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 type of movies do u enjoy? , USER: I like watching entertaining movies, mostly animation movies. , ASSISTANT: can u name a movie that fits that category that you thoroughly enjoyed? , USER: Yes, recently I watched, well, last year a movie called Your Name which was a movie with a great plot that was very interesting. , ASSISTANT: what qualities about your name did u enjoy? besides the plot , USER: The the depiction of characters and how the director played with different timelines in one movie. Kinda don't want to if you've never seen it spoiler, but the way that you walk up to the climax at the end was masterfully done., classify_text: thanks for describing that for me. is there a movie that fits the category you mentioned that you didn't enjoy
Answer:
ASSISTANT