Beginner here -- I have a basic machine learning / text classification problem. Labeled data, a text column strings of various lengths and I'd like to find which words in those strings are most correlated with my identifier.

My data is

unique id | text string | label (1 or 0) |

Imagine the text string is jokes and the label is 1 for funny 0 for not funny. The strings are the text of jokes of varying length. I want to see if any words within the strings are more correlated with a joke being funny or not.

What would be the best way to begin this analysis?