• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Korean Journal of Occupational Health Nursing
• /
• v.11 no.1
• /
• pp.13-30
• /
• 2002

Industrial shift workers feels suffer mental stresses which are caused by unfamiliar day sleep, noisy environment, sleeping disorder by bright light, unusual contacts with family, difficulty in meeting with friends or having formal social meetings and other social limitations such as the use of transportation. Such stresses influence health of the workers negatively. Thus the health promotion policy for shift workers should be made considering the workers' ways of living and shift work specially. This study attempted to provide basic information for development of the health promotion program for industrial shift workers by examining predictive factors influencing health promotion behaviors of those workers. In designing the study, three power generation plants located in Pusan and south Kyungsang province were randomly selected and therefrom 280 workers at central control, boiler and turbine rooms and environmental chemistry parts whose processes require shift works were sampled as subjects of the study. Data were collected two times from September 17 to October 8, 1999 using questionnaires with helps of safety and health managers of the plants. The questionnaires were distributed through mails or direct visits. Means for the study included the measurement tool of health promotion behavior provided by Park(1995), the tool of self-efficacy measurement by Suh(1995), the tool of internal locus of control measurement by Oh(1987), the measurement tool of perceived health state by Park(1995) and the tool of social support measurement by Paek(1995). The collected data were analyzed using SPSS program. Controlling factors of the subjects were evaluated in terms of frequency and percentage ratio Perceived factors and health promotion behaviors of the subjects were done so in terms of mean and standard deviation, and average mark and standard deviation, respectively. Relations between controlling and perceived factors were analyzed using t-test and ANOVA and those between perceived factors and the performance of health promotion behaviors, using Pearson's Correlation Coefficient. The performance of health promotion behaviors was tested using t-test, ANOVA and post multi-comparison (Scheffe test). Predictive factors of health promotion behavior were examined through the Stepwise Multiple Regression Analysis. Results of the study are summarized as follows. 1. The performance of health promotion behaviors by the subjects was evaluated as having the value of mean, $161.27{\pm}26.73$ points(min.:60, max.:240) and average mark, $2.68{\pm}0.44$ points(min.:1, max.:4). When the performance was analyzed according to related aspects, it showed the highest level in harmonious relation with average mark, $3.15{\pm}.56$ points, followed by hygienic life($3.03{\pm}.55$), self-realization ($2.84{\pm}.55$), emotional support($2.73{\pm}.61$), regular meals($2.71{\pm}.76$), self-control($2.62{\pm}.63$), health diet($2.62{\pm}.56$), rest and sleep($2.60{\pm}.59$), exercise and activity($2.53{\pm}.57$), diet control($2.52{\pm}.56$) and special health management($2.06{\pm}.65$). 2. In relations between perceived factors of the subjects(self-efficacy, internal locus of control, perceived health state) and the performance of health promotion behaviors, the performance was found having significantly pure relations with self-efficacy (r=.524, P=.000), internal locus of control (r=.225, P=.000) and perceived health state(r=.244, P=.000). The higher each evaluated point of the three factors was, the higher the performance was in level. 3. When relations between the controlling factors(demography-based social, health-related, job-related and human relations characteristics) and the performance of health promotion behaviors were analyzed, the performance showed significant differences according to marital status (t=2.09, P= .03), religion(F=3.93, P= .00) and participation in religious activities (F=8.10, P= .00) out of demography-based characteristics, medical examination results (F=7.20, P= .00) and methods of the collection of health knowledge and information(F=3.41, P= .01) and methods of desired health education(F=3.41, P= .01) out of health-related characteristics, detrimental factors perception(F=4.49, P= .01) and job satisfaction(F=8.41, P= .00) out of job-related characteristics and social support(F=14.69, P= .00) out of human relations characteristics. 4. The factor which is a variable predicting best the performance of health promotion behaviors by the subjects was the self-efficacy accounting for 27.4% of the prediction, followed by participation in religious activities, social support, job satisfaction, received health state and internal locus of control in order all of which totally account for 41.0%. In conclusion, the predictive factor which most influence the performance of health promotion behaviors by shift workers was self-efficacy. To promote the sense, therefore, it is necessary to develop the nursing intervention program considering predictive factors as variables identified in this study. Further industrial nurses should play their roles actively to help shift workers increase their capability of self-management of health.

