Given the task definition and input, reply with output. 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 type of movies do you like? , USER: Comedies. , ASSISTANT: okay what do you like about comedies? , USER: That they make me happy when I don't feel like I have any other reason to be happy. They give distract. , ASSISTANT: Can you tell me the title of one of your favorite movies? , USER: White Chicks, classify_text: Can you say why you like that type of movie?
ASSISTANT