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: can you tell me what type of movies you like? , USER: I like dramatic movies. , ASSISTANT: ok, what about dramas do you like? , USER: I like how they're all sad, profound. , ASSISTANT: great, can you tell me about a movie you really like? , USER: Forrest Gump, classify_text: what about forrest gump do you like?
ASSISTANT