• Journal of Korea Multimedia Society
• /
• v.5 no.1
• /
• pp.105-113
• /
• 2002

XML documents, which are becoming new standard for expressing and exchanging data in the Internet, don't have defined schema. It is not adequate to directly apply XML documents to the existing SQL or OQL. Research on how to extract schema for XML documents and query language is going on actively. Fer users' query, the results could be too many or too less. It is important to give the users adequate results. This paper suggests the way to extract many levelized schema according to the frequency of element occurrence in XML documents. The Schema can be reduced or extended to correspond to the users'query more flexibly.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• ETRI Journal
• /
• v.43 no.1
• /
• pp.95-108
• /
• 2021

Application (app) ratings are feedback provided voluntarily by users and serve as important evaluation criteria for apps. However, these ratings can often be biased owing to insufficient or missing votes. Additionally, significant differences have been observed between numeric ratings and user reviews. This study aims to predict the numeric ratings of Google apps using machine learning classifiers. It exploits numeric app ratings provided by users as training data and returns authentic mobile app ratings by analyzing user reviews. An ensemble learning model is proposed for this purpose that considers term frequency/inverse document frequency (TF/IDF) features. Three TF/IDF features, including unigrams, bigrams, and trigrams, were used. The dataset was scraped from the Google Play store, extracting data from 14 different app categories. Biased and unbiased user ratings were discriminated using TextBlob analysis to formulate the ground truth, from which the classifier prediction accuracy was then evaluated. The results demonstrate the high potential for machine learning-based classifiers to predict authentic numeric ratings based on actual user reviews.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.10
• /
• pp.215-225
• /
• 2022

This study investigates employees' online reviews, conducts in-depth text topic mining, effectively summarizes the dimensions of employer brand value, and seeks effective ways to build employer brands from a multi-dimensional perspective. This study employs samples of employer reviews, filter keywords according to word frequency-inverse document frequency, builds a review network containing the same keywords, explore the community and summarize the theme dimensions. Simultaneously, it makes a dynamic comparison and analysis of the employer brand value dimension of different industries and enterprises. The study shows that the community exploration theme can be summarized into 11 dimensions of employer brand value, and the dimensions of employer brand value are significantly different across industries and among different enterprises within the industry. The attention to the employer brand value dimension has a significant time change. Various industries pay increasing attention to the dimension of work intensity and career development, while employers pay steady attention to the dimension of welfare benefits. The findings of this study suggest that seeking the heterogeneity of employer brand resources from the multi-dimensional differences and changes is an effective way to improve the competitiveness of enterprises in the human capital market.

• Journal of muscle and joint health
• /
• v.27 no.3
• /
• pp.255-267
• /
• 2020

Purpose: The purpose of this study is to compare topics through keywords related to nurses in internet portals and social media Pre coronavirus disease (COVID-19) era and during the COVID-19 era. Methods: For six months before and during the outbreak of COVID-19 in Korea, "nurse" was searched on the internet. For data collection, we implemented web crawlers in programming languages such as Python and collected keywords. The keywords collected were classified into three domains of topic Modeling. Results: The keyword 'nurse' increased by 15% during COVID-19 era. Keywords that ranked high in Term Frequency - Inverse Document Frequency (TF-IDF) values were before COVID-19, such as "nurse" and "C-section". during COVID-19, however, they were not only "nurse" but also "emergency" and "gown" related to pandemics. Conclusion: Various topics were being uploaded into the internet media. Nursing professionals should be interested in the text that is revealed in the internet media and try to continuously identify and improve problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2188-2203
• /
• 2021

With the rapid development of mobile Internet, smart phones have been widely popularized, among which Android platform dominates. Due to it is open source, malware on the Android platform is rampant. In order to improve the efficiency of malware detection, this paper proposes deep learning Android malicious detection system based on behavior features. First of all, the detection system adopts the static analysis method to extract different types of behavior features from Android applications, and extract sensitive behavior features through Term frequency-inverse Document Frequency algorithm for each extracted behavior feature to construct detection features through unified abstract expression. Secondly, Long Short-Term Memory neural network model is established to select and learn from the extracted attributes and the learned attributes are used to detect Android malicious applications, Analysis and further optimization of the application behavior parameters, so as to build a deep learning Android malicious detection method based on feature analysis. We use different types of features to evaluate our method and compare it with various machine learning-based methods. Study shows that it outperforms most existing machine learning based approaches and detects 95.31% of the malware.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4706-4724
• /
• 2020

