factors that may induce user churn, mainly from perspectives of motives to play and game as a virtual society. However, such works largely dismiss the service aspects of online games. Dissatisfaction of user needs constitutes a crucial aspect for user churn, especially with online services where users expect a continuous improvement in service quality via software updates. Hence, we examine the relationship between a game's quality management and its user base. With text mining and survival analysis, we identify complaint factors that act as key predictors of user churn. Additionally, we find that enjoyment-related factors are greater threats to user base than usability-related ones. Furthermore, subsequent quasi-experiment shows that improvements in the complaint factors (i.e., via game patches) curb churn and foster user retention. Our results shed light on the responsive role of developers in retaining the user base of online games. Moreover, we provide practical insights for game operators, i.e., to identify and prioritize more perilous complaint factors in planning successive game patches.

User Experience Analysis of Smart bands (스마트 밴드에 대한 사용자경험 분석)

  • Kim, Gun-A;Kim, Suk-Tae
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.8
    • /
    • pp.99-105
    • /
    • 2017
  • With the advancement of Information and Communication Technology (ICT), the wearable-device industry is growing at a rapid pace in line with the hyper-connected society of people-to-things and things-to-things network connections. International Data Corporation (IDC), a market research institute, estimates that the wearable-device industry will grow rapidly by 2020, despite not yet attracting a popular response. This study investigates the trend of the wearable-device industry and draws implications for product and service development through user experience analysis. The subject of analysis was smart bands and the data generated from product review were collected and analyzed. As a result, user experience could extract utility, usability, aesthetics, value, and reliability, and polarity was analysed and visualized in the extracted data. The study results reveal that current wearable-devices are expensive, that users cannot receive useful information from the long-term viewpoint since the analysis of accumulated data remains focused on functional development, and that they are recognized as a fashion item or an accessory. These factors hinder the continuous usage, motivation and market spread of the product. In a future follow-up study, we will conduct a comparative study on bands and watches by analyzing the second smart watch.

Does Online Social Network Contribute to WOM Effect on Product Sales? (온라인 소셜네트워크의 제품판매 관련 구전효과에 대한 기여도 분석)

  • Lee, Ju-Yoon;Son, In-Soo;Lee, Dong-Won
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.2
    • /
    • pp.85-105
    • /
    • 2012
  • In recent years, IT advancement has brought out the new Internet communication environment such as online social network services, where people are connected in global network without temporal and spatial limitation. The popular use of online social network helps people share their experience and preference for specific products and services, thus holding large potential to significantly affect firms' business performance through Word-of-Mouth (WOM). This study examines the role of online social network in raising WOM effect on the movie industry by comparing with the similar role of Internet portal, another major online communication channel. Analyzing 109 movies and data from both Twitter and Naver movie, we found that significant WOM effect exists simultaneously in both Twitter and Naver movie. However, we also found that different figures of online viral effects exist depending on the popularity of movies. In the hit movie group, before the movie release, the WOM effect occurs only in Twitter while the WOM effect arises in both Twitter and Naver movie at the same time after the movie release. In the less-popular (or niche) movie group, the WOM effect occurs in both Twitter and Naver movie only before the movie release. Our findings not only deepen theoretical insights into different roles of the two online communication channels in provoking the WOM effect on entertainment products but also provide practitioners with incentive to utilize SNS as strategic marketing platform to enhance their brand reputations.

Informatics analysis of consumer reviews for 「Frozen 2」 fashion collaboration products - Semantic networks and sentiment analysis - (「겨울왕국2」의 콜라보레이션 패션제품에 대한 소비자 리뷰 - 의미 네트워크와 감성분석 -)

  • Choi, Yeong-Hyeon;Lee, Kyu-Hye
    • The Research Journal of the Costume Culture
    • /
    • v.28 no.2
    • /
    • pp.265-284
    • /
    • 2020
  • This study aimed to analyze the performance of Disney-collaborated fashion lines based on online consumer reviews. To do so, the researchers employed text mining and network analysis to identify key words in the reviews of these products. Blogs, internet cafes, and web documents provided by Naver, Daum, and YoutTube were selected as subjects for the analysis. The analysis period was limited to one year after for the 2019. Data collection and analysis were conducted using Python 3.7, Textom, and NodeXL. The research terms in question were as follows: 'Disney fashion collaboration' and 'Frozen fashion collaboration'. Preliminary survey results indicated that 'Elsa's dress' was the most frequently mentioned term and that the domestic fashion brand Eland Retail was the most active in selling Disney branded clothing through its own brand. The writers of reviews for Disney-collaborated fashion products were primarily mothers with daughters. Their decision to purchase these products was based upon the following factors; price, size, stability of decoration, shipping, laundry, and retailer. The motives for purchasing the product were the positive response of the consumer's child and the satisfaction of the parents due to the child's response. The problems to be solved included insufficient quantity of supply, delay in delivery, expensive price considering the number of times children's clothes are worn, poor glitter decoration, faded color, contamination from laundry, and undesirable smells immediately after the purchase.

