You will be given a definition of a task first, then some input of the task.
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, could you tell the name of a movie that you like? , USER: pathology , ASSISTANT: What is it about this movie that you like? , USER: I like that the doctors who are seen as people of high moral are going against this moral to commit crimes and cover there murders, it's very interesting and intriguing to me. , ASSISTANT: What else? , USER: I like the suspense. I like the raunchiness, sex scenes, the murder scenes. Is very Is very on edge. I like it., classify_text: Ok. now. Could you tell the name of a movie that you dislike?
Output:
ASSISTANT