During this still increasing proliferation age of mobile devices, much of human-computer interaction involves text input, and the task of typing text is provided via virtual keyboards. In a mobile setting, energy consumption is a key concern for both hardware manufacturers and software developers. Virtual keyboards are software applications, and thus, they may have a significant impact on the overall energy consumption of the underlying device.

Energy consumption analysis and optimization of mobile software is recent and active area of research. Surprisingly, there is no study analysing the energy efficiency of the most used software keyboards and evaluating the performance advantage of its features. In this paper we analyse the energy performance of virtual keyboards and its respective impact in mobile devices operation. We studied the energy performance of five of the most used keyboards in the Android ecosystem. We conduct and present the results of two studies: one where we instructed the keyboards to simulate the writing of a predefined input text, and another where we performed an empirical study with real users and we monitored the energy consumption of the device when writing the same text. Moreover, we measure and analyse the energy consumption in different keyboard scenarios, namely with or without using word prediction. Our studies show that exist relevant performance differences among the most used keyboards of the considered ecosystem, and it possible to save nearly 18% of energy by replacing the most used keyboard in Android by the most efficient one. We also showed that is possible to save both energy and time by disabling keyboard intrinsic features and that the use of word suggestions not always compensate for energy and time.