Earticle

온라인 리뷰는 네트워크 기술의 발전을 통해 그 영향력이 확대되고 있다. 특히, 사전 정보로 통해 소비가 결정되는 영화는 온라인 리뷰가 소비자들의 영화 결정에도 중요한 영향을 미치고 있다. 이에 본 연구는 영화관련 온라인 리뷰를 영화 소비 후 소비자들의 평가 정보라 가정하고, 이를 활용한 영화 흥행성과 예측모형을 제시하고자 한다. 선행 연구를 통하여 영화관련 온라인 리뷰에 감독, 배우, 스토리, 효과 등의 독립적인 속성 및 종합적인 평가가 있음을 확인하였으며, 본 연구에서는 각 속성을 2개 이상 평가하고 있는 복합형 리뷰 10가지를 추가하여 총 15가지로 온라인 리뷰 분류하였다. 2010년 부터 2013년까지 개봉한 한국영화 중 상업영화 209개의 개봉 첫 주 온라인 리뷰를 온라인 리뷰 마이닝 을 진행하고, 최종적으로 리뷰 마이닝 결과를 판별분석을 통한 영화 흥행성적 예측모형을 제시한다. 판별분석을 실시한 결과, 온라인 리뷰로부터 도출된 감독, 배우, 효과 및 스토리 관련 평가와 개봉 첫 주 전체 온라인 리뷰 수가 유의미하게 변별하였다.

Since a movie is an experience goods, purchase can be decided upon preliminary information and evaluation. There are ongoing researches on what impact online reviews might have on movie revenues. Whereas research in the past was focused on the effect of online reviews. The influence of online reviews appears to be significant in products like a movie because it is difficult to evaluate the feature prior to “consuming” the product. Since an online review is regarded to be objective, consumers find it more trustworthy. Contrary to prior research focused on movie review ratings and volume, we focus moves on movie features related specific reviews. This research proposes a predictive model for movie revenue generation. We decided 15 criteria to classify movie features collected from online reviews through the online review mining and made up feature keyword list each criterion. In addition, we performed data preprocessing and dimensional reduction for data mining through factor analysis. We suggest the movie revenue predictive model is tested using discriminant analysis. Following the discriminant analysis, we found that online review factors can be used to predict movie popularity and revenue stream. We also expect using this predictive model, marketers and strategic decision makers can allocate their resources in more parsimonious fashion.

Purpose: The purposes of this study were to develop a prediction model for pressure injury using a machine learning algorithm and to integrate it into clinical practice. Methods: This was a retrospective study of tertiary hospitals in Seoul, Korea. It analyzed patients in 12 departments where many pressure injuries occurred, including 8 general wards and 4 intensive care units from January 2018 to May 2022. In total, 182 variables were included in the model development. A pressure injury prediction model was developed using the gradient boosting algorithm, logistic regression, and decision tree methods, and it was compared to the Braden scale. Results: Among the 1,389,660 general ward cases, there were 451 cases of pressure injuries, and among 139,897 intensive care unit cases, there were 297 cases of pressure injuries. Among the tested prediction models, the gradient boosting algorithm showed the highest predictive performance. The area under the receiver operating characteristic curve of the gradient boosting algorithm's pressure injury prediction model in the general ward and intensive care unit was 0.86 (95% confidence interval, 0.83~0.89) and 0.83 (95% confidence interval, 0.79~0.87), respectively. This model was integrated into the electronic health record system to show each patient's probability for pressure injury occurrence, and the risk factors calculated every hour. Conclusion: The prediction model developed using the gradient boosting algorithm exhibited higher performance than the Braden scale. A clinical decision support system that automatically assesses pressure injury risk allows nurses to focus on patients at high risk for pressure injuries without increasing their workload.

