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: I'd like to discuss your movie preferences. , USER: Okay. I generally prefer comedies. , ASSISTANT: what do you like about comedies? , ASSISTANT: nice, so you think they are good distractions? , USER: Yeah. Yeah. In moderation, they are. , ASSISTANT: can you name a comedy that you really liked?, classify_text: Yeah, Superbad.
USER