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 drama and action. , ASSISTANT: What do you like about drama or action movies? , USER: I like that they make me feel all different kinds of emotions. , ASSISTANT: What type of emtions do you feel , USER: Emotions? You mean happy, sad, happy, sad, excited, something that keeps me interested., classify_text: is there a specific title in these genres that you like?
ASSISTANT