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 , ASSISTANT: What kind of movies do you like? , USER: I like action movies. , ASSISTANT: why do you like action movies? , USER: They're entertaining and the storyline is packed full of excitement. , ASSISTANT: Can you name a particular movie you like?, classify_text: like Die Hard
Output:
USER