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 kinds of movies do you like? , USER: I like movies that have a good storyline and artsy flair to them, usually funny. , ASSISTANT: Is there a specific genre you like? , USER: I like I like comedy. , ASSISTANT: Why do you like comedy? , USER: I like comedy cuz it makes me laugh and makes me happy., classify_text: cool, how about a movie you liked?
Output:
ASSISTANT