Q: 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 kinds of movie do you like? , USER: I like horror movies , ASSISTANT: Why do you like horror movies? , USER: Because I think life is really scary and horror movies allow me to be scared in a safe space. , ASSISTANT: Is there a horror movie you like? , USER: I like Poltergeist., classify_text: why did you like Poltergeist
A:
ASSISTANT