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: Hello. I like horror movies. , ASSISTANT: can you give two reasons why you like horror movies , USER: I like to feel that inside of you that scares you to death, but you still want to continue watching the movie. I like when I feel goosies all over my arms, you know? That's the reason why I like it. , ASSISTANT: Can you name a particular movie that you like? , USER: Saw, classify_text: What are the 2 reasons you like Saw?
Output:
ASSISTANT