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 kinds of movies do you like? , USER: I really like romantic comedies. , ASSISTANT: Why do you like romantic comedies? , USER: They're fun. They're usually funny. They have a happy ending. They're more light-hearted in nature. And they're a nice escape. , ASSISTANT: alright , how about a movie you liked? , USER: One of my favorites is When Harry Met Sally., classify_text: Why did you like that movie?
Output:
ASSISTANT