• The Journal of Korean society of community based occupational therapy
• /
• v.8 no.1
• /
• pp.33-44
• /
• 2018

Objective : This study aims to review research trends in driving rehabilitation for the disabled in South Korea since 2000 suggesting research directions for clinicians and researchers. Methods : Fifty eight articles in 16 journals listed in accredited or candidate journal lists of National Research Foundation of Korea from January, 2000 to December, 2016 were reviewed. 'Driving rehabilitation' and 'driving for disabled' were used as search terms. Descriptive statistics were used to classify articles according to study methodology, levels of evidence, study participants, research topics, and academic associations or official journals. Results : Fifty percent of analyzed researches have been published since 2012. Twenty-two studies (37.9%) were published as group comparison and correlational research. Only seven studies (12.1%) were included in evidence level I. There were 19 studies (38.8%) conducted with brain-injured patients among 49 studies including participants. The Korean Society of Occupational Therapy Journal, having published 15 studies (25.9%) about driving rehabilitation, ranked first among the analyzed journals. In research topic, 15 (25.9%) studies were performed about clinical evaluation. Conclusion : The present study showed that the quality of driving rehabilitation-related studies has been increasing, but more intervention-based researches need to be carried out and it is also necessary to carry out various researches in related fields in order to establish efficient driving rehabilitation in Korea.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.373-381
• /
• 2016

This research is a descriptive correlation research to examine the relationship among stress, coping behaviors, and perceived social support in school-age children. Students in third, fourth, and fifth grades at one elementary school in A metropolitan city were included for this research. A researcher of the study visited the elementary school and obtained appropriate approval to conduct this survey. Then, a total of 481 students answered the questionnaire; finally, the questionnaires of 409 students were analyzed after excluding 72 questionnaires due to unreliable responses. Descriptive statistics, T-test, ANOVA, and Pearson's correlation were used to analyze the collected data with SPSS 13.0. In the stress scores, academic stress was associated with the highest score ($9.30{\pm}4.41$). With respect to stress coping behaviors, lower-grade students showed to have significantly higher scores in coping behavior of pursuing social support than higher-grade students (F=3.181, p=.043); male students had higher scores in aggressive coping behavior than female students (t=-3.399, p=.001). Perceived social support scores were higher in the following order: family members ($33.01{\pm}7.61$), friends ($28.43{\pm}7.89$), and teachers ($25.71{\pm}6.30$). Female students had higher scores in perceived social support from friends (t=3.842, p=.000) and teachers (t=3.037, p=.003) than the male students. As the stress scores increased, passive coping behaviors (r=.410, p=.000) and aggressive coping behaviors (r=.445, p=.000) have been significantly increased. As perceived social support is higher, active coping behaviors (r=.455, p=.000) and coping behaviors to pursue social support (r=.429, p=.000) were significantly increased. Therefore, we can conclude that stress management is very significant for children. It would be necessary to develop nursing intervention programs in order to reduce the aggressive and passive coping behaviors of children and encourage perceived social support.

• Korean Journal of Culture and Social Issue
• /
• v.18 no.4
• /
• pp.505-532
• /
• 2012

