Given the task definition and input, reply with output. 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 kinds of movies do you typically enjoy? , USER: Mostly, I enjoy action movies and science fiction movies. , ASSISTANT: what draws you to that kind of movie? , ASSISTANT: I see. and what kinds of movies do you tend to dislike or avoid? , USER: I tend to avoid any type of romance movies or movies with a big boring story. , ASSISTANT: Why do you avoid those kinds of movies?, classify_text: They just don't interest me, I feel like they're boring and they're not fun to watch. They just don't speak to me.
USER