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: can you tell me what types of movies you like? , USER: I like dramas quite a bit. , ASSISTANT: ok, what about dramas do you like? , USER: Usually the story, they're interesting. And it's easy to get involved with them. Just cuz it's an important story, it's not just mindless action or just something that doesn't matter. , ASSISTANT: got it, can you name a specific film you enjoyed? , USER: Shawshank Redemption was really good., classify_text: what about shawshank redemption did you like?
Student:
ASSISTANT