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 kind of movies do you like? , USER: I love romantic comedies. I love drama movies. I like suspense movies. , ASSISTANT: what do you like about these kind of movies? , USER: Well, I I usually like the acting, like how sophisticated the acting is. I like to, you know, I like the scenarios, the the plots. I enjoy the scenery in the movie, and the costumes. , ASSISTANT: nice, so a good movie production catches your attention. , USER: Yes, it does., classify_text: is there any particular movie that you've liked a lot?
ASSISTANT