Given the task definition and input, reply with output. You are provided with a list of converations between a "USER" and "ASSISTANT". Figure out if the conversation provided as "classify_text" is authored by "USER" or "ASSISTANT". There are maximum of 7 conversations between "USER" and "ASSISTANT" in each input

ASSISTANT: What type of movies do you enjoy? , USER: I like sci-fi movies quite a bit. , ASSISTANT: What do you enjoy about them? , USER: It's an interesting take on the future and kind of seeing what people think the future will be like and it's just neat to see how people's brains were able to come up with ideas that might be realistic. , ASSISTANT: I can definitely see why people would be interested in that especially with that imaginative aspect , ASSISTANT: What movie from that genre do you enjoy?, classify_text: I haven't seen it in a while but I really liked Gattaca.
USER