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 are some movie genres that you like? , USER: I really enjoy animated movies, romantic comedies, and thrillers. , ASSISTANT: why romantic comedies? , USER: They usually tend to be feel-good type movies with happy endings, and I really like a happy ending. , ASSISTANT: What is one of your favorite movies? , USER: Pretty Woman, classify_text: what did you like about that movie?
Output:
ASSISTANT