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: What kind of movies do you like? , USER: I like action, and comedy movies, and drama movies the most. , ASSISTANT: cool can you tell me what about those movies you like? , USER: With comedies, I like to laugh and enjoy it with other people, and then dramas, if if it's a good story line and it's suspenseful, that's what I like about it. And if if there's good actors and actresses in the movie. , ASSISTANT: interesting , ASSISTANT: have you seen game night?, classify_text: No, I have not.
Output:
USER