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 type of movies do you like? , USER: psychological thrillers , ASSISTANT: why psychological thrillers? , USER: They make you think and can be scary. , ASSISTANT: so like shutter island? , USER: Yes., classify_text: What is one of your favorite movies?
ASSISTANT