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 like? , USER: I like mysteries, adventures, and romance the most. , ASSISTANT: Why do you enjoy these genres and is there a specific film? , USER: Let's see. Gosh, there's so many movies I like. I really like Titanic and movies like that that have adventure and romance in them. Let's see. The stars that are in it, as well as the story, and there is you know a lot of action, kind of like I was on the edge of my seat the entire time. , ASSISTANT: Is there a reason why you enjoy that movie? , USER: I like a movie that has a fast pace., classify_text: Is there a movie genre you dislike?
Answer:
ASSISTANT