Purpose: The aim was to identify high-risk groups for postretirement depression among those aged 65 or older. Methods: This study used the 9th Korean Longitudinal Study of Ageing to identify the prevalence of depression among 1,879 retirees aged 65 and above and to develop a predictive model. The decision-tree-analysis method was used to construct a predictive model. Results: The highest proportion of depression, at 58.5%, was observed in males who do not engage in regular exercise and have low daily living performance. In the predictive model where age is fixed as the first branch, depression was highest at 55.4% among middle-old or old-old individuals with low oral-health-related quality of life and marital status of separated/divorced/widowed/never married. In a predictive model that first classifies by sex, the proportion of depression was highest at 53.7% for dependent males. Conclusion: This study confirmed that age, oral health, marital status, heath status, instrumental activities of daily living, activities of daily living, and regular exercise have an impact on depression. However, these factors change over time, so longitudinal studies should be conducted to understand how depression changes with them.

Purpose: This study was conducted to build a decision tree model composed of factors that predict whether or not the elderly population underwent health or cancer screening using the 2021 community health survey.Methods: This study included 74,434 and 74,417 subjects who answered for experience of health checkup or cancer screening, respectively. This study used Chi-squared test, independent t-tests, and decision tree analysis to analyze the data.Results: Regarding the health checkup, 78.1% of women received a health checkup, and among women, those aged 65-74 years who were not recipients of the basic livelihood service showed the highest participation rate of 85.0%. In case of men, those who were married and had no problems in daily activity showed the highest participation rate of 81.4%. In the case of cancer screening, for women, those who were 65-74 years old and were nonrecipients of basic livelihood benefits showed the highest participation rate of 75.3%. For men, the cancer screening rate was the highest at 74.3% in those who had no problems with mobility and were married.Conclusion: It was found that the general and health characteristics of the elderly had a great influence on the health checkup and cancer screening. In order to develop a more improved screening system, screening rates and effects should be continuously observed and studied.

Purpose Climate change affects human health and calls for health meteorological services. The purpose of this study is to find the significant predictors for the demands of the health meteorological information. Methods This study used a descriptive design through structured self-report questionnaires. Data from 956 participants who were at least 18 years old and living in Busan, Korea, were collected from June 1 to July 31, 2009. The data was analyzed using a decision tree method, one of the data mining techniques by SAS 9.1 and Enterprise Miner 4.3 program. Results Two hundred and ninety participants (30.3%) demanded the information, and 505 of them (52.8%) perceived the necessity of health meteorological information. From the decision tree method, the predictors related to the demands of the health meteorological information were determined as “the perception of the necessity of health meteorological information,” “the coping to the weather warnings” and “the importance of the weather forecasting in daily life.” In Particular, the significant different variables in the perception of the necessity of health meteorological information were “female,” “aged over 40” and “environmental diseases.” Thus, the model derived in this study is considered for explaining and predicting the demands of health meteorological information. Conclusions It can be effectively used as a reference model for future studies and is a suggested direction in health meteorological information service and policy development. We suggest health forecasting as a nursing service and a primary health care network for healthier and more comfortable life.

Purpose: This study aimed to inform a basis for nursing intervention through investigating the clinicalrisk factors for prolonged length of stay (PLOS) in patients with chronic acalculous cholecystitis (CAC)after cholecystectomy and constructing a predictive model. Methods: The prediction model for the PLOS in patients with CAC after cholecystectomy was developedusing a retrospective research design. Data were extracted from Medical Information Mart for IntensiveCare IV. Logistic regression was used to explore the influencing factors of PLOS using the interpolateddata. A variety of statistical methods, such as receiver operating characteristic (ROC) analysis, decisioncurve analysis, 5-fold cross-validation method, and SHapley Additive exPlanations, were conducted toassess, validate, and interpret the prediction model. Results: The study included 204 patients with CAC who underwent cholecystectomy. The average age was60.23 ± 14.30 years, with 65.2% experiencing a PLOS. Multivariable logistic regression analysis showedthat age (odds ratio [OR] = 1.04, 95% confidence interval [CI]: 1.01-1.08), calcium (OR = 0.48, 95% CI: 0.24-0.93), ciprofloxacin (OR = 3.08, 95% CI: 1.14-9.91), fentanyl (OR = 4.08, 95% CI: 1.36-14.53), and mild liverdisease (MLD) (OR = 0.30, 95% CI: 0.11-0.76) may be the influencing factors for PLOS. The prediction modelbased on the five variables demonstrated moderate discrimination capacity according to ROC and decisioncurve analysis. The ROC results based on the 5-fold cross-validation method revealed that the average areaunder the curve was 0.75 (95%CI: 0.67-0.83) in the training set, 0.71 (95%CI: 0.54-0.88) in the validationset, and 0.72 (95%CI: 0.53-0.90) in the test set. SHapley Additive exPlanations analysis identified age as themost influential factor, followed by calcium, fentanyl, ciprofloxacin, and MLD. Conclusion: The prediction model, based on age, calcium, fentanyl, ciprofloxacin, and MLD, demonstratedmoderate discrimination capacity in predictive PLOS in patients with CAC after cholecystectomy. These findings may support the identification of at-risk patients and inform early nursing interventions.

