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 dramas just because they're central to real life experiences. , ASSISTANT: Is there a particular film you enjoy? , USER: the hate you The Hate U Give , ASSISTANT: What did you like about that kind of film? , USER: It was depicting real life. And definitely the the information that was done with race, I thought it was needed to be known., classify_text: Is there a particular movie you don't enjoy?
ASSISTANT