According to the definition of Wikipedia, Science Fiction (Sci-fi) is a speculative fiction with imaginative and futuristic concepts including advanced science and technology, space exploration, time travel, parallel universes, and extraterrestrial life. Sci-fi also explores the potential consequences of scientific, social, and technological innovations. Science fiction can be traced back to ancient times, when the precursors of Sci-fi were related to fantasy, horror, and superhero mythologies. From then until now, there has been no clear answer for the genre science fiction fits into and what categories Sci-fi can be divided into. As we can see from the poster, the topics of science fictions can be wide-ranging. I wonder what the content of science fiction, and whether such works can be classified by modern natural language models. Using the tools and methods from my course, Data 88: Language Modeling and Text Analysis, I show how Topic Modeling can help establish the relationships and clusters in a landscape of Sci-fi literature.

Screenshots