Text augmentation plays an important role in enhancing the generalization performance of language models. However, traditional methods often overlook the unique roles that individual words play in conveying meaning in text and imbalance class distribution, thereby risking suboptimal performance and compromising the model's generalization ability. This limitation motivated us to create a novel technique, Text Augmentation with Word Contributions (TAWC). Our approach tackles this problem in two core steps: Firstly, it employs analytical correlation and semantic similarity metrics to discern the relationships between words and their associated aspect polarities; and secondly, it tailors distinct augmentation strategies to individual words, based on their identified functional contributions within the text. Extensive experiments on two aspect-based sentiment analysis datasets reveal that TAWC significantly improves the classification performance of popular language models, achieving gains of up to 4%, thereby setting a new standard in the field of text augmentation.