According to an embodiment an electronic device includes at least one sensor, a display, a memory, and a processor operatively connected to the at least one sensor, the display, and the memory. The memory is configured to store instructions that, when executed, the processor is configured to recognize a context of a user by using the at least one sensor based on at least one of a speed of the electronic device, a location of the electronic device, a level of external noise, an external illuminance, personal information of the user, or a connection state between the electronic device and an external electronic device. The processor is also configured to control an execution environment of a voice assistant application based on the recognized context.