• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.1-19
• /
• 2019

Artificial intelligence (AI) is one of the main driving forces leading the Fourth Industrial Revolution. The technologies associated with AI have already shown superior abilities that are equal to or better than people in many fields including image and speech recognition. Particularly, many efforts have been actively given to identify the current technology trends and analyze development directions of it, because AI technologies can be utilized in a wide range of fields including medical, financial, manufacturing, service, and education fields. Major platforms that can develop complex AI algorithms for learning, reasoning, and recognition have been open to the public as open source projects. As a result, technologies and services that utilize them have increased rapidly. It has been confirmed as one of the major reasons for the fast development of AI technologies. Additionally, the spread of the technology is greatly in debt to open source software, developed by major global companies, supporting natural language recognition, speech recognition, and image recognition. Therefore, this study aimed to identify the practical trend of AI technology development by analyzing OSS projects associated with AI, which have been developed by the online collaboration of many parties. This study searched and collected a list of major projects related to AI, which were generated from 2000 to July 2018 on Github. This study confirmed the development trends of major technologies in detail by applying text mining technique targeting topic information, which indicates the characteristics of the collected projects and technical fields. The results of the analysis showed that the number of software development projects by year was less than 100 projects per year until 2013. However, it increased to 229 projects in 2014 and 597 projects in 2015. Particularly, the number of open source projects related to AI increased rapidly in 2016 (2,559 OSS projects). It was confirmed that the number of projects initiated in 2017 was 14,213, which is almost four-folds of the number of total projects generated from 2009 to 2016 (3,555 projects). The number of projects initiated from Jan to Jul 2018 was 8,737. The development trend of AI-related technologies was evaluated by dividing the study period into three phases. The appearance frequency of topics indicate the technology trends of AI-related OSS projects. The results showed that the natural language processing technology has continued to be at the top in all years. It implied that OSS had been developed continuously. Until 2015, Python, C ++, and Java, programming languages, were listed as the top ten frequently appeared topics. However, after 2016, programming languages other than Python disappeared from the top ten topics. Instead of them, platforms supporting the development of AI algorithms, such as TensorFlow and Keras, are showing high appearance frequency. Additionally, reinforcement learning algorithms and convolutional neural networks, which have been used in various fields, were frequently appeared topics. The results of topic network analysis showed that the most important topics of degree centrality were similar to those of appearance frequency. The main difference was that visualization and medical imaging topics were found at the top of the list, although they were not in the top of the list from 2009 to 2012. The results indicated that OSS was developed in the medical field in order to utilize the AI technology. Moreover, although the computer vision was in the top 10 of the appearance frequency list from 2013 to 2015, they were not in the top 10 of the degree centrality. The topics at the top of the degree centrality list were similar to those at the top of the appearance frequency list. It was found that the ranks of the composite neural network and reinforcement learning were changed slightly. The trend of technology development was examined using the appearance frequency of topics and degree centrality. The results showed that machine learning revealed the highest frequency and the highest degree centrality in all years. Moreover, it is noteworthy that, although the deep learning topic showed a low frequency and a low degree centrality between 2009 and 2012, their ranks abruptly increased between 2013 and 2015. It was confirmed that in recent years both technologies had high appearance frequency and degree centrality. TensorFlow first appeared during the phase of 2013-2015, and the appearance frequency and degree centrality of it soared between 2016 and 2018 to be at the top of the lists after deep learning, python. Computer vision and reinforcement learning did not show an abrupt increase or decrease, and they had relatively low appearance frequency and degree centrality compared with the above-mentioned topics. Based on these analysis results, it is possible to identify the fields in which AI technologies are actively developed. The results of this study can be used as a baseline dataset for more empirical analysis on future technology trends that can be converged.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.227-240
• /
• 2011

