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 kind of movies do you like? , USER: Thrillers, action, political thrillers, action movies like Die Hard or The Matrix, Sci-Fi movies, things like that. , ASSISTANT: Great. Can you give me a movie you really liked? , USER: Well, let's go with The Matrix. , ASSISTANT: what did you like about it? , USER: I liked the It has a lot of the things I like in it. Action, has a pretty heavy sci-fi bent to it. There's just a little bit of religious subtext. But mostly it's the action and the storytelling I thought were very good., classify_text: Okay
ASSISTANT