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 kinds of movies do you like? , USER: I like science fiction. , ASSISTANT: Well, tell me why do you like sci-fi? , USER: I've always been interested in astronomy, and the planets, and the solar system, and the galaxy that we live in, and the universe in general. , ASSISTANT: how about a movie you liked? , USER: I definitely liked all the Star Trek movies., classify_text: alright, Why did you like that movie?
ASSISTANT