I began by making an API call to Project Gutenberg, intrigued by the idea of comparing books with similar plots. My focus was on exploring different translations or versions of the same story to see how they diverged. How can we observe these differences? How is the protagonist portrayed in each version? To investigate, I selected the first three paragraphs from each story as a starting point for analysis.
As I read through the different versions of Pinocchio, I quickly noticed how the character was portrayed differently—brave in one, lazy in another, and magical in a third. However, when I tried to analyze the words more systematically, it became clear that finding the right method to capture these nuances with this particular algorithm would take time. Although I considered using RiTa, it didn’t feel like the best tool for extracting the differences I was seeing. I’ve paused for now, but I plan to revisit and refine this approach later in the semester.