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: What kind of movies do you not like? , USER: I don't like horror movies, and I don't like drama movies. , ASSISTANT: Why do you not like Horror movies? , USER: I find they're often too predictable and too cliche. Usually, the plots are really similar which is that there is something scary, nobody knows about it, but it's killing people or terrorizing people or something. And then they figure it and they usually they end up beating it or locking it away or whatever it is that ends up happening to it. , ASSISTANT: What kind of movies do you like the most? , USER: It's a toss-up between comedy and war movies., classify_text: What was the last movie that you watched that disappointed you
Answer:
ASSISTANT