Given the task definition and input, reply with output. 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 sad movies. , ASSISTANT: What is it about sad movies that you like? , USER: It made me feel sad and emotional. , ASSISTANT: Interesting, is there a sad movie that you like? , USER: I like The Lion King., classify_text: What is it about Lion King that you liked?
ASSISTANT