New concepts and ideas often result from extensive recombination of existing concepts or ideas. Both researchers and developers build on existing concepts and ideas in published papers or registered patents to develop new theories and technologies that in turn serve as a basis for further development. As the importance of patent increases, so does that of patent analysis. Patent analysis is largely divided into network-based and keyword-based analyses. The former lacks its ability to analyze information technology in details while the letter is unable to identify the relationship between such technologies. In order to overcome the limitations of network-based and keyword-based analyses, this study, which blends those two methods, suggests the keyword network based analysis methodology. In this study, we collected significant technology information in each patent that is related to Light Emitting Diode (LED) through text mining, built a keyword network, and then executed a community network analysis on the collected data. The results of analysis are as the following. First, the patent keyword network indicated very low density and exceptionally high clustering coefficient. Technically, density is obtained by dividing the number of ties in a network by the number of all possible ties. The value ranges between 0 and 1, with higher values indicating denser networks and lower values indicating sparser networks. In real-world networks, the density varies depending on the size of a network; increasing the size of a network generally leads to a decrease in the density. The clustering coefficient is a network-level measure that illustrates the tendency of nodes to cluster in densely interconnected modules. This measure is to show the small-world property in which a network can be highly clustered even though it has a small average distance between nodes in spite of the large number of nodes. Therefore, high density in patent keyword network means that nodes in the patent keyword network are connected sporadically, and high clustering coefficient shows that nodes in the network are closely connected one another. Second, the cumulative degree distribution of the patent keyword network, as any other knowledge network like citation network or collaboration network, followed a clear power-law distribution. A well-known mechanism of this pattern is the preferential attachment mechanism, whereby a node with more links is likely to attain further new links in the evolution of the corresponding network. Unlike general normal distributions, the power-law distribution does not have a representative scale. This means that one cannot pick a representative or an average because there is always a considerable probability of finding much larger values. Networks with power-law distributions are therefore often referred to as scale-free networks. The presence of heavy-tailed scale-free distribution represents the fundamental signature of an emergent collective behavior of the actors who contribute to forming the network. In our context, the more frequently a patent keyword is used, the more often it is selected by researchers and is associated with other keywords or concepts to constitute and convey new patents or technologies. The evidence of power-law distribution implies that the preferential attachment mechanism suggests the origin of heavy-tailed distributions in a wide range of growing patent keyword network. Third, we found that among keywords that flew into a particular field, the vast majority of keywords with new links join existing keywords in the associated community in forming the concept of a new patent. This finding resulted in the same outcomes for both the short-term period (4-year) and long-term period (10-year) analyses. Furthermore, using the keyword combination information that was derived from the methodology suggested by our study enables one to forecast which concepts combine to form a new patent dimension and refer to those concepts when developing a new patent.

• Journal of Science Education
• /
• v.45 no.3
• /
• pp.292-303
• /
• 2021

This study identifies the terms frequently used together with energy in online science news articles and topics of the news reports to find out how the term energy is used in everyday life and to draw implications for science curriculum and instruction about energy. A total of 2,171 online news articles in science category published by 11 major newspaper companies in Korea for one year from March 1, 2018 were selected by using energy as a search term. As a result of natural language processing, a total of 51,224 sentences consisting of 507,901 words were compiled for analysis. Using the R program, term frequency analysis, semantic network analysis, and structural topic modeling were performed. The results show that the terms with exceptionally high frequencies were technology, research, and development, which reflected the characteristics of news articles that report new findings. On the other hand, terms used more than once per two articles were industry-related terms (industry, product, system, production, market) and terms that were sufficiently expected as energy-related terms such as 'electricity' and 'environment.' Meanwhile, 'sun', 'heat', 'temperature', and 'power generation', which are frequently used in energy-related science classes, also appeared as terms belonging to the highest frequency. From a network analysis, two clusters were found including terms related to industry and technology and terms related to basic science and research. From the analysis of terms paired with energy, it was also found that terms related to the use of energy such as 'energy efficiency,' 'energy saving,' and 'energy consumption' were the most frequently used. Out of 16 topics found, four contexts of energy were drawn including 'high-tech industry,' 'industry,' 'basic science,' and 'environment and health.' The results suggest that the introduction of the concept of energy degradation as a starting point for energy classes can be effective. It also shows the need to introduce high-tech industries or the context of environment and health into energy learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.3
• /
• pp.145-154
• /
• 2016

