Recommendations
TouchDesigner, Beautiful Soup, ml5.js, Socket.IO
2019
Recommendations is an interactive installation that matches the user with a product on the Amazon marketplace based on the user’s appearance — referencing the modern e-commerce and tech companies’ seemingly limitless capability to surveil our behavior and use opaque algorithms to create finely-tuned suggestions (whether in the form of advertisements or content recommendations), usually in service of promoting more consumption and consumerist behavior.
Recommendations seeks to raise awareness of this trend by bringing a simplified form of the algorithmic suggestion process to the forefront.
Recommendations was built using TouchDesigner, Beautiful Soup (Python library), ml5.js (p5.js library) and Socket.IO. The installation uses a webcam connected to the ml5.js library via a locally hosted p5.js sketch to “recognize” objects in front of the camera. