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: Do you like movies like the Spotlight? , USER: Yeah, for the most part I do like movies like Spotlight. , ASSISTANT: Ok. What is it about this type of movie that you like? , USER: It's a controversial topic that is covering and it's trying to send a message about what they're doing now. It depicted a preachiness I think because that's what the journalists were doing but still came off a little bit that way but a really great movie and it doesn't take away from it. It's just a little bit I I still would put all the president's men of those kinds of movies ahead of spotlight one of the reasons because of that. , ASSISTANT: Do you like movies like Inside Man? , USER: I don't know that movie., classify_text: Do you like movies like Good Will Hunting?
ASSISTANT