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 kinds of movies do you like? , USER: Pretty much everything except like Hallmark type movies or really really cheesy rom coms or family movies and some documentaries I don't some. If some the documentary is really dry, I can't get into it, it puts me to sleep. , ASSISTANT: Is there something specific you can always watch? , USER: As a movie, or a genre? , ASSISTANT: Genre , USER: Probably action movies. I mean it's always fun to watch things blow up, you don't have to put much thought into it but so I guess that's the easiest answer to give., classify_text: Alright, how about a movie you liked?
ASSISTANT