Purpose: Radiation-induced dermatitis (RD) is a common side-effect of therapeutic ionizing radiation that can severely affect patient quality of life. This study aimed to develop a risk prediction model for the occurrence of RD in patients with cervical carcinoma undergoing chemoradiotherapy using electronic medical records (EMRs). Methods: Using EMRs, the clinical data of patients who underwent simultaneous radiotherapy and chemotherapy at a tertiary cancer hospital between 2017 and 2022 were retrospectively collected, and the patients were divided into two groups: a training group and a validation group. A predictive model was constructed to predict the development of RD in patients who underwent concurrent radiotherapy and chemotherapy for cervical cancer. Finally, the model's efficacy was validated using a receiver operating characteristic curve. Results: The incidence of radiation dermatitis was 89.5% (560/626) in the entire cohort, 88.6% (388/438) in the training group, and 91.5% (172/188) in the experimental group. The nomogram was established based on the following factors: age, the days between the beginning and conclusion of radiotherapy, the serum albumin after chemoradiotherapy, the use of single or multiple drugs for concurrent chemotherapy, and the total dose of afterloading radiotherapy. Internal and external verification indicated that the model had good discriminatory ability. Overall, the model achieved an area under the receiver operating characteristic curve of .66. Conclusions: The risk of RD in patients with cervical carcinoma undergoing chemoradiotherapy is high. A risk prediction model can be developed for RD in cervical carcinoma patients undergoing chemoradiotherapy, based on over 5 years of EMR data from a tertiary cancer hospital.

Purpose: Body image distortion (BID) in adolescents is a crucial problem that causes both abnormal eating habits and unhealthy weight control behaviors. COVID-19 has had a negative impact on adolescents’ psychological and behavioral status, and this might influence the onset of BID in adolescents. This study aimed to develop a prediction model for BID in Korean adolescents using decision tree analysis. Methods: The decision tree analysis was used to develop a prediction model for BID in Korean adolescents using the data of 2021 Korea Youth Risk Behavior Survey Web-based (KYRBS). Results: In the present study, about one-third of the study subjects (31%, n=6,316) showed BID. The BID rate was higher in females (37.2%, node1) than in males (21.2%, node2). Female students with severe GAD-7 level and smartphone use on the weekend over 12h showed the highest rate of BID (66.9%). As to males, the BID rate was the highest (33.1%) among middle school male students who did strength training once a week or none. Conclusion: In order to reduce BID, there is a need to develop a customized BID education and management programs.

Purpose: Developing a risk prediction model for invasive fungal disease based on an analysis of the disease-related risk factors in critically ill patients in the intensive care unit (ICU) to diagnose the invasive fungal disease in the early stages and determine the time of initiating early antifungal treatment. Methods: Data were collected retrospectively from 141 critically ill adult patients with at least 4 days of general ICU stay at Sun Yat-sen Memorial Hospital, Sun Yat-sen University during the period from February 2015 to February 2016. Logistic regression was used to develop the risk prediction model. Discriminative power was evaluated by the area under the receiver operating characteristics (ROC) curve (AUC). Results: Sequential organ failure assessment (SOFA) score, antibiotic treatment period, and positive culture of Candida albicans other than normally sterile sites are the three predictors of invasive fungal disease in critically ill patients in the ICU. The model performs well with an ROC-AUC of .73. Conclusion: The risk prediction model performs well to discriminate between critically ill patients with or without invasive fungal disease. Physicians could use this prediction model for early diagnosis of invasive fungal disease and determination of the time to start early antifungal treatment of critically ill patients in the ICU.

