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

USER: Hello, how are you? , ASSISTANT: Hello there! Mind if I ask a few questions about movies? , USER: Hello. Go ahead. I don't mind at all. , ASSISTANT: Do you like movies like Good Will hunting? , USER: It's a good movie. , ASSISTANT: What did you like about that movie?, classify_text: The acting. I loved the acting in it. Really good.
USER