• Title/Summary/Keyword: Structured Data

Search Result 4,007, Processing Time 0.035 seconds

A study on the classification of research topics based on COVID-19 academic research using Topic modeling (토픽모델링을 활용한 COVID-19 학술 연구 기반 연구 주제 분류에 관한 연구)

  • Yoo, So-yeon;Lim, Gyoo-gun
    • Journal of Intelligence and Information Systems
    • /
    • v.28 no.1
    • /
    • pp.155-174
    • /
    • 2022
  • From January 2020 to October 2021, more than 500,000 academic studies related to COVID-19 (Coronavirus-2, a fatal respiratory syndrome) have been published. The rapid increase in the number of papers related to COVID-19 is putting time and technical constraints on healthcare professionals and policy makers to quickly find important research. Therefore, in this study, we propose a method of extracting useful information from text data of extensive literature using LDA and Word2vec algorithm. Papers related to keywords to be searched were extracted from papers related to COVID-19, and detailed topics were identified. The data used the CORD-19 data set on Kaggle, a free academic resource prepared by major research groups and the White House to respond to the COVID-19 pandemic, updated weekly. The research methods are divided into two main categories. First, 41,062 articles were collected through data filtering and pre-processing of the abstracts of 47,110 academic papers including full text. For this purpose, the number of publications related to COVID-19 by year was analyzed through exploratory data analysis using a Python program, and the top 10 journals under active research were identified. LDA and Word2vec algorithm were used to derive research topics related to COVID-19, and after analyzing related words, similarity was measured. Second, papers containing 'vaccine' and 'treatment' were extracted from among the topics derived from all papers, and a total of 4,555 papers related to 'vaccine' and 5,971 papers related to 'treatment' were extracted. did For each collected paper, detailed topics were analyzed using LDA and Word2vec algorithms, and a clustering method through PCA dimension reduction was applied to visualize groups of papers with similar themes using the t-SNE algorithm. A noteworthy point from the results of this study is that the topics that were not derived from the topics derived for all papers being researched in relation to COVID-19 (

    ) were the topic modeling results for each research topic (
    ) was found to be derived from For example, as a result of topic modeling for papers related to 'vaccine', a new topic titled Topic 05 'neutralizing antibodies' was extracted. A neutralizing antibody is an antibody that protects cells from infection when a virus enters the body, and is said to play an important role in the production of therapeutic agents and vaccine development. In addition, as a result of extracting topics from papers related to 'treatment', a new topic called Topic 05 'cytokine' was discovered. A cytokine storm is when the immune cells of our body do not defend against attacks, but attack normal cells. Hidden topics that could not be found for the entire thesis were classified according to keywords, and topic modeling was performed to find detailed topics. In this study, we proposed a method of extracting topics from a large amount of literature using the LDA algorithm and extracting similar words using the Skip-gram method that predicts the similar words as the central word among the Word2vec models. The combination of the LDA model and the Word2vec model tried to show better performance by identifying the relationship between the document and the LDA subject and the relationship between the Word2vec document. In addition, as a clustering method through PCA dimension reduction, a method for intuitively classifying documents by using the t-SNE technique to classify documents with similar themes and forming groups into a structured organization of documents was presented. In a situation where the efforts of many researchers to overcome COVID-19 cannot keep up with the rapid publication of academic papers related to COVID-19, it will reduce the precious time and effort of healthcare professionals and policy makers, and rapidly gain new insights. We hope to help you get It is also expected to be used as basic data for researchers to explore new research directions.

