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 type of movies do you like? , USER: I like several different types of movies. , ASSISTANT: such as? , USER: I liked the film Black Swan, which is a drama. , ASSISTANT: ooh, black swan was a good movie , USER: I agree., classify_text: what did you like ab out it?
ASSISTANT