In this research, a new Instagram popularity metric was defined, i.e. outsiders percentage (OP) of a post. Outsiders are non-followers who liked a user’s post. It was found that OP is the most effective metric if compared to engagement rate and followers growth. Regression models were tested for predicting OP, using features from user data, post data, hashtag, engagement, and image sentiment. The prediction accuracy (R2), reached up to 71.9% using Random Forest. This research also analyzed the trend of each feature against the OP. It was found that hashtag usage is the most important factor in raising OP.

Purpose: Delirium is a common syndrome in the intensive care unit (ICU), with a high incidence incritically ill children. This study aims to develop and validate a prediction model for delirium in criticallyill children, which could potentially enhance early identification and management strategies. Methods: In this prospective cohort study, we collected 1,047 critically ill children admitted to the pediatricintensive care unit (PICU) of a tertiary children's hospital from November 2021 to November 2023. Based on the risk prediction model derived from multiple logistic regression analysis performed withSPSS software, a nomogram was constructed using R software. The model's predictive performance wasevaluated through analysis of the area under the curve (AUC) of the receiver operating characteristiccurve (ROC) and the calibration curve for discriminatory ability and accuracy. Results: Among the 1,047 critically ill children, delirium occurred in 26.6% of cases. Mechanical ventilation,benzodiazepines, age 2 years, number of catheters 3, and physical restraints were independentpredictors of delirium in critically ill children. The predictive model demonstrated a sensitivity of 85.6%and a specificity of 76.1%, with a Youden index of .62. The validation analysis demonstrated an AUC of .88(95% CI: 0.86-0.90). The Hosmer-Lemeshow goodnessoffit test yielded a x2 value of 15.23 (P > .05),demonstrating satisfactory discriminatory performance and good calibration of the predictive model. Conclusions: This study provided a predictive model for the occurrence of delirium in critically ill children,enabling nurses to accurately assess delirium risk and enhance the quality of nursing care for thisvulnerable patient population.

The performance of cellular networks depends heavily on accurate traffic prediction, as it is essential for smooth service delivery and effective resource management. However, the unpredictable and constantly changing patterns of network activity make this task highly challenging. Traditional forecasting approaches often fall short in representing these complex dependencies, leading to reduced prediction accuracy and inefficiency. To address this issue, the objective of this work is to design a prediction model that is both accurate and computationally efficient. In this paper, we have proposed a lightweight hybrid prediction model integrated with an Advanced Temporal model with Attention Mechanism (ATAM). The temporal attention mechanism enhances the model’s ability to focus on relevant sequential patterns, while the hybrid architecture ensures computational efficiency and scalability for real-time deployment. The model’s performance is evaluated through Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and paired t-test demonstrating significant improvements over traditional forecasting approaches. These findings highlight that combining temporal attention with lightweight architecture enhances predictive performance while maintaining efficiency. In conclusion, the ATAM-based framework offers a reliable solution for traffic prediction in 5G and beyond cellular networks. Further our proposed model can be extended to support adaptive resource allocation strategies, thereby enabling operators to optimize network quality of service while reducing computational overhead.

Lane-changing represents not only a common driving behavior but also a potentially hazardous one. Accurately predicting lane change intentions plays a crucial role in enhancing road traffic safety and guiding autonomous vehicle planning. In this study, a Face-mesh model is used to extract salient features from complex driver behavior data. Subsequently, by using the Farneback optical flow algorithm in conjunction with the ResNet-50 neural network, important lane change cues were extracted from the vehicle surroundings. The Transformer model was optimized using the Teacher-forcing training strategy and the Scheduled-sampling method, fostering faster convergence and heightened prediction accuracy. Empirical tests had shown that this model had attained an impressive precision of 98.61%, recall of 98.24 %, and an F1 score of 98.42 % when forecasting lane change intentions 0.5 s ahead.