  • The Determinants of Health Promoting Behavior of Industrial Workers (산업장 근로자의 건강증진행위와 자아개념 및 건강의 중요성 인식에 관한 연구)

    • Kim, Chung Nam
      • Korean Journal of Occupational Health Nursing
      • /
      • v.7 no.1
      • /
      • pp.5-19
      • /
      • 1998
    • This descriptive-correlational study was conducted to identify the major factors affecting health promoting behaviors. 344 workers who employed in four different manutacturing plants in Taegu and Kyungbuk area were selected by convenience sampling method. Data were collected from April let to April 18th, 1998 by ready structured questionaires. The purpose of this study was to offer the basic data for health promotion theory development and health promotion strategy planning. This study was based on Pender's Health Promotion Model and examined three variables health promoting behavior, self-concept and perceived importance of health. The Life Style and Health Habit Assessment scale(LHHA) developed by Pender(1982).The Self-concept scale developed by Choi(1972) and the Health Value scale developed by Wallston, Maides and Wallston(1980) were used for this study. Data was analyzed by percentage, mean. t-test. ANOVA, Pearson Correlation Coefficient, and Stepwise Multiple Regression. The major findings of this study are as follows ; 1. The average level of health promoting behavior practice was 63.2% and possible range was from 62 to 248 point. The mean score of respondent's positive self-concept was 75.8. 81.4% of respondents put a high priority on the importance of health. 2. There was a significant difference between the practice level in the category of general self care and less amount of working hours per day(P=0.000), less amount of working hours per week(P=0.000). There was a significant difference between the practice level in the category of nutrition and age(0.002), marital status(0.000), working hour per day(0.008), working hours per week(0.001), There was a significant difference between the practice level in the category of nutriton and sex(0.000), age(0.000), marital status(0.025), education level(0.000), working hours per day(0.002), working hours per week(0.006). There was a significant difference between the practice level in the category of sleep and rest and age(0.003), marital status(0.002), working hours per day(0.001), working hours per week(0.001). There was a significant difference between the practice level in the category of stress management and working hours per day(0.001), working hours per week(0.002). There was a significant difference between the practice level in the category of self-actualization and working hours per day(0.050). 3. General characteristics influencing the respodent's self-concept were level(P=0.009) and worksite(P=0.001). 4. The results of the hypothesis tests are as follows The first hypothesis, that "The respondent who have more positive self-concept will have higher scores in the practice of health promoting behavior." was supported(r=0.2973, P=0.0001). The second hypothesis that "The respondent who have higher perception level on importance of health will have higher scores in the practice health promoting behavior." was rejected(r=- 0665, P=0.2225). 5. The most important factor that affects health promoting behavior practice was working hours per week(6.0%). The combination of working hours per week, age, education level accounted for 10.0% of the variance in health promoting behavior. In conclusion, the results of this study on industrial workers supported Pender's health promotion model in partial and showed the relatedness between self concept and the practice of health promoting behavior. Further research is required to find factors influencing health promoting behaviors of industrial workers.

    • PDF

    The Empirical Study on the Effects of the Team Empowerment caused by the Team-Based Organizational Structure in KBS (팀제가 팀 임파워먼트에 미치는 영향에 관한 연구;KBS 팀제를 중심으로)

