In order for a sustainable product to be successful in the market, designers must create products that are not only sustainable in reality, but are also sustainable as perceived by the customer — and reality vs. perception of sustainability can be quite different. This paper details a design method to identify perceived sustainable features (PerSFs) by collecting online reviews, manually annotating them using crowd-sourced work, and processing the annotated review fragments with a Natural Language machine learning algorithm. We analyze all three pillars of sustainability — social, environmental, and economic — for positive and negative perceptions of product features of a French press coffee carafe. For social aspects, the results show that positive PerSFs are associated with intangible features, such as giving the product as a gift, while negative PerSFs are associated with tangible features perceived as unsafe, like sharp corners. For environmental aspects, positive PerSFs are associated with reliable materials like metal while negative PerSFs are associated with the use of plastic. For economic aspects, PerSFs mainly serve as a price constraint for designers to satisfy other customer perceptions. We also show that some crucial sustainability concerns related to environmental aspects, like energy and water consumption, did not have a significant impact on customer sentiment, thus demonstrating the anticipated gap in sustainability perceptions and the realities of sustainable design, as noted in previous literature. From these results, online reviews can enable designers to extract PerSFs for further design study and to create products that resonate with customers’ sustainable values.