With the development of Internet, user review data are growing rapidly, which can be analyzed through text mining and the Kano model to reveal more comprehensive customization demands of users. A research method based on big data text mining was proposed to obtain the personalized customization demands of walking sticks for the elderly. Firstly, the walking sticks for the elderly were divided into three different levels. Then typical samples were selected and the big data of users' reviews were crawled. Secondly, the text was analyzed to obtain the differences in user demands among different levels. Then, the LDA model and Delphi expert method were used to obtain user demands groups. Finally, the Kano model was used to distinguish the three types of user demands and a Fisher's exact test was used to measure the significance of differences between three groups. The basic demand, performance demand, and exciting demand were identified to guide the interface design of customized walking sticks for the elderly. The result shows that the method of combining big data mining and the Kano model can effectively obtain different types of users' personalized demands and guide the construction of customization platform, providing a scientific basis for the design of product personalized customization platform.