    • Ahn, Dong-Su;Kim, Hong
      • 한국벤처창업학회:학술대회논문집
      • /
      • 2006.04a
      • /
      • pp.167-201
      • /
      • 2006
    • Korean corporations are transforming their vertical operational structure to a team-based structure to compete in the rapidly changing environment and for improved performance. However, a high percentage of the respondents in KBS said that despite the appearance of the present team structure, the organization operates much like a vertically-structured organization. This result can be attributed to the lack of study and implementation toward the goal of empowerment, the key variable for the success of the team-based structure. This study aims to provide policy suggestions on how to implement the process of empowerment, by investigating the conditions that hinder the process and the attitude of the KBS employees. For the cross-sectional study, this thesis examined the domestic and international references, conducted a survey of KBS employees, personal interviews and made direct observations. Approximately 1,200 copies of the Questionnaire were distributed and 474 were completed and returned. The analysis used SPSS 12.0 software to process the data collected from 460 respondents. For the longitudinal-study, six categories that were common to this study and "The Report of the Findings of KBS Employees' View of the Team Structure" were selected. The comparative study analyzed the changes in a ten-month period. The survey findings showed a decrease of 24.2%p in the number of responses expressing negative views of the team structure and a decrease of 1.29%p in the number of positive responses. The findings indicated a positive transformation illustrating employees' improved understanding and approval of the team structure. However, KBS must address the issue on an ongoing basis. It has been proven that the employee empowerment increases the productivity of the individual and the group. In order to boost the level of empowerment, the management must exercise new, innovative leadership and build trust between the managers and the employees first. Additional workload as a result of shirking at work places was prevalent throughout all divisions and ranks, according to the survey data. This outcome leads to the conclusion that the workload is not evenly distributed or shared. And the data also showed the employees do not trust the assessment and rewards system. More attention and consideration must be paid to the team size and job allocation in order to address this matter; the present assessment and rewards system need to be complemented. The type of leadership varies depending on the characteristics of the organization's structure and employees' disposition. KBS must develop and reform its own management, leadership style to suit the characteristics of individual teams. Finally, for a soft-landing of KBS team structure, in-house training and education are necessary.

    • PDF

    A Comparative Study on Injury Severity, Self esteem, Health Locus of control and Health Promotion Lifestyles between Helmeted and Nonhelmeted Motorcycle Accident Victims (오토바이 사고환자의 안전모 착용여부에 따른 뇌 손상비교와 자아존중감, 건강통제위 성격, 건강증진행위의 비교연구)

    • 최스미
      • Journal of Korean Academy of Nursing
      • /
      • v.23 no.4
      • /
      • pp.585-601
      • /
      • 1993
    • Data on 63 patients who had had motorcycle accidents and who were admitted to four general hospitals in the Chung Chung Nam Do area from July / 1993 to August 1993 were analyzed. The tool used for this study was a structured questionnaire which consisted of ten items on self- esteem, 18 items on health locus of control and 37 items profiling health prometion lifestyle. Injury severity scores were calculated bated based on data from the patients’ medical records. The collected data were analyzed using the SPSS, yielding descriptive statistics, t-test, ANOVA, Pearson’s Product Moment Correlation. The findings of this study are as follows. 1) Of the 63 injured motorcyclists, 35(55.6%) were helmeted and 28(44.4%) were nonhelmeted, and the nonhelmeted motorcyclists were predominantly young and male. The demographic variables for the helmeted and nonhelmeted groups were heterogeneous for age and occupation. 2) The results of the comparison between the two groups showed a statistically significant difference in the injury severity score(t=-4.70, p=0.000). The helmeted group had lower scores on injury severity score (9.00±3.93) than the nonhelmeted group(14.32土5.05). More than 60% of the nonhelmeted motorcyclists had brain injuries compared to only a third of the helmeted cyclists. 3) There .was a statistically significant difference between the two groups on self esteem(t=4.5, 000). The helmeted group had a higher mean score (31.27±2.72) than the nonhelmeted group(27.46±3.80). 4) The means for Internal health locus of control (IHLC), Powerful others health locus of control (PHLC), and Chance health locus of control (CHLC) in the two groups were similar to instrument norms reported in other literature. The mean scores on the IHLC in the two groups were higher than scores on the PHLC or the CHLC. However, there was a significant difference between the mean scores for the two groups on the PHLC (t=2.85, P=0.006). 5) The mean score for the helmeted group on the health promotion lifestyle profile was higher than the mean score for the nonhelmeted group(107.30±11.10, 96.57土 15.54 respectively), and there was a significant difference between the mean scores (t=3.64, p=0.001) . The highest score for helmeted group on the health promotion lifestyle profile was in the health care domain. However, for the nonhelmeted group the highest score was in the exercise domain and the lowest score was in the health care domain. 6) With regard to the relationship between health promotion lifestyle, health locus of control and self esteem in the two groups, the correlation coefficient between health promotion lifestyle and internal health locus of control for the helmeted group was 50(p〈0.01). For the nonhelmeted group, there was no correlation between health promotion lifestyle and internal health locus of control. However, there were significant correlation between health pro-motion lifestyle and external locus of control(r=0. 46, p〈0.01), and self esteem(r=0.495, p〈0.01). 7) Among the demographic variables, age and education had an impact on individual’s self-esteem The modifying factors of age made a contribution to explaining health - promoting lifestyle. In the present study, more than 40% rf the motorcyclists were riding without a helmet. The incidence of brain injury for patients riding without a helmet was nearly twice as high in the nonhelmeted rider as compared to the helmeted rider. The nonhelmeted motorcyclists in this study had lower self-esteem, obtained a higher score on the IHLC, and were not strongly engaged in performing health promotion activities as compared to the helmeted riders. However, some of the nonhelmeted riders who had a strong belief in PHLC were positively associated with engaging in health promotion activities. Based on the results obtained from this study, strategies to promote helmet usage for motorcyclists have to be developed.

