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 normally watch? , USER: horror movies , ASSISTANT: What was the last movie that you enjoyed? , USER: Wreck-It Ralph , ASSISTANT: What made you enjoy it so much? , USER: It was cute and funny, and it had a happy ending., classify_text: What was a movie that you had recently watched that was disappointing ?
Output:
ASSISTANT