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 type of movies do you like? , USER: I like war movies. , ASSISTANT: what do you like about war movies? , USER: Well, I like the action, the fact that the stories are usually based in reality. , ASSISTANT: can you think of one of your favorite movies? , USER: Saving Private Ryan, classify_text: how is it one of your favorites?
Output:
ASSISTANT