Purpose: This study aimed to develop a predictive model for the early identification of patients at risk of sepsis, using routinely available clinical information and laboratory test results collected during the initial phase of patient care. Methods: This retrospective analysis included electronic medical records of 22,400 adult patients who presented with suspected infection to a tertiary care university hospital in Korea between January 2013 and May 2024. Patients were classified according to Systemic Inflammatory Response Syndrome (score ≥ 2) or Quick Sequential Organ Failure Assessment (score ≥ 2), in combination with sepsis-related International Classification of Diseases, 10th revision codes. Four different machine learning models were trained and validated using five-fold cross-validation. In addition, Shapley additive explanations analysis was performed to interpret the contribution and clinical relevance of key predictive variables. Results: Among the evaluated models, CatBoost demonstrated the strongest predictive performance. Notably, platelet distribution width, alveolar?arterial oxygen difference, procalcitonin, and the arterial/alveolar oxygen ratio consistently emerged as major predictors. Importantly, several variables that did not reach statistical significance in univariate analysis nevertheless contributed substantially to overall model performance, highlighting the importance of complex, multidimensional interactions among clinical factors. Conclusion: These findings indicate that a model based on simple, routinely collected clinical data can achieve high predictive accuracy and strong generalizability. Such a tool may support early clinical decision-making by multidisciplinary teams, including nurses, across diverse real-world care settings. Further prospective studies are warranted to validate its clinical utility and to assess its potential effects on patient outcomes.

Objective: To develop and validate a clinically actionable prediction model for postoperative pulmonary complications (PPCs) in cardiac surgery patients, focusing on modifiable preoperative risk factors amenable to targeted optimization.Methods: In this prospective observational cohort study, 492 adults undergoing open-chest cardiac surgery between August 15, 2023 and December 31, 2023 were analyzed. Prespecified predictors included gas exchange variables, pulmonary function, inspiratory muscle strength, and physical performance. Univariable and multivariable logistic regression analyses were used to develop the prediction model. Discrimination was assessed by the area under the receiver operating characteristic curve (AUC).Results: A total of 90 patients (14.1%) developed PPCs after surgery. Five independent predictors were identified: elevated arterial PaCO2 (odds ratio [OR] 1.12, 95% confidence interval [CI] 1.00?1.26), oxygen desaturation (SpO2<93%) (OR 12.47, 95% CI 3.51?48.13), reduced gait speed (OR 0.17, 95% CI 0.04?0.71), lower FEV1/FVC ratio (OR 0.96, 95% CI 0.92?1.00), and diminished inspiratory muscle strength (MIP % predicted) (OR 0.96, 95% CI 0.92?0.99). The model demonstrated good discriminative ability with an AUC of 0.86 (95% CI 0.80?0.93) in the training cohort and 0.87 (95% CI 0.74?0.93) in the validation cohort.Conclusion: This parsimonious model achieved high predictive accuracy using five modifiable physiological variables. By targeting abnormalities in gas exchange, pulmonary mechanics, muscle strength, and functional reserve, the model offers a practical tool to guide individualized prehabilitation strategies for reducing PPC risk in cardiac surgery patients.

