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: Tell me what type of movies you like. , USER: I really like psychological thrillers. , ASSISTANT: Got it. Could you give me some reasons you enjoy that type of movie? , USER: I like thinking about what's going to happen next, and I like trying to figure out the plot of the story. , ASSISTANT: Ok thanks. How about a movie you really didn't like? , USER: Didn't like, classify_text: A Simple Favor
Output:
USER