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 kinds of movies do you like? , USER: I really like action movies. , ASSISTANT: Why do you like actions movies? , USER: They're fun to watch. They keep you keep you excited. There's not really too many lulls in action movies. , ASSISTANT: Alright, how about a movie you liked? , USER: I liked Them, classify_text: Why did you like that movie?
ASSISTANT