Abstract: To examine the impact of incentive strategies on the quality of online reviews, this study constructs a comparative framework comprising five dimensions—timeliness, accuracy, completeness, usefulness, and credibility—and eleven associated features. Quantitative metrics are developed for each feature. To enhance analytical efficiency, the study integrates these metrics with large language models and proposes an AI-assisted quantitative analysis approach for online review texts. Based on this framework, incentivized and organic reviews were collected from G2, a professional review platform. By applying the proposed metrics and leveraging the large language model DeepSeek, an empirical analysis was conducted to identify differences between the two types of reviews. The findings indicate that incentive strategies have a relatively limited effect on the overall content of reviews but exert a significant impact on descriptions of product usage details, particularly in low-rating reviews. Consumers should pay particular attention to such details in low-rating reviews, as they may provide more accurate insights into actual product performance.