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 normally watch? , USER: psychological thrillers , ASSISTANT: What was a movie that you last watched that you enjoyed? , USER: Jaws , ASSISTANT: What did you most enjoy about Jaws? , USER: the characters, classify_text: What was a movie that you have seen that was disappointing?
ASSISTANT