With the development of science and technology, the level of informatization construction in the education industry has been continuously improved, and a campus big data environment has gradually been formed. This article used three common classification algorithms for evaluation, using a test set to screen students with mental health problems for better education. According to the test results, the algorithm achieved a precision rate of 0.70, a recall rate of 0.59, and an F1 value of 0.68. A recognition method based on the DeepPsy network model was proposed, which used a two-dimensional convolutional neural network (2D-CNN) and a long short-term memory network (LSTM) to capture dependencies to further enhance the recognition effect. Additionally, by merging basic features and trajectory patterns, a deep learning network was created. According to the experiment, the precision rate was 0.73, and the recall rate was 0.76, with the F1 value of 0.72., making it possible to recognize 76% of students who had mental health issues.

Xin Lin, Management Model of College Students and the Influence of Mental Health Education under the Background of Big Data. International Journal of Educational Innovation and Science (2026), Vol. 7, Issue 1: 109-118. https://doi.org/10.38007/IJEIS.2026.070114.

[1] Dong H. On the Infiltration and Integration of Disciplines in Primary and Secondary School Mental Health Education Curriculum[J]. Theory and Practice of Psychological Counseling, 2021, 3(3):145-147.

[2] Kiima D. Mental health policy in Kenya -an integrated approach to scaling up equitable care for poor populations[J]. Int J Ment Health Syst, 2017, 4(1):19-19.

[3] Askari M, Noah SM, Hassan SA, Baba M. Comparison of the Effects of Communication and Conflict Resolution Skills Training on Mental Health[J]. International Journal of Psychological Studies, 2017, 5(1):5-9.

[4] Armbruster L. Mental Health Education: Editor: Sarah Benes[J]. Journal of Physical Education Recreation & Dance, 2020, 91(9):51-53.

[5] Wang X. Research on Mental Health Education for College Students[J]. International Journal of Social Science and Education Research, 2020, 3(3):153-157.

[6] Aikat J, Carsey T M, Fecho K, Jeffay K, Krishnamurthy A, Mucha PJ, et al. Scientific Training in the Era of Big Data: A New Pedagogy for Graduate Education[J]. Big Data, 2017, 5(1):12-18.

[7] Diebolt C, Franzmann G, Hippe R, Sensch J. The Power of Big Data: Historical Time Series on German Education[J]. Working Papers of BETA, 2017, 83(03):329-376.

[8] Zhao Y, Tang Q. Analysis of Influencing Factors of Social Mental Health Based on Big Data[J]. Mobile Information Systems, 2021, 2021(3):1-8.

[9] Williams MO. The relationship between climate change and mental health information-seeking: a preliminary investigation[J]. Journal of Public Mental Health, 2021, 20(1):69-78.

[10] Shatte A, Hutchinson D M, Teague S J. Machine learning in mental health: A scoping review of methods and applications[J]. Psychological Medicine, 2019, 49(9):1-23.

[11] Hafferty J D, Smith D J, Mcintosh A M. Invited Commentary on Stewart and Davis " 'Big data' in mental health research—current status and emerging possibilities"[J]. Social Psychiatry & Psychiatric Epidemiology, 2017, 52(2):1-3.

[12] Cardoso G, Xavier M, Vilagut G, Petukhova M, Alonso J, Kessler RC, et al. Days out of role due to common physical and mental conditions in Portugal: results from the WHO World Mental Health Survey[J]. BJPsych Open, 2017, 3(1):15-21.

[13] Dos S, Carlos B J, Cecilio H. Ayahuasca: what mental health professionals need to know[J]. Arch.clin.psychiatry, 2017, 44(4):103-109.