    • PDF

    The Spiritual Well-Being and the Spiritual Nursing Care of Nurses for Cancer Patients (암 환자를 돌보는 간호사의 영적안녕과 영적간호수행)

    • Yoon, Me-Ok
      • Journal of Hospice and Palliative Care
      • /
      • v.12 no.2
      • /
      • pp.72-79
      • /
      • 2009
    • Purpose: The purpose of this study was to test the correlation between the levels of spiritual well-being and spiritual nursing care of nurses for cancer patients and to provide baseline data for spiritual nursing care. Methods: In the study, there were 209 nurses involved who cared for cancer patients, and they were from Christian General Hospital in a city, Jeonju. Data were collected from September 17 to 30 in 2008 using structured questionnaires. The data were analyzed using research methods, including descriptive statistics, t-test, ANOVA, Duncan test, and Pearson correlation coefficients. Results: The mean score of spiritual well-being of nurses was $63.41{\pm}10.32$ (range $20{\sim}80$) and that of spiritual nursing care was $26.96{\pm}7.05$ (range $15{\sim}60$). There was a significant positive correlation between the spiritual well-being of nurses and their spiritual nursing care (r=.353, P=.000). Conclusion: The spiritual well-being and spiritual nursing care have a positive correlation. The level of spiritual well-being of nurses was relatively significant, whereas that of spiritual nursing care was relatively low. Therefore, it is recommended, for spiritual nursing care that nurses responsible for cancer patients should pursue more spiritual growth, attend church services regularly, and should further be educated in their care and responsibility.

    • PDF

    The Relationship between the Nurse's Reward Fit and Job Involvement${\cdot}$Organizational Commitment (간호사의 보상적합도와 직무몰입 ${\cdot}$ 조직몰입정도간의 관계 연구)

