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: can you tell me what types of movies you like? , USER: I like comedy movies. , ASSISTANT: ok, what about comedies do you like? , USER: They make me laugh, they make me happy, they make me they make me feel sense of enjoyment. , USER: The movie will take take away from the stress that I maybe feeling before I watch it. , ASSISTANT: got it, can you name a specific movie you really enjoyed?, classify_text: The Waterboy.
USER