Hugo Liu and Pattie Maes, Massachusetts Institute of Technology Media Laboratory
The traditional story understanding dogma in AI holds that there exists a singular, objective meaning implied by text, which can be uncovered by applying just the right logical inferences. But according to research into the cognition of reading, text can also be read, not objectively, but aesthetically. An aesthetic reading of text engages not only the agency of thought, but also intuition, sensation, and sentiment, and cultural interpretation. We have developed and implemented a basic computational model of aesthetic reading, which employs Carl Jung’s Modes of Interpretation idea to delegate the task of aesthetic interpretation out to several different textual analysis engines, each computing a different mode of interpreting text, such as generating sentimental evocations of a text (Feeling modality), or remembering visual imagery evoked by the text (Sensation modality). The outputs of the various interpretive modalities are merged and then their unification is achieved by mapping them into color space using theories of color psychology. We built the Aesthetiscope, an artwork whose grid of colors are dynamically generated from aesthetic readings of an inputted poem or song, to illustrate the power and potential of going beyond literal understandings of text.