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: Hello, can you please name one of your favourite movie? , USER: I'll see, let me think. I really like , USER: Wonder Woman, it was very good movie. , ASSISTANT: What is it about this type of movie that you like? , USER: it's a movie about a character that I grew up with. I remember watching Wonder Woman on television when I was a kid, and I was a big fan of it then, and I'm a big fan of it now. , ASSISTANT: What else?, classify_text: I'm just a fan of the genre and
Output:
USER