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 kind of movies do you enjoy and why? , USER: I enjoy action movies. , USER: Because they're fun to watch. , ASSISTANT: Is there a particular film you enjoy? , USER: Yes. I enjoy watching the the Ninja Turtle movie. , ASSISTANT: What did you like about that film?, classify_text: That film has a lot of action in it. It has a lot of action where it's fighting bad guys.
USER