    • Kim, Jung-A
      • Journal of Korean Academy of Nursing Administration
      • /
      • v.3 no.2
      • /
      • pp.41-59
      • /
      • 1997
    • This study surveyed nurses' value of reward and recognition level of organizational reward, and measured the fit of both. It also looked into the relationship between the reward fit and attitude of nurses toward their job and organization (job involvement${\cdot}$organizational commitment). It was planned to suggest the alternative of a future reward system. The sample consisted of 625 nurses of 8 private University Hospitals. Data for this study was collected from Mar. 25 to Apr. 17 by structured questionnaire. This study examined the differences of nurses' value of reward by their demographic characteristics, and looked into the relationship between the reward fit and job involvement${\cdot}$organizational commitment. Four instruments and a demographic questionnair were used to collect the data. Developed for myself and repaired by panel of judges, the value of reward scale and organizational reward scale consisted of 34 items on five points Likert-type scale. Developed by Kanungo and repaired by panel of judges, the job involvement scale measured overall job involvement on 7 items. The organizational commitment scale was developed by Mowday et al and repaired by panel of judges on 10 items. The data was analyzed by frequency, percentage, ranking, one-way ANOVA, Pearson's correlation coefficient, Chronbach alpha coefficient, t-test, SNK test, factor analysis with SPSS/PC+ progra,.Major findings are as follows 1. The mean of nurses' value of reward is 4.2435 and job content rewards are seen as the most important(M=4.5532). The following orders are seen as follows; financial rewards(M=4.4181), human realtion rewards(M=4.4130), establishment ${\cdot}$ facilities rewards(M=4.1632), professional rewards(M=4.1117), social status or prestige rewards(M=3.9228), career rewards(M=3.8816). Of 34 indivisual reward factors, the retainment allowance is seen to be thought of as the most important thing. 2. The mean of nurses' actual reward is 2.6035. The actual reward responded to the most extremely offered is job content rewards. The following orders are seen as follows ; human relation rewards(M=2.9420), financial rewards(M=2.7682), professional rewards(M=2.4601), social status or prestige rewards(M=2.3696), career rewards(M=2.3466), establishment ${\cdot}$ facilities rewards(M=1.9364). Of 34 indivisual reward factors, medical insurance benefits are felt to be most extremely offered. 3. The mean of fit of reward is -1.6874 and that means actual reward doesn't egual the value of the reward. What is offered mostly to nurses' value of reward is human relation rewards. The following orders are seen as follows; job content rewards(M=-1.5938), career rewards(M=-1.6381), social status of prestige rewards(M=-1.6382), financial rewards(M=-1.6836), professional rewards(M=-1.6854), establishment${\cdot}$facilities rewards(M=-2.3130). Of 34 indivisual factors, the item of fered most closely to nurses' value of reward is seen as the participation in educational programs at the nursing department of the hospital. 4. The mean of nurses' job involvement is 3.1987 and SD is 0.5667. 5. The mean of murses' organizational commitment is 2.9348 and SD is 0.6124, that is seen as a little lower than job involvement. 6. Significant value of reward differences were found among nurses by their demographic characteristics such as married status, tenure, academic career. 7. The fit of reward was significant related to job involvement and organizational commitment. When generalizing the result of this study, the value of reward, which nurses consider important and appropriate offers a reward that corresponds to the nurses' value of reward. This increases nurses' job and organization devotion further, as well as hospital effectiveness. It appears that nurses have recognized that the present reward offered in hospitals doesn't come up to their expectations so I think it is urgent to plan and perform the new reward system which is in accord with the nurses' reward fit.

    • PDF

    A Study on Factors Influencing The State of Adaptation of The Hemiplegic Patients (편마비 환자의 퇴원후 적응상태와 관련요인에 대한 분석적 연구)

