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

ASSISTANT: what kind of movies do u like watching? , USER: I like movies that, you know, have a great story line, that are memorable, that have great acting, that you can't, you know, that make you cry or are very emotional movies. , ASSISTANT: can u name a movie that fits what you've mentioned? , ASSISTANT: what about that movie did u like? , USER: It's just very interesting overall. , ASSISTANT: what about a movie u didn't like?, classify_text: Movies I didn't like there are so many movies that are bad, you know, the the acting is terrible, it doesn't keep your interest. You just want to turn it off. Just poor poor acting, very cheaply image movies
Output:
USER