Optimizing University Recruitment Campaigns through Big Data and AI-Driven Communication Strategies: A Case Study of the “Tianfu Ambassador” Program

Abstract

This study investigates the optimization of university recruitment campaigns through the application of big data and artificial intelligence (AI) technologies, using the “Tianfu Ambassador” program at Tianfu College of Southwestern University of Finance and Economics as a case study. By leveraging AI-driven content recommendation algorithms and big data analysis, the study evaluates the communication effectiveness of various new media platforms and content formats. The findings reveal that short-video and live-streaming formats on Douyin (the Chinese version of TikTok) significantly enhance awareness, attitudes, and behavioral conversion among potential students compared to traditional text-based content. Key variables such as content credibility, interaction depth, and algorithm-based recommendation intensity are identified as significant predictors of application intentions. The study proposes strategies for optimizing recruitment campaigns, including user-portrait-oriented precise content distribution, enhanced student-driven co-creation mechanisms, and platform-differentiated operation. These strategies are supported by real-time data monitoring and AI-driven evaluation frameworks to improve the efficiency and sustainability of university recruitment communication systems in the new media environment.In addition, this paper designs and implements an interpretable CTR proxy model to quantify the marginal effect of algorithmic recommendation intensity on application willingness, achieving an AUC of 0.847, significantly enhancing regression explanatory power.By introducing an interpretable CTR-proxy model, we quantify algorithmic recommendation intensity (ARI) and verify its significant positive effect on application intention (β = 0.19, p < 0.001), filling the technical gap in prior higher-education communication studies.

Ähnliche Arbeiten