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 u like watching , USER: I generally like sci-fi and fantasy, and on occasion I like documentaries , ASSISTANT: why do you like those type of movies , USER: Basically, it's an extension of what I like to read in books. I love Sci-Fi fantansy and I like historical fiction and things like that. , ASSISTANT: could you name a specific movie that fits that category and tell me why you like that kind of movie , USER: I As far as sci-fi goes, I really like Blade Runner., classify_text: It feels like a very good classic movie that embodies everything I like about sci-fi. Basically anything Asimov I really like.
USER