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 enjoy? , USER: comedies, thrillers, suspense , ASSISTANT: What appeals to you with these type of movies? , USER: I like to laugh, I like to be in suspense, and I like thrillers. , ASSISTANT: Is there a specific movie you enjoy from these genres? , USER: The Avengers, classify_text: What did you like about this movie?
Output:
ASSISTANT