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 you like? , USER: drama , ASSISTANT: why do you like drama , USER: I like the stories, like a beginning, middle, and end, figuring out what's going to happen. , ASSISTANT: can you name a particular drama movie you like? , USER: The Martian, classify_text: what exactly is it about the Martians that you like
ASSISTANT