Because of the recent interest in the u-Health and development of IT technology, a need of utilizing a medical information data has been increased. Among previous studies that utilize various data mining algorithms for processing medical information data, there are studies of association rule analysis. In the studies, an association between the symptoms with specified diseases is the target to discover, however, infrequent terms which can be important information for a disease diagnosis are not considered in most cases. In this paper, we proposed a new association rule mining system considering the importance of each term using TF-IDF weight to consider infrequent but important items. In addition, the proposed system can predict candidate diagnoses from medical text records using term similarity analysis based on medical ontology.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.113-125
• /
• 2013

Every company wants to know customer's requirement and makes an effort to meet them. Cause that, communication between customer and company became core competition of business and that important is increasing continuously. There are several strategies to find customer's needs, but VOC (Voice of customer) is one of most powerful communication tools and VOC gathering by several channels as telephone, post, e-mail, website and so on is so meaningful. So, almost company is gathering VOC and operating VOC system. VOC is important not only to business organization but also public organization such as government, education institute, and medical center that should drive up public service quality and customer satisfaction. Accordingly, they make a VOC gathering and analyzing System and then use for making a new product and service, and upgrade. In recent years, innovations in internet and ICT have made diverse channels such as SNS, mobile, website and call-center to collect VOC data. Although a lot of VOC data is collected through diverse channel, the proper utilization is still difficult. It is because the VOC data is made of very emotional contents by voice or text of informal style and the volume of the VOC data are so big. These unstructured big data make a difficult to store and analyze for use by human. So that, the organization need to automatic collecting, storing, classifying and analyzing system for unstructured big VOC data. This study propose an intelligent VOC analyzing system based on opinion mining to classify the unstructured VOC data automatically and determine the polarity as well as the type of VOC. And then, the basis of the VOC opinion analyzing system, called domain-oriented sentiment dictionary is created and corresponding stages are presented in detail. The experiment is conducted with 4,300 VOC data collected from a medical website to measure the effectiveness of the proposed system and utilized them to develop the sensitive data dictionary by determining the special sentiment vocabulary and their polarity value in a medical domain. Through the experiment, it comes out that positive terms such as "칭찬, 친절함, 감사, 무사히, 잘해, 감동, 미소" have high positive opinion value, and negative terms such as "퉁명, 뭡니까, 말하더군요, 무시하는" have strong negative opinion. These terms are in general use and the experiment result seems to be a high probability of opinion polarity. Furthermore, the accuracy of proposed VOC classification model has been compared and the highest classification accuracy of 77.8% is conformed at threshold with -0.50 of opinion classification of VOC. Through the proposed intelligent VOC analyzing system, the real time opinion classification and response priority of VOC can be predicted. Ultimately the positive effectiveness is expected to catch the customer complains at early stage and deal with it quickly with the lower number of staff to operate the VOC system. It can be made available human resource and time of customer service part. Above all, this study is new try to automatic analyzing the unstructured VOC data using opinion mining, and shows that the system could be used as variable to classify the positive or negative polarity of VOC opinion. It is expected to suggest practical framework of the VOC analysis to diverse use and the model can be used as real VOC analyzing system if it is implemented as system. Despite experiment results and expectation, this study has several limits. First of all, the sample data is only collected from a hospital web-site. It means that the sentimental dictionary made by sample data can be lean too much towards on that hospital and web-site. Therefore, next research has to take several channels such as call-center and SNS, and other domain like government, financial company, and education institute.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.311-321
• /
• 2020

The purpose of the study is to verify the effectiveness the Freshman Preliminary Health Administrators(FPHA)' Empathic Problem Solving Ability(EPSA) through the application of Medical Service Design Thinking(MSDT) conducted by undergraduate school of SNS hospital marketing education. The pre-post questionnaire survey was conducted on 39 students in the freshman year of the Department of Health Administration after applying MSDT for 15 weeks from September to December, 2019 at a college in Daegu. MSDT was positive influenced on the improvement of Empathic Imagine, Empathic interest, Empathic awakening of the FPHA' EPSA. In the analysis of key common words, the use of neutral and negative words was low, while the use of positive words was high. In order to systematically equip Empathic problem solving job competency in the age of artificial intelligence, it is meaningful to develop a program for the freshmen curriculum and to conduct a analysis of the structured and unstructured data to verify its effectiveness. Additional program development research is needed for the application of theoretical subjects.

