During recent years, the standardisation committees on video compression and broadcast formats have worked on extending practical video frame rates up to 120 frames per second. Generally, increased video frame rates have been shown to improve immersion, but at the cost of higher bit rates. Taking into consideration that the benefits of high frame rates are content dependent, a decision mechanism that recommends the appropriate frame rate for the specific content would provide benefits prior to compression and transmission. Furthermore, this decision mechanism must take account of the perceived video quality. The proposed method extracts and selects suitable spatio-temporal features and uses a supervised machine learning technique to build a model that is able to predict, with high accuracy, the lowest frame rate for which the perceived video quality is indistinguishable from that of video at the acquisition frame rate. The results show that it is a promising tool for prior to compression and delivery processing of videos, such as content-aware frame rate adaptation.