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 are some types of movies do you like? , USER: I really like I like thrillers, and I like movies that have a lot of suspense and things that keep me guessing. , ASSISTANT: why else do you like thrillers? , USER: Because they They tend to really keep me interested in the plot, and I really like I like the the pace and how it makes me feel excited. , ASSISTANT: what do you think mystery movies? , USER: They can be good sometimes, so long as they aren't too obvious or they aren't too complicated. I think sometimes they can go overboard, but I like a mystery every now and again., classify_text: What is one of your favorite movies?
Answer:
ASSISTANT