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 you enjoy? , USER: I really like romance, and comedies, and some dramas as well. , ASSISTANT: What appeals to you with these type of movies? , USER: I like that they're really cute and I like that they always , USER: I like to see like keep me on the edge of my seat wanting to know who is going to end up with who, and who's going to get married to who or, you know, stuff like that. , ASSISTANT: Is there a specific movie you enjoy from this genre?, classify_text: I really like How to Lose a Guy In 10 Days and I like let's see How to Lose a Guy in 10 Days, and She's All That, and Never Been Kissed.
Answer:
USER