Objective To develop a new prediction model by combining independence in eating and bladder management functions, and to assess its utility in an acute care setting. Methods Patients with ischemic stroke who were admitted in our acute stroke care unit (n=250) were enrolled in this study. Functional Independence Measure (FIM) scores for eating and bladder management on the initial day of rehabilitative treatment (median, 3 days) were collected as predictive variables. These scores were divided into low (<5) and high (≥5) and categorized as values 0 and 1, respectively. From the simple summation of these two-level model values, we derived a three-level model that categorized the scores as values 0, 1, and 2. The FIMmotor scores at discharge (median, 14 days) were collected as outcome measurements. The three-level model was assessed by observing the distribution patterns of the outcome FIM-motor scores and logistic regression analyses. Results The median outcome FIM-motor score was 19 (interquartile range [IQR],13.8?45.3) for the value 0 category (n=14), 66.5 (IQR, 59.5?81.8) for the value 1 category (n=16), and 84 (IQR, 77?89) for the value 2 category (n=95) in the three-level model. Data fitting by logistic regression for FIM-motor scores of 41.3 and 61.4 reached 50% probability of values 1 and 2, respectively. Conclusion Despite the simplicity of the three-level model, it may be useful for predicting outcomes of patients with ischemic stroke in acute care.

Electrical and mechanical failures in electric vehicles (EVs) during passenger operation cause significant operational losses and elevated energy consumption, amplifying range anxiety. To address this issue, we utilized 250,000 rows of real-time data from electric trolleybuses operating in Turkiye to develop a robust artificial intelligence (AI)-based optimization model for failure mitigation. Initially, Tri layered Neural Network (TNN) was employed to create a predictive function for electrical and mechanical failures, followed by comparative analyses across six optimization algorithms widely adopted in failure prediction studies. Among these, the Developed Honey Badger Algorithm with AI Approach (DHBA) emerged as the most effective, achieving a predictive accuracy improvement of 15 % over the standard Honey Badger Algorithm (HBA). The DHBA incorporates a Dynamic Fitness-Distance Balance (DFDB) mechanism and a novel spiral motion feature to enhance search precision, leading to the DHBA-FPM (Developed-Honey Badger Algorithm - Failure Prediction Model). The final DHBA-FPM model was applied to the 10 highest-density bus routes in Turkiye to predict and optimize failures. Results indicate that applying the DHBA-FPM model across these routes yielded a 3.96 % average range increase in EVs, extending the total range by approximately 79,200 km annually. It can be concluded that the model could prevent the release of 238.7 tons/year of CO2, NO, and NO2 emissions through its potential to improve both the operational efficiency and sustainability of EVs in public transit networks.

본 연구는 질병관리청에서 제공하는 2021년 청소년건강행태조사 데이터를 활용하여 의사결정나무 분석 법으로 코로나19 시대 중 ‧ 고등학생의 성별에 따른 체질량지수를 예측하는 모델을 구현하고자 하였다. 예측 모형에서 체질량지수는 성별에 따라 유의미한 차이가 있었고, 남자 중학생의 경우에 고강도 신체활 동을 전혀 하지 않으면서 주말 동안의 스마트폰 사용 시간이 11시간 이상인 경우 비만율이 37.4%로 가장 높게 나타났다. 남자 고등학생은 고강도 신체활동을 하지 않거나 일주일에 1번 정도 하면서 학업 성적이 중간-낮음의 수준인 경우 비만 비율이 36.2%로 가장 높았다. 여중생의 경우 학업성적이 낮으면서 불안장애수준이 심각하거나 반대로 완전히 낮은 경우 비만 비율이 18.4%로 가장 높았다. 여고생의 경우 는 코로나19에 따른 경제적 상황에 크게 변화가 있으면서 주말 동안의 스마트폰 사용 시간이 9.8시간 이상인 경우에 비만율이 20.5%로 가장 높았다. 코로나19 상황 이후 비만 청소년 관리를 위하여 개인적 특성 및 상황을 고려한 맞춤형 관리프로그램의 개발과 적용이 시급하다.

This study built a prediction model for BMI by sex of middle and high school students in the COVID-19 era by using 2021 Korea Youth Risk Behavior Survey. This study used data from 30,015 middle school and 24,833 high school students. The data was analyzed by using decision tree analysis. For male middle school students, if they did not engage in strenuous physical activity and spent more than 11 hours on a smartphone during the weekend, the obesity rate was the highest at 37.4%. Male high school students, those who did 0-1time strenuous physical activity a week and had medium-low level academic performance showed the highest level of obesity(36.2%). Middle school girls, when the academic performance was low and the anxiety disorder level was severe or conversely, the obesity rate was the highest at 18.4%. High school girls, the obesity rate was the highest at 20.5% when there was a significant change in the economic situation due to COVID-19 and the time spent on smartphone over the weekend was 9.8 hours or more. It is needed to develop a customized management and counseling program for obese adolescents.

