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

Let me give you an example: ASSISTANT: generally speaking what type of movies do you watch , USER: I like thrillers a lot. , ASSISTANT: thrillers? for example? , USER: Zodiac's one of my favorite movies. , USER: Zodiac the movie about a serial killer from the '60s or '70s, around there. , ASSISTANT: Zodiac? oh wow ok, what do you like about that movie, classify_text: And I just think serial killers, in general, are interesting, so the movie was really good. And it was just neat to see that world. Like it went really in-depth. It was like almost 3 hours long, so you got to really feel like you were a part of that world and time period. And see what the detectives and the police did and the investigators.
The answer to this example can be: USER
Here is why: Based on last conversation in which the ASSISTANT ask's a question for which it waits for a reply from the "USER". We can classify this conversation as "USER" as it needs to respond for the given question.

OK. solve this:
ASSISTANT: Hello, can you please name one of your favourite movie? , USER: Saving Private Ryan , ASSISTANT: What is it about this type of movie that you like? , USER: I enjoy historical movies, and war movies, action movies, and the first 20 minutes of that movie are some of the most visceral war movie making ever, and the rest of it is just a good story that shot well, and , USER: I think makes you feel what felt like to be in World War II, maybe. , ASSISTANT: Ok. now. Could you tell the name of a movie that you dislike?, classify_text: There's a movie by I can't remember his name now. It's called Spartan.
Answer:
USER