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 types of movies do you usually see? , USER: I like horror, comedy, action. , ASSISTANT: Give me one of your top 5 movies , USER: Avengers: Infinity War , ASSISTANT: Great. Why did you like it? , USER: It was action packed and had a lot of great moments., classify_text: What else did you like about it?
ASSISTANT