A sorption cooler, which utilizes helium-4 as a working fluid, was previously developed and tested in KAIST. The cooler consists of a sorption pump and a thermosyphon. The developed sorption cooler aims to pre-cool a certain amount of the magnetic refrigerant of an adiabatic demagnetization refrigerator (ADR) from 4.5 K to 2.5 K. To simulate the high heat capacitance of the magnetic refrigerant, liquid helium was utilized not only as a refrigerant for the sorption cooling but also as a thermal capacitor. The previous experiment, however, showed that the lowest temperature of 2.7 K which was slightly higher than the target temperature (2.5 K) was achieved due to the radiation heat leak. This excessive heat leak would not occur when the sorption cooler is completely integrated with the ADR. Thus, based on the experimentally obtained pumping speed, the prediction model for the sorption cooler is developed in this study. The presented model in this paper assumes the sorption cooler is integrated with the ADR and the heat leak is negligible. The model predicts the amount of the liquid helium and the required time for the sorption cooling process. Furthermore, it is confirmed that the performance of the sorption cooler is enhanced by reducing the volume of the thermosiphon. The detailed results and discussions are summarized.

본 연구는 미래를 이끌어갈 MZ세대의 대표 집단인 대학생의 기부행동을 설명하고 예측하고자 Ajzen & Fishbein(1980)의 합리적 행동이론을 개념적 기틀로 설정하여 예측 모형을 검증하였다. 본 연구는 수도권에 위치한 대학의 재학생 351명을 대상으로 2022년 7월부터 10월까지 자료를 수집 및 분석하였다. SPSS Window 18.0과 AMOS 17.0을 이용하여 가설모형의 적합성과 가설을 검증하기 위해 공분산 구조 방법으로 분석하였다. 분석결과, 연구모델의 모델 적합도 지수는 χ2/df=2.97(p<.001), GFI=.89, AGFI=.84, NFI=.91, CFI=.87, RMR=.08, RMSEA=.08로 나타났다. 기부경험(γ=.09, p=.049), 기부태도(γ=.13, p=.014), 공동체의식(γ=.14, p=.024), 사회공정성(γ=.18, p=.004)과 기부의도(γ=.45, p=.015)가 기부행동 증가에 직접효과가 나타났다. 또한, 기부태도(γ=.11, p=.013), 공동체의식(γ=.09, p=.009)과 기부재미(γ=.11, p=.014)가 기부의도를 매개로 하여 기부행동 증가에 영향을 주었다. 이러한 결과를 바탕으로 기부행동을 증가시키기 위하여 도출된 변인들을 중심으로 특화된 프로그램 개발 및 적용이 필요하다.

This study aims to explain and predict the donation behavior of college students, a representative group of the MZ generation who will lead the future, by verifying the prediction model. This study collected data from July to October 2022 from 351 university students. SPSS Window 18.0 and AMOS 17.0 were used to analyze the fit of the hypothesis model and verify the hypothesis using the covariance structure method. As a result of the analysis, the model fit indices of the research model were χ2/df=2.97 (p<.001), GFI=.89, AGFI=.84, NFI=.91, CFI=.87, RMR=.08, and RMSEA=.08. Donation experience (γ=.09, p=.049), donation attitude (γ=.13, p=.014), sense of community (γ=.14, p =.024), social justice (γ=.18, p =.004) and donation intention (γ=.45, p =.015) had a direct effect on increasing donation behavior. In addition, donation attitude (γ=.11, p =.013), sense of community (γ=.09, p=.009), and donation fun (γ=.11, p =.014) influenced the increase in donation behavior through donation intention. It is necessary to develop and apply specialized programs centered on the derived variables to increase donation behavior.