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, horror, adventure, fantasy. , ASSISTANT: what do you like about these kind of movies? , USER: They make me think, and they make me smile, and yeah. , ASSISTANT: so you like cerebral movies? , USER: Yeah., classify_text: is there any particular movie that you've liked a lot?
Output:
ASSISTANT