• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.165-171
• /
• 2020

Most of the stock price prediction research using text mining uses news and SNS data. However, there is a weakness that it is difficult to get honest and vivid information about companies from them. This paper deals with the problem of the prediction for the direction of stock price by doing text mining the online company reviews of internal staff indicating employee satisfaction. The comparative analysis of the prediction models for the direction of stock price showed the prediction model, which adds internal employee reviews, has better performance than those that did not. This paper presents the convergence study using natural language processing in financial engineering. In the field of stock price prediction, This paper pursued a new methodology that used employee satisfaction. In practice, it is expected to provide useful information in the field of forecasting stock price direction.

• Informatization Policy
• /
• v.27 no.1
• /
• pp.3-35
• /
• 2020

Interest in smart cities is growing; information and communication technology, urban planning, urban economy development, health, and many other areas are intertwined within smart city research and practice. The definition of smart city is evolving, and its vagueness is sometimes confusing. This review of the smart city literature tries to capture the big picture of this big idea. This review places into context work done since 2016, as earlier work is well reviewed in Albino (2015) and Cochia (2014). First is a review of the various smart city definitions. Second, an inventory of terms related to or subsumed by the smart city label are presented. Third, outcomes of indexes created to measure a city's smartness are presented. Fourth, the taxonomies used to organize the disparate content that falls under the smart city umbrella are discussed. Fifth, the most recent literature associated with six commonly recognized subgenres, namely smart economy, smart governance, smart living, smart people, smart environment, and smart mobility are reviewed. Sixth, important critiques of the smart city idea are presented.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.181-188
• /
• 2018

In this paper, we propose an analysis scheme of customer spending pattern using text mining. In proposed consumption pattern analysis scheme, first we analyze user's rating similarity using Pearson correlation, second we analyze user's review similarity using TF-IDF cosine similarity, third we analyze the consistency of the rating and review using Sendiwordnet. And we select the nearest neighbors using rating similarity and review similarity, and provide the recommended list that is proper with consumption pattern. The precision of recommended list are 0.79 for the Pearson correlation, 0.73 for the TF-IDF, and 0.82 for the proposed consumption pattern. That is, the proposed consumption pattern analysis scheme can more accurately analyze consumption pattern because it uses both quantitative rating and qualitative reviews of consumers.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.91-102
• /
• 2020

The Internet of Things (IoT) is characterized as the market where various companies compete for the same consumers. Thus, there are differences in functions and performance provided by the main business area and other characteristics of the service providers. This paper investigates whether satisfaction with the service provided depends on the characteristics of the operator by using sentiment analysis of comments. To achieve this goal, word importance analysis and sensitivity analysis are conducted on 34,310 reviews of 41 applications registered in the Google Play. The review analysis was conducted at various levels, including TD-IDF (Term frequency-inverse document frequency) value of keywords, service sectors, the origin of providers, and domestic/foreign providers. The results show that users' overall assessment of IoT services was found to be low, and smart homes received relatively high reviews compared to other services, and manufacturing-based and overseas providers received relatively higher evaluations than others.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2357-2364
• /
• 2008

In this paper, we consider the problem of exploiting a taxonomy of propositionalized attributes in order to generate compact and robust classifiers. We introduce Propositionalized Attribute Taxonomy guided Naive Bayes Learner (PAT-NBL), an inductive learning algorithm that exploits a taxonomy of propositionalized attributes as prior knowledge to generate compact and accurate classifiers. PAT-NBL uses top-down and bottom-up search to find a locally optimal cut that corresponds to the instance space from propositionalized attribute taxonomy and data. Our experimental results on University of California-Irvine (UCI) repository data set, show that the proposed algorithm can generate a classifier that is sometimes comparably compact and accurate to those produced by standard Naive Bayes learners.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.145-153
• /
• 2020

Recently, keyword extraction from social big data has been widely used for the purpose of extracting opinions or complaints from the user's perspective. Regarding this, our previous work suggested a method to improve accuracy of keyword extraction based on the notion of cohesion scoring, but its accuracy can be degraded when the number of input reviews is relatively small. This paper presents a method to resolve this issue by applying simplified morphological analysis as a postprocessing step to extracted keywords generated from the algorithm discussed in the previous work. The proposed method enables to add analysis rules necessary to process input data incrementally whenever new data arrives, which leads to reduction of a dictionary size and improvement of analysis efficiency. In addition, an interactive rule adder is provided to minimize efforts to add new rules. To verify performance of the proposed method, experiments were conducted based on real social reviews collected from online, where the results showed that error ratio was reduced from 10% to 1% by applying our method and it took 450 milliseconds to process 5,000 reviews, which means that keyword extraction can be performed in a timely manner in the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.201-207
• /
• 2022

In this paper, we propose a movie recommendation model that uses the users' ratings as well as their reviews. To understand the user's preference from multicriteria perspectives, the proposed model is designed to apply attribute-based sentiment analysis to the reviews. For doing this, it divides the reviews left by customers into multicriteria components according to its implicit attributes, and applies BERT-based sentiment analysis to each of them. After that, our model selectively combines the attributes that each user considers important to CF to generate recommendation results. To validate usefulness of the proposed model, we applied it to the real-world movie recommendation case. Experimental results showed that the accuracy of the proposed model was improved compared to the traditional CF. This study has academic and practical significance since it presents a new approach to select and use models in consideration of individual characteristics, and to derive various attributes from a review instead of evaluating each of them.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.81-91
• /
• 2018

A counterfeit product is a product that pretends to be a genuine product by pretending to be false. It can also be called a counterfeit product. This study attempts to investigate how such illegal floods of counterfeit goods affect online shopping consumers. In addition, the accessibility of various product reviews on the internet is increasing, and the product reviews are divided into positive and negative reviews, affecting the information that the customer has already, and the influence of the information acceptance on the purchase intention depending on the product involvement Respectively. Therefore, the focus of this study was to examine whether the information presentation about counterfeit products affects consumers' purchase intention, review direction (positive / negative), and involvement (high / low) control the information about counterfeit products. Therefore, this study has shown that it provides a marketing strategy to increase the intention to purchase products and products in online companies and stores in a situation where information about counterfeits is exposed to online consumers in China market.

• Journal of Korea Game Society
• /
• v.18 no.6
• /
• pp.69-82
• /
• 2018

The need of high quality VR contents has been steadily raised in recent years. Therefore, this study investigated the user's interest factors of VR game which is receiving the most attention among VR contents. We used STEAM review data and applied Text mining and Network analysis to perform this research. As a result, it was possible to confirm 4 word clusters related VR game users. Each cluster is named by 'presence', 'first person view game', 'auditory factor' and 'interaction'. This study has its meaning. First, user related research would be very helpful to develop high quality VR game. Second, it confirms that review data of VR game users can be structured, analyzed and used.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.36-48
• /
• 2020

App market has continuously been growth since its launch. The market revenues will reach about 1,000 billion US dollars in 2019. App is a core service for smartphone. Currently, there are more than 1.5 million mobile apps in App platform calling out for attention. So, if you are looking at developing a successful app, you need to have a solid marketing and distribution strategy. Online word of mouth(eWOM) is one of the most effective, powerful App marketing method. eWOM affect potential consumers' decision making, and this effect can spread rapidly through online social network. Despite the increasing research on word of mouth, only few studies have focused on content analysis. Most of studies focused on the causes and acceptance of eWOM and eWOM performance measurement. This study aims to content analysis of mobile apps review In 2013, Google researchers announced Word2Vec. This method has overcome the weakness of previous studies. This is faster and more accurate than traditional methods. This study found out the relationship between mobile app reviews and checked for reactions by Word2vec.