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 like dramatic movies. , USER: Because they make me like feel like I'm not alone in the world, or the world is just like interesting and fun. Not fun. , ASSISTANT: Is there a particular film you enjoy? , USER: I like Set It Off. , ASSISTANT: What did you like about that kind of film?, classify_text: I thought it was like a cool real life story, and it made be connected to black people, which I am black, so I liked it.
USER