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: Hello. What kind of movies do you like? , USER: I like action movies , ASSISTANT: Why do you like actions? , USER: Because of the guns. , ASSISTANT: what else? , USER: the scenes, classify_text: Can you name a particular movie that you like?
Output:
ASSISTANT