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: I really love action movies. , ASSISTANT: Well, tell me why do you like action movies , USER: They just kind of really get my my heart pumping just really fun to watch lots of cool scenes. , ASSISTANT: cool, what is your favorite movie? , USER: I really love Transporter., classify_text: alright, Why is that your favorite movie?
ASSISTANT