• Journal of Information Technology Services
• /
• v.19 no.3
• /
• pp.35-56
• /
• 2020

The purpose of this study is to measure corporate personality by analyzing the internal employees' corporate reviews and to identify the impact of the representative corporate personality on the relationship between job satisfaction of internal employees and the turnover rate of the company. To this end, we first created a dictionary of words representing the corporate personality with a Word2vec method based on words explaining five corporate personalities, such as reliability, initiative, practicality, activism, and femininity, obtained from the preceding study. Next, we analyzed reviews which were written by internal employees on their companies to measure the score of corporate personality at a review level, aggregated the review level scores for each company to calculate the company level score of corporate personality, and assigned to each company the corporate personality with the maximum score among the five such scores. Also, job satisfaction and turnover rate were measured from internal employees' corporate evaluation scores and the percentage of former employees of each company who left a review on the company, respectively. This study collected datasets of corporate reviews, employee information, and corporate information from Job-Planet from 2014 to 2017, conducted a technical statistic check and correlation analysis to confirm the suitability of the datasets, and performed linear regression analysis to evaluate the research model and verify hypotheses. As a result of the analysis, the job satisfaction of the internal staff has a significant negative impact on the corporate's turnover rate. In addition, companies having a personality of reliability, initiative and femininity also showed a significant cause-and-effect relationship between job satisfaction and turnover rate and among them, job satisfaction of companies having a personality, initiative, showed a greater impact on turnover rate. In sum, we not only proposed a novel method of measuring corporate personality, but also showed that corporates need to identify its corporate personality and to utilize a different strategy to reduce their employee's turnover rate depending on the corporate personality.

• International journal of advanced smart convergence
• /
• v.5 no.2
• /
• pp.53-58
• /
• 2016

With the growing use of big data and data mining, it serves to understand how such techniques can be used to understand various relationships in the healthcare field. This study uses hierarchical methods of data analysis to explore similarities in hospitalization across several New York state counties. The study utilized methods of measuring crowding distance of data for age-specific hospitalization period. Crowding distance is defined as the longest distance, or least similarity, between urban cities. It is expected that the city of Clinton have the greatest distance, while Albany the other cities are closer because they are connected by the shortest distance to each step. Similarities were stronger across hospital stays categorized by age. Hierarchical clustering can be applied to predict the similarity of data across the 10 cities of hospitalization with the measurement of crowding distance. In order to enhance the performance of hierarchical clustering, comparison can be made across congestion distance when crowding distance is applied first through the application of converting text to an attribute vector. Measurements of similarity between two objects are dependent on the measurement method used in clustering but is distinguished from the similarity of the distance; where the smaller the distance value the more similar two things are to one other. By applying this specific technique, it is found that the distance between crowding is reduced consistently in relationship to similarity between the data increases to enhance the performance of the experiments through the application of special techniques. Furthermore, through the similarity by city hospitalization period, when the construction of hospital wards in cities, by referring to results of experiments, or predict possible will land to the extent of the size of the hospital facilities hospital stay is expected to be useful in efficiently managing the patient in a similar area.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.23 no.3
• /
• pp.279-289
• /
• 2017

Purpose: The purpose of this study is to investigate the learning experience, self-directed learning ability and self-efficacy of Japanese nursing students undergoing portfolio-based clinical practicums. Methods: The self-directed learning ability and self-efficacy of nursing students were examined using two scales. And using a text-mining approach, we constructed correspondence analysis followed by cluster analysis of open-ended responses forms. Results: The mean score of the self-directed learning ability was $60.89{\pm}5.28$ and the generalized self-efficacy was $68.37{\pm}11.56$. Moreover, the scores in the self-directed learning ability were positively correlated with scores in the generalized self-efficacy. In correspondence analysis, the distribution of extracted words showed that record was located on the negative side of the third quadrant, to the first principal component and that patient was located on the positive side of the first quadrant, contributing greatly to the second principal component. Conclusion: The results of this study contribute to approaching to "confidence, pride, stability," "growth and intention to development'' offers a key in developing self-directed learning ability. Students record what they see and learn the importance of visualizing it in learning portfolios. "Expression in detail of the learned contents" and "concerning to which objective evaluation is suggested" are important to the students.