    • 서문자
      • Journal of Korean Academy of Nursing
      • /
      • v.20 no.1
      • /
      • pp.88-117
      • /
      • 1990
    • The purposes of this study are to delineate a profile of the state of a stroke patient's adaptation at 3 months after hospitalization and to explore the relationship between the level of adaptation and the variables which influence the adaptation of hemiplegic patients. To these ends, theoretical framework was derived basically from the stress adaptation model. The basic assumption underlying the level of adaptation is influenced by the presenting focal, contextual and residual stimuli. This group of stimuli is further operationalized and represented by a perception of stress. which is the perceived effect of the disability and by the mediating variables such as sociodemographic factors as an external conditioning variables and perceived social support and hardiness personality characteristics as an internal intervening variables. The dependent varibales in this study is the level of physical, psychological and social adaptation and is hypothesized to be a function of the interaction between 3 sets of variables namely, the perceived disability effect, external conditioning variables and internal intevening varibles. A total of fourty three subjects from 3 general hospitals in Seoul were observed and interviewed with the aid of 7 structured instruments. The data were collected twice on each subject : first at the pre-discharge period arid at 3 months post-discharge from hospital for the second time. The study was carried out for the period from February to August, 1988. The instruments used for the study include 4 existing scales and 3 scales developed by the researcher for this study. They are : 1) The ADL dependency scale and the scale of the clinical physical functions for the assessment of physical adaptation. 2) the SDS(self report of depression) to measure the level of psychological adaptation. 3) The scale for the amount of social activities for the measurement of the level of social adaptation. 4) The scale for the perceived effect of disability for the measurement of the focal stimuli. 5) The health related hardiness scale and the perceived interpersonal support self evaluation list(ISEL) for the measurement of the hardiness personality character and the perceived social support. The data obtained were analyzed using percentage, oneway ANOVA, Pearson coefficients correlation and stepwise multiple regression. The findings provide valuable information about the present level of physical adaptation at 3 months after discharge. The patient revealed a decreased ADL dependency and lowered limitation of physical function as compared with pre - discharge state. Psycholcgically, the average degree of depression at follow up was within normal range of depression. Socially, the amount of social activities was very low. The one way ANOVA and the correlational analysis revealed the relationship between the 3 sets of variables and the adaptation level as follows : 1) The perceived disability effect was related to the degree of the depression and the amount of social activities but was not related to the physical adaptation. 2) Among the sociodemographic variables, sex and education were related to the difference of ADL dependency and the change of physical function. These factors indicate that women more than men and educated more than the less educated were found more independent. The education was also related to the degree of depression suggesting that the higher the educational level, the more well adapted the patients were both physically and psychologically. Age, marital status and job state were not found to be related to the patient's adaptation level. 3) Among the internal intervening variables, the health related hardiness characteristic was related to the differences of ADL dependency, physical functions and the social activities, indicating that the higher the hardiness character the higher the level of physical and social adaptation. 4) The perceived social support, another internal intervening variable, was related to the degree of depression and the social activities. This data suggest that the higher the perception of social support, the better adapted the patients were psychogically and socially. In summarizing the results of the correlational analysis, the level of physical adaptation was influenced by sex, the years of education and the hardiness character. The level of psychological adaptation was influenced by the years of education, the perceived disability effect and the perceived social support. And the level of social adaptation was influenced by the perceived disability effect, the hardiness character and the perceived social support. The stepwise multiple regression analysis shows findings as follows : 1) The most important factor to explain the difference of ADL dependency was sex, indicating females were more independent than males. 2) The most important factor to explain the difference of physical function and the degree of depression was the patient's education level. 3) The strongest explaining factor for the amount of social activities was perceived self esteem(one of the subconcepts of perceived social support). Thus the most important factors influencing the level of adaptation were found to be sex, education, the hardiness character and self esteem. From the above findings, the significance of this study can be delineated as follows : 1) Corroboration of the assumed relationship between the various variables and the adaptation level as suggested in the conceptual model. 2) Support for the feasibility of the cognitive approach for nursing intervention such as hardness character training, counselling and teaching for self-care in the chronic patients.

    • PDF

    Correlations among Family Support, Self-Esteem and Compliance with Preventive Health. Behavior in Elderly People (노인이 지각한 가족지지와 자아존중감 및 예방적 건강행위 이행과의 관계)

