Article: Social psycho-emotional characterisation of college students based on semi-supervised learning Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.1 pp.117 - 130 Abstract: Texts generated by college students through social sharing are characterised by emotional richness and psychological vulnerability. To address the issue that existing social-psycho-emotional profiling methods for college students rely on the size of the labelled dataset and have unsatisfactory classification results, this article first optimises semi-supervised learning (MSASL), which composes the samples and incorporates a smoothness loss while imposing consistency constraints. The BERT model is then used to obtain a semantic representation of the social text, using interactive attention to capture important feature information related to the opinion tendency of the topic words. Finally, semi-supervised GAN (MSASL-GAN) is applied to optimise the text feature representation, and the sentiment feature classification results are output through the fully connected layer. The experimental results show that the classification accuracy of the proposed method is improved by 5.01%-11.51% compared with the comparison model. Inderscience Publishers - linking academia, business and industry through research

Title: Social psycho-emotional characterisation of college students based on semi-supervised learning

Authors: Weihua Li

Addresses: School of Culture and Arts, Xinjiang Institute of Engineering, Urumqi, 830023, China

Abstract: Texts generated by college students through social sharing are characterised by emotional richness and psychological vulnerability. To address the issue that existing social-psycho-emotional profiling methods for college students rely on the size of the labelled dataset and have unsatisfactory classification results, this article first optimises semi-supervised learning (MSASL), which composes the samples and incorporates a smoothness loss while imposing consistency constraints. The BERT model is then used to obtain a semantic representation of the social text, using interactive attention to capture important feature information related to the opinion tendency of the topic words. Finally, semi-supervised GAN (MSASL-GAN) is applied to optimise the text feature representation, and the sentiment feature classification results are output through the fully connected layer. The experimental results show that the classification accuracy of the proposed method is improved by 5.01%-11.51% compared with the comparison model.

Keywords: sentiment profiling; semi-supervised learning; SSL; BERT model; interactive attention; generative adversarial network; GAN.

DOI: 10.1504/IJICT.2025.144014

International Journal of Information and Communication Technology, 2025 Vol.26 No.1, pp.117 - 130

Received: 27 Oct 2024
Accepted: 23 Nov 2024
Published online: 20 Jan 2025 *

Title: Social psycho-emotional characterisation of college students based on semi-supervised learning

Keep up-to-date