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: hello , ASSISTANT: What kind of movies do you like? , USER: I like documentaries. , ASSISTANT: Why do you like documentaries? , ASSISTANT: What did you like about that documentary? , ASSISTANT: Can you tell me a movie you did not like?, classify_text: Yeah, I watched about the first 5 minutes of the Ali G movie. I don't remember the title of it, but it was just absolutely terrible, gut wrenching, just absolutely awful, absolutely awful. I'm not I don't want to watch something if it's that bad, you know. I watched the first 10 minutes. I thought, this is not going to be good, so I just sort of left it at that, even though I love the TV show. It was kind of weird, because I thought it would be a lot better than what it was.
USER