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: I like all different types of movies. , ASSISTANT: Why is that? , USER: They're quite fun to watch. A lot of different genres out there to pick from, so you can never really get too bored. , ASSISTANT: any least favorite genres? , USER: My least favorite is probably horror, not a huge fun of scary movies., classify_text: do u get scared easily?
ASSISTANT