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: comedy , USER: I like funny movies. , ASSISTANT: What is your favorite comedy? , USER: The Hot Chick. , USER: My favorite comedy is The Hot Chick., classify_text: What is a movie that you recently watched that disappointed you?
Output:
ASSISTANT