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 kind of movies do you normally watch? , USER: I really like romantic comedies, dramas, adventures, and mysteries. , ASSISTANT: What makes you like Rom Com movies? , USER: I don't know if I really like comedy, and I like the romance aspect of it. , USER: I guess on top of romantic comedies, just romance movies, too. , ASSISTANT: Have you seen The Shape of Water?, classify_text: No, I haven't.
USER