    • Choi Young-A;Park Jum-Hee
      • Journal of Korean Academy of Fundamentals of Nursing
      • /
      • v.6 no.1
      • /
      • pp.141-152
      • /
      • 1999
    • The purpose of this study was to identify correlations among family support, self-esteem and compliance in preventive health behavior in elderly people. The results will provide valuable data for nursing interventions towards help the elderly lead better lives. Those who lived with elderly people in Kimchun were interviewed by the researcher and an assistant. The subjects were 191 elderly people over the age of 65. The study method used was a structured questionnaire and the data were collected from September 17th to September 31th in 1998. The tools for this study were the family support scale designed by Gang Hyun Sook, the self-esteem scale designed by Rosenberg and the preventive health behavior scale designed by Gang Yune Sook. The data were analyzed by the SAS program, Mean, SD, T-test, ANOVA, Pearson Correlation Coefficients. The results of this study are as follows : 1. The mean score for family support was 40.49. The score of family support of the elderly showed significant differences according to age(F=2.66, P<.05), spouse presence(t=4.20, P<.001), family pattern(F=4.56, P<.01), economic status (F=10.47, P<.001) and pocket money(F=10.46, P<.001). 2. The mean score for self-esteem was 29.01. The score of self-esteem of the elderly showed significant differences according to educational level(F=3.47, P<.01), spouse presence(t=2.49, P<.05), family pattern(F=3.79, P<.01), economic staus(F=15.65, P<.001) and pocket money(F=14.04, P<.001). 3. The mean score for compliance with preventive health behavior was 53.15. The score of compliance of preventive health behavior of the elderly showed significant differences according to economic status(F=9.34, P<.001) and pocket money(F=8.13, P<.001). 4. The relation between family support and self-esteem was significantly different(r=.57, P<.001). The relation between family support and compliance with preventive health behavior was significantly different(r=.44, P<.001). The relation between self-esteem and compliance with proventive health behavior was significantey different(r=.51, P<.001), In conclusion, the correlations among lamily support, self-esteem and compliance with preventive health behavior in elderly people showed significant differences.

    • PDF

    Korean Word Sense Disambiguation using Dictionary and Corpus (사전과 말뭉치를 이용한 한국어 단어 중의성 해소)

    • Jeong, Hanjo;Park, Byeonghwa
      • Journal of Intelligence and Information Systems
      • /
      • v.21 no.1
      • /
      • pp.1-13
      • /
      • 2015
    • As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

    The Effects of Job Stress of Nurses Working in the General Hospitals on Their Turnover Intention -Mediating Effects Organizational Commitment- (종합병원 간호사의 직무스트레스가 이직의도에 미치는 영향 -조직몰입의 매개효과-)

    • Kim, Gyeong-Suk;Cho, In-Sook
      • Journal of the Korean Applied Science and Technology
      • /
      • v.36 no.2
      • /
      • pp.656-667
      • /
      • 2019
    • This study is a descriptive research to grasp the effects of job stress on turnover intention and to confirm the mediating effect of organizational commitment according to the extent of job stress, organizational commitment and turnover intention in the relations between job stress and Turnover Intention of nurses working in general hospitals. Method: The subjects of this study were 199 nurses are working in general hospitals, that have more than 200 beds and less than 400 beds, located in Gwangju. I surveyed them using a structured questionnaire for collecting data from Sep. 01, 2017 to Sep. 20, 2017. The collected data were analyzed by the frequency, the percentage, t-test, ANOVA, Scheffe's Test, Pearson's Correlation Coefficient, Multiple Regression Analysis and Sobel Results: In the first step, job stress as an independent variable had a statistically significant effect on organizational commitment(${\beta}=-.321$, p<.001). In the second step, job stress, an independent variable, also had an important effect on turnover intention as a dependent variable(${\beta}=.389$, p<.001). Job stress and organizational commitment were meaningful predictor variables of turnover intention in the third step. The explanatory power of two variables was 45.5%. The value ${\beta}$ of job stress in the third step was .203(p<.001) which was smaller than its value ${\beta}$,.389(p<.001), in the second step. That meant organizational commitment had the mediating effect on turnover intention. The Sobel Test was conducted to verify the significance of the extent of the mediating effects of organizational commitment. The test result was that the value Z was -3.694 and the mediating effect of organizational commitment was significant on the relation between job stress and turnover intention(p<.002). Conclusion: this study is expected be useful to find ways to reduce subjects' turnover intention by decreasing their job stress, increasing their organizational commitment and developing intervention programs as basic data.


    (34141) Korea Institute of Science and Technology Information, 245, Daehak-ro, Yuseong-gu, Daejeon
    Copyright (C) KISTI. All Rights Reserved.