The purpose of this study was to examine the relationship among the growth period wounds, inferiority complex and personality disorder of teenaged students, which affected their mental health. The subjects in this study were 2,110 secondary students. After a survey was conducted, the collected data were analyzed. Whether there would be any differences among the adolescents in those factors were analyzed, and multiple regression analysis and path analysis were carried out. As a result, there were relatively more significant problems with the growth period wounds, inferiority complex, personality disorder and mental health of the students who were girls, who were high schoolers, whose household economy was more vulnerable and whose academic standing was lower. The growth period wound that exerted the largest significant influence on inferiority complex was happiness, followed by wound of security and wound of recognition, and the growth period wound that had the greatest significant impact on personality disorder was happiness, followed by wound of security, wound of confidence, wound of love and wound of equity. The growth period wound that exercised the biggest influence on mental health was happiness, followed by wound of security, wound of confidence, wound of love and wound of equity. As for the influence of the variables related to mental health, the indirect effects of the growth period wounds through personality disorder and inferiority complex were greater than their direct effects. The findings of the study suggest that growth period wounds are likely to lead to inferiority complex and personality disorder and ultimately to the injury of mental health, and indicate the importance of healthy family environments and of educational environments in the growth period.and mental health was analyzed, there was a statistically significant positive(+) correlation among all the variables. Third, the wound factors related to happiness and stability were identified as the factors that affected inferiority complex among the growth period wound factors. Personality disorder was found to be under the influence of the wound factors related to happiness, stability, love, confidence and a sense of equality in the growth period, and mental health was found to be affected by the wound factors related to happiness, stability, confidence, love and a sense of equality. Fourth, the growth period wounds had a direct impact on mental health, and inferiority complex played a significant mediating role at that time. Every subfactor of personality disorder also produced significant mediating effects except the wound factor of pride. The above-mentioned findings suggest that every possible effort should be made to let secondary students get hurt less to promote their mental health and resolve their mental health problems, and that professional counseling intervention and institutional assistance are required to help them to remove their inferiority complex and personality disorder.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.231-252
• /
• 2021

Artificial intelligence (AI) is a key technology that will change the future the most. It affects the industry as a whole and daily life in various ways. As data availability increases, artificial intelligence finds an optimal solution and infers/predicts through self-learning. Research and investment related to automation that discovers and solves problems on its own are ongoing continuously. Automation of artificial intelligence has benefits such as cost reduction, minimization of human intervention and the difference of human capability. However, there are side effects, such as limiting the artificial intelligence's autonomy and erroneous results due to algorithmic bias. In the labor market, it raises the fear of job replacement. Prior studies on the utilization of artificial intelligence have shown that individuals do not necessarily use the information (or advice) it provides. Algorithm error is more sensitive than human error; so, people avoid algorithms after seeing errors, which is called "algorithm aversion." Recently, artificial intelligence has begun to be understood from the perspective of the augmentation of human intelligence. We have started to be interested in Human-AI collaboration rather than AI alone without human. A study of 1500 companies in various industries found that human-AI collaboration outperformed AI alone. In the medicine area, pathologist-deep learning collaboration dropped the pathologist cancer diagnosis error rate by 85%. Leading AI companies, such as IBM and Microsoft, are starting to adopt the direction of AI as augmented intelligence. Human-AI collaboration is emphasized in the decision-making process, because artificial intelligence is superior in analysis ability based on information. Intuition is a unique human capability so that human-AI collaboration can make optimal decisions. In an environment where change is getting faster and uncertainty increases, the need for artificial intelligence in decision-making will increase. In addition, active discussions are expected on approaches that utilize artificial intelligence for rational decision-making. This study investigates the impact of artificial intelligence on decision-making focuses on human-AI collaboration and the interaction between the decision maker personal traits and advisor type. The advisors were classified into three types: human, artificial intelligence, and human-AI collaboration. We investigated perceived usefulness of advice and the utilization of advice in decision making and whether the decision-maker's personal traits are influencing factors. Three hundred and eleven adult male and female experimenters conducted a task that predicts the age of faces in photos and the results showed that the advisor type does not directly affect the utilization of advice. The decision-maker utilizes it only when they believed advice can improve prediction performance. In the case of human-AI collaboration, decision-makers higher evaluated the perceived usefulness of advice, regardless of the decision maker's personal traits and the advice was more actively utilized. If the type of advisor was artificial intelligence alone, decision-makers who scored high in conscientiousness, high in extroversion, or low in neuroticism, high evaluated the perceived usefulness of the advice so they utilized advice actively. This study has academic significance in that it focuses on human-AI collaboration that the recent growing interest in artificial intelligence roles. It has expanded the relevant research area by considering the role of artificial intelligence as an advisor of decision-making and judgment research, and in aspects of practical significance, suggested views that companies should consider in order to enhance AI capability. To improve the effectiveness of AI-based systems, companies not only must introduce high-performance systems, but also need employees who properly understand digital information presented by AI, and can add non-digital information to make decisions. Moreover, to increase utilization in AI-based systems, task-oriented competencies, such as analytical skills and information technology capabilities, are important. in addition, it is expected that greater performance will be achieved if employee's personal traits are considered.