Conditional Semi-Supervised Data Augmentation for Spam Message Detection with Low Resource Data

TL;DR

This paper introduces CSSDA, a semi-supervised data augmentation method that leverages unlabeled data to improve spam message detection, especially in low-resource scenarios, achieving robust and balanced accuracy.

Contribution

The paper presents a novel conditional semi-supervised data augmentation framework that effectively utilizes unlabeled data for spam detection with limited labeled data.

Findings

CSSDA achieves about 85% balanced accuracy with limited labeled data.

Unlabeled data significantly enhances data augmentation and model robustness.

Ablation studies confirm the effectiveness of the proposed scheme.

Abstract

Several machine learning schemes have attempted to perform the detection of spam messages. However, those schemes mostly require a huge amount of labeled data. The existing techniques addressing the lack of data availability have issues with effectiveness and robustness. Therefore, this paper proposes a conditional semi-supervised data augmentation (CSSDA) for a spam detection model lacking the availability of data. The main architecture of CSSDA comprises feature extraction and enhanced generative network. Here, we exploit unlabeled data for data augmentation to extend training data. The enhanced generative in our proposed scheme produces latent variables as fake samples from unlabeled data through a conditional scheme. Latent variables can come from labeled and unlabeled data as the input for the final classifier in our spam detection model. The experimental results indicate that our proposed CSSDA achieves excellent results compared to several related methods both exploiting unlabeled data and not. In the experiment stage with various amounts of unlabeled data, CSSDA is the only robust model that obtains a balanced accuracy of about 85% when the availability of labeled data is large. We also conduct several ablation studies to investigate our proposed scheme in detail. The result also shows that several ablation studies strengthen our proposed innovations. These experiments indicate that unlabeled data has a significant contribution to data augmentation using the conditional semi-supervised scheme for spam detection.