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 historical dramas. , ASSISTANT: Why historical dramas? , USER: I like seeing the costumes and scenery from a different time period. , ASSISTANT: I see. Can you tell me a specific historical drama you liked that i should watch? , USER: I liked watching Elizabeth., classify_text: what did you like about it?
Output:
ASSISTANT