You will be given a definition of a task first, then some input of the task.
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 kind of movies do u like , USER: I really like movies in a science fiction setting. Or fantasy are my favorites. , ASSISTANT: can u name a particular movie that fits that category that you liked, and some qualities about it that you liked , USER: The Matrix, for one, has a bit of action but in a futuristic-type setting. , USER: and with well-developed characters. , ASSISTANT: thanks for describing that. and could u tell me about a movie that fits that category but you didn't like, classify_text: Let me think.
Output:
USER