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: I'd like to discuss your movie preferences. , USER: I like musical movies. , USER: They transform me into a world that I didn't know existed, and it makes me peaceful, happy, and like I believe that I can do anything I want. , USER: The Wizard of Oz , ASSISTANT: what did you like about it? , USER: It made me believe in the ever-after in another word that I have just dreamed about., classify_text: I did not like scary movies like Screams. Scream was not one of my favorites.
Output:
USER