Teacher: 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
Teacher: Now, understand the problem? If you are still confused, see the following 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.
Solution: USER
Reason: 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.

Now, solve this instance: ASSISTANT: What kinds of movies do you like? , USER: I mainly like drama films and maybe like suspense films. , ASSISTANT: Why do you like drama films? , USER: Well, I usually like You know, I enjoy a good movie with a good story. And there's been a lot of good drama movies out lately, so anything that has me escape from reality, and something that draws me in is a great movie. , ASSISTANT: Alright, how about a movie you liked? , USER: I really like Bohemian Rhapsody. I saw this one recently., classify_text: Why did you like that movie?
Student:
ASSISTANT