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 tell me, What type of movies do you like? , USER: I like thrillers. , USER: And fantasy movies. , ASSISTANT: okay. Great. Why do you like fantasy movies? , USER: They are fun and I escape this, I guess. , USER: They're pretty, usually, and interesting premise., classify_text: so do you like movies like harry potter?
Output:
ASSISTANT