Exploring the Sustainable Development Path of College Volunteerism with Voluntarism in the Context of Deep Learning

Abstract

This paper first analyzes the pain points and needs of voluntary college student volunteering in conjunction with college volunteering program management. Combined with the logic of generating a sense of acquisition for college students’ volunteer service, it explores the types of motivation that drive their volunteer demand. Based on deep learning, we propose volunteer integrity neural network prediction, classify volunteer integrity, and select different data sources to compare the running time and effectiveness of four classification algorithms, namely artificial neural network, Bayesian network, decision tree and support vector machine. Volunteer portraits are established with two dimensions: natural attributes and interest attributes. Deep feature extraction is utilized to recommend college volunteer activities. Among the sources of volunteering accessibility, 72.2% of college students consider volunteering information sources to be highly important. It can be seen that college volunteer service can help strengthen the construction of volunteer service information channels.

Keywords

• neural network prediction
• deep learning
• deep feature extraction
• volunteer activity recommendation
• college volunteer service
• 11a63