摘要：The COVID-19 pandemic has caused tremendous loss starting from early this year. This paper aims to investigate the change of anxiety prevalence and severity of non-graduating undergraduate students in the new semester of online learning during COVID-19 in China and also to evaluate a machine learning model based on XGBoost model. 1172 non-graduating undergraduate students aged between 18 to 22 from 34 provincial-level administrative units and 260 cities in China were enrolled to this study to fill in a sociodemographic questionnaire and the Self-Rating Anxiety Scale (SAS) twice respectively during February 15 to 17 before new semester started and March 15 to 17, 2020 one month after new semester based on online learning started. SPSS 22.0 was used to conduct t-test and single factor analysis. XGBoost models were implemented to predict the anxiety level of students one month after the start of new semester. There were 184 (15.7%, Mean=58.45, SD= 7.81) and 221 (18.86%, Mean=57.68, SD= 7.58) students met the cut-off of 50 and were screened positive for anxiety respectively in the two investigations. The mean SAS scores in the second test was significantly higher than those in the first test (P <0.05). Significant differences were also found among all males, female, students majoring arts and sciences between two studies (P <0.05). The results also showed students from Hubei province where most cases of COVID-19 were confirmed had a higher percentage of participants meeting the cut-off of being anxious. This paper applied machine learning to establish XGBoost models to predict successfully the anxiety level and changes of anxiety levels four weeks later based on their SAS scores in the first test. It was concluded that during COVID-19 Chinese non-graduating undergraduate students showed higher anxiety in the new semester based on online learning than before the new semester started. Families, universities and society should pay attention to the psychological health of non-graduating undergraduate students and take measures accordingly. It also confirmed that XGBoost model was better on the prediction accuracy compared to the traditional multiple stepwise regression model on the anxiety status of university students.
关键词：COVID-19; college students; Anxiety; new semester; machine learning; XGBoost model
