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: Do you like movies like Star Wars; or Trainwreck or Spotlight , USER: I like movies like Spotlight, so I'm looking for something that's meaningful like a good Spotlight kind of a movie. , ASSISTANT: Ok. What is it about this type of movieÂ that you like the most? , USER: The connection between being young, gay and black. , ASSISTANT: Can you say a little more about that please? , USER: I like that it highlights being African American and what it means to be gay and like all the hardships that go along with that because of it., classify_text: Anything about this type of movieÂ that you dislike?
Output:
ASSISTANT