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 like? , USER: I like war movies. , ASSISTANT: what do you like about war movies? , USER: I like that they depict an otherwise taboo subject, like I know that Hollywood and movies in general are a bit exaggerated and they are not necessary factually correct, but they give people like me who have never seen anything like war a glimpse into what war could or does look like. , USER: I think that's pretty cool. , ASSISTANT: Can you name a particular war movie you like?, classify_text: Saving Private Ryan is a good one.
USER