JMIR Publications

ABSTRACT

Background:

Depression is a predominant feature of many psychological problems leading to extreme behaviors and, in some cases, suicide. Campus information systems keep detailed and reliable student behavioral data; however, whether this data can reflect depression and what are the differences in behavior between depressive and non-depressive students is still a research problem.

Objective:

The purpose of this paper is to investigate the behavioral patterns of depressed students by using multi-source campus data, and to explore the link between behavioral preferences and depressive symptoms. The campus data described in this paper includes basic personal information, academic performance, poverty subsidy, consumption habit, daily routine, library behavior, and meal habit, totaling 121 features.

Methods:

Campus data was proven to be useful in characterizing depressive individuals and thus could be an indicator of depression. The Mann-Whitney U-Test demonstrated that the mean values of 25 variables about the daily routine, meal habits and social behavior were significantly different between the two groups. Four factors were tagged by factor analysis of questionnaire results. The correlation between these factors and the features were computed. The results indicated that there were 25 features correlated with either 4 factors or SDS score. The statistical results indicated that depressive students were more likely to fail exams, have poor meal habits, increased night activities and decreased morning activities, and to engage less in social activities, e.g., avoiding meal times with friends. Correlation analysis showed that the somatic factor 2 (F4) was negatively correlated with the number of library visits (r=-.179, p<.001), and, compared to other factors, had the greatest impact on students' daily schedule, eating and social habits. The biggest influencing factor to poor academic performance was cognitive factor F1, and its score was found to be significantly positively correlated with fail rate (r=.185,p=.02).

Results:

The correlation between these factors and the features were computed. The results indicated that there were 25 features correlated with either 4 factors or SDS score. The statistical results indicated that depressive students were more likely to fail exams, have poor meal habits, increased night activities and decreased morning activities, and to engage less in social activities, e.g., avoiding meal times with friends. Correlation analysis showed that the somatic factor 2 (F4) was negatively correlated with the number of library visits (r=-.179, p<.001), and, compared to other factors, had the greatest impact on students' daily schedule, eating and social habits. The biggest influencing factor to poor academic performance was cognitive factor F1, and its score was found to be significantly positively correlated with fail rate (r=.185,p=.02).

Conclusions:

The results presented in this study indicate that campus data can reflect depression and its symptoms. By collecting a large number of questionnaire data and combining machine learning algorithms, it is possible to realize an identification method of depression and depressive symptoms based on campus data.