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: I like romantic comedies. , ASSISTANT: Can you name a particular movie you like? , USER: The Wedding Singer , ASSISTANT: What did you like about the wedding singer? , USER: familiarity with the story made me feel connected to the character, and I was just happy to see myself reflected., classify_text: I see. Can you tell me a movie you did not like?
Output:
ASSISTANT