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 to watch, generally , USER: Generally I like to stay with science fiction movies, anything that's paranormal or futuristic or anything like that. , ASSISTANT: can u name a movie that fits that category that you like , USER: Yes, the Terminator 2 was a really great movie. , ASSISTANT: what qualities of that movie did u like most? , USER: A great science fiction story with time travel, good characters, and a really good plot that actually made sense., classify_text: thanks for sharing. how about a movie in that category that you didn't like
ASSISTANT