Wireless capsule endoscopy Locomotion

  • Wang, Zhao;Lim, Eng Gee;Leach, Mark;Xia, Tianqi;Lee, Sanghyuk
    • Journal of Convergence Society for SMB
    • /
    • v.4 no.1
    • /
    • pp.55-62
    • /
    • 2014
  • Wireless capsule endoscopy (WCE) was one of the most influential bio-medical electronic technologies to be developed at the beginning of the century. In comparison to traditional endoscopic diagnosis, this application is characterized as non-invasive and low-risk, thereby providing surgeons with a new alternative for inspecting the entire gastrointestinal (GI) track in a much more user friendly way. Apart from regular hardware upgrades, the frontier of WCE research basically lies in the miniaturization of the capsule and in active locomotion. In order to overcome the intrinsic drawback of current commercialized WCE products, which is that locomotion is generally a function of natural peristalsis, active locomotion is proposed as a series of strategies used to effectively navigate the device into different organs and conduct therapeutic functions within targeted human tissues. Reviews of several novel designs with respect to this aspect of research will be discussed in this article.

  • PDF

Online to Offline Convergent Ecosystem: a Case Study of Dianping.com (온라인과 오프라인을 융북합 생태계: Dianping.com 사례연구)

  • Zhang, Chao;Wan, Lili
    • Journal of Digital Convergence
    • /
    • v.13 no.6
    • /
    • pp.105-111
    • /
    • 2015
  • In this highly competitive century, selling products and service through Internet and smart phones offers both opportunities and challenges. Online commerce is expanding it's wings to the offline market. The connection between online market and offline market is called O2O(Offline to Online) market. In this study we examine the best practice case study of an Internet company's successful efforts to connect users and offline merchants. Based on Dianping.com success story in China, a successful framework for building online to offline ecosystem is examined. Dianping.com successful experience may provide suggestions for other online companies operate in the convergent field.

A study on online word-of-mouth effect through blog reviews on fashion products - Based on the theory of planned behavior - (패션제품 블로그 리뷰를 통한 온라인 구전효과에 대한 연구 - 계획된 행동이론을 중심으로 -)

  • Kwon, Su Kyung;Kim, Sun-Hee
    • The Research Journal of the Costume Culture
    • /
    • v.21 no.4
    • /
    • pp.478-493
    • /
    • 2013
  • The purpose of this study is to examine the online WOM effect of blog review depending on brand awareness and message direction. The theory of planned behavior was applied to understand online WOM acceptance. A survey was conducted targeting female in 20s and 30s and 312 questionnaires were used for analysis. Frequency analysis, reliability analysis, t-test, and regression analysis were conducted using SPSS ver. 18.0. The results are as follows. First, purchase intention and online re-WOM intention are higher when brand awareness is higher. Second, subjective norm, perceived behavioral control, WOM acceptance intention, purchase intention and off-line re-WOM intention show higher values when negative information is afforded. Third, in type 1 (high brand awareness/positive message) and type 3 (low brand awareness/positive message), attitude, subjective norm and perceived behavioral control have a positive effect on WOM acceptance intention. In type 2 (high brand awareness/negative message), subjective norm and attitude have a positive effect on WOM acceptance intention. In type 4 (low brand awareness/negative message), subjective norm and perceived behavioral control have a positive effect on WOM acceptance intention. Forth, in type 1 and type 3, WOM acceptance intention has a positive effect on purchase intention, offline re-WOM intention and online re-WOM intention. In type 2 and type 4, WOM acceptance intention has a negative effect on purchase intention, and a positive effect on offline re-WOM intention. The results show that blog review has ripple effect on consumer behavior by affecting purchase intention and offline re-WOM intention.

Evaluation of Classification Algorithm Performance of Sentiment Analysis Using Entropy Score (엔트로피 점수를 이용한 감성분석 분류알고리즘의 수행도 평가)

  • Park, Man-Hee
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.22 no.9
    • /
    • pp.1153-1158
    • /
    • 2018
  • Online customer evaluations and social media information among a variety of information sources are critical for businesses as it influences the customer's decision making. There are limitations on the time and money that the survey will ask to identify a variety of customers' needs and complaints. The customer review data at online shopping malls provide the ideal data sources for analyzing customer sentiment about their products. In this study, we collected product reviews data on the smartphone of Samsung and Apple from Amazon. We applied five classification algorithms which are used as representative sentiment analysis techniques in previous studies. The five algorithms are based on support vector machines, bagging, random forest, classification or regression tree and maximum entropy. In this study, we proposed entropy score which can comprehensively evaluate the performance of classification algorithm. As a result of evaluating five algorithms using an entropy score, the SVMs algorithm's entropy score was ranked highest.

Bioactive Compounds Isolated from Pinus densiflora and koraiensis and their Applications (Pinus densiflora와 Pinus koraiensis로부터 분리된 생리활성 물질들 및 응용)

  • Kim, Nam Hee;Yoon, Sunkwon;Um, Byung-Hun;Kim, Jung Won
    • Applied Chemistry for Engineering
    • /
    • v.32 no.2
    • /
    • pp.132-138
    • /
    • 2021
  • This review investigated the types of physiologically active substances isolated and extracted from Pinus densiflora and koraiensis native to Republic of Korea, and the current status of research on their effectiveness and industrial use. They contain various bioactive substances including essential oils, polyphenols, resins, and stilbene derivatives. In recent, physiological activities such as antioxidant, anti-inflammatory, antibacterial, cataract prevention, and neuroprotection from extracts of Pinus densiflora and koraiensis have been identified by domestic researchers. The extracts have been used in different industrial fields like food, health functional foods, cosmetics, and household goods, but the high proportion of them is industrially made from exotic species. Therefore, various studies on industrial applicability are needed due to the lack of cases in which the activity is applied to actual products, with respect to the effects that have been scientifically recognized.