You will be given a definition of a task first, then some input of the task.
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

USER: Hi. , ASSISTANT: hello. What type of movies do you like? , USER: I like superhero movies and some of the action movies, not all of them, but really seen a lot of superhero movies lately. , USER: Science fiction's good, too. , ASSISTANT: so do you like movies like the avengers? , USER: Oh, yeah. Last one was really good. The second Avengers, classify_text: It was It was okay, but it wasn't as good as the first one or the last one.
Output:
USER