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: Can you tell me what type of movies you like? , USER: I like fantasy movies. , ASSISTANT: ok, what about fantasy movies do you like in particular? , USER: I like that they're acceptable for children to watch, that they're they're not that violent. , USER: Lets imagination run. Yeah, those are the several reasons why I like them. , ASSISTANT: ok, can you name a specific film that you really enjoyed?, classify_text: Toy Story 2.
Output:
USER