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: romance , ASSISTANT: Why do you like romance movies? , USER: Because they make you feel good. , ASSISTANT: Is there a romance movie you like? , USER: How to Lose a Guy in 10 Days, classify_text: and why did you like that movie?
ASSISTANT