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 kind of movie do you generally like , USER: I like interesting movies. They could be action or story-driven, science fiction, anything, except romantic movies. , ASSISTANT: why do you like those type of movies? , USER: They keep my interests and I feel like I can put myself in the movie by imagining it. , ASSISTANT: can you name a particular movie that fits that category, and describe a bit about why u like that kind of movie , USER: Guardians of the Galaxy because I really enjoyed it. And the story was compelling, and I liked the characters presented., classify_text: nice choice. how about a movie that you didn't necessarily like that fits that category, and why you didn't like that kind of movie
Student:
ASSISTANT