With various structured data, such as the company size, loan balance, and savings accounts, the voice of customer (VOC), which is text data containing contact history and counseling details was analyzed in this study. To analyze unstructured data, the term frequency-inverse document frequency (TF-IDF) analysis, semantic network analysis, sentiment analysis, and a convolutional neural network (CNN) were implemented. A performance comparison of the models revealed that the predictive model using the CNN provided the best performance with regard to predictive power, followed by the model using the TF-IDF, and then the model using semantic network analysis. In particular, a character-level CNN and a word-level CNN were developed separately, and the character-level CNN exhibited better performance, according to an analysis for the Korean language. Moreover, a systematic selection model for optimal text mining techniques was proposed, suggesting which analytical technique is appropriate for analyzing text data depending on the context. This study also provides evidence that the results of previous studies, indicating that individual customers leave when their loyalty and switching cost are low, are also applicable to corporate customers and suggests that VOC data indicating customers' needs are very effective for predicting their behavior.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.147-159
• /
• 2022

Nowadays, various social media platforms are widely spread and people closely use such platforms in daily life. By doing so, social influencers with a large number of subscribers, views, and comments have huge impact in our society. Following this trend, many companies are actively using influencers for marketing purpose to promote their products and services. In this study, we extract the speeches of influencers from videos for game marketing and analyze them using various text mining techniques. In the analysis, we distinguish game videos leading to successful marketing and failed marketing, and we explore and compare the linguistic features of the influencers for successful and failed marketings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.3029-3042
• /
• 2022

For over half a century, the United States (US) and its coalition military aircrafts have been using Ultra High Frequency (UHF) band analog modulation (AM) radios in ground-to-air communication and short-range air-to-air communications. Evolving from this, since 2007, the US military and the North Atlantic Treaty Organization (NATO) adopted HAVE QUICK to be used by almost all aircrafts, because it had been revealed that intercepting and jamming of former aircraft communication signals was possible, which placed a serious threat to defense systems. The second-generation Anti-jam Tactical UHF Radio for NATO (SATURN) was developed to replace HAVE QUICK systems by 2023. The NATO Standardization Agreement (STANAG) 4372 is a classified document that defines the SATURN technical and operational specifications. In preparation of this future upgrade to SATURN systems, in this paper, the SATURN technical and operational specifications are reviewed, and the network synchronization, frequency hopping, and communication setup parameters that are controlled by the Network (NET) Time, Time Of Day (TOD), Word Of Day (WOD), and Multiple Word of Day (MWOD) are described in addition to SATURN Edition 3 (ED3) and future Edition 4 (ED4) basic features. In addition, an anti-jamming performance analysis (in reference to partial band jamming and pulse jamming) and the time delay queueing model analysis are conducted based on a SATURN transmitter and receiver assumed model.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.421-431
• /
• 2023

Nuclear power plants (NPPs) have technical specifications (Tech Specs) to ensure that the equipment and key operating parameters necessary for the safe operation of the power plant are maintained within limiting conditions for operation (LCO) determined by a safety analysis. The LCO of Tech Specs that identify the lowest functional capability of equipment required for safe operation for a facility must be complied for the safe operation of NPP. There have been previous studies to aid in compliance with LCO relevant to rule-based expert systems; however, there is an obvious limit to expert systems for implementing the rules for many situations related to LCO. Therefore, in this study, we present a retrieval methodology for similar LCO cases in determining whether LCO is met or not met. To reflect the natural language processing of NPP features, a domain dictionary was built, and the optimal term frequency-inverse document frequency variant was selected. The retrieval performance was improved by adding a Boolean retrieval model based on terms related to the LCO in addition to the vector space model. The developed domain dictionary and retrieval methodology are expected to be exceedingly useful in determining whether LCO is met.