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 you like? , USER: I like action movies. , ASSISTANT: What is it about action movies do you like? , USER: They're fun and interesting to watch. , ASSISTANT: Is there an action movie that you like? , USER: Yes. I like the Harry Potter movies., classify_text: What is it about the Harry Potter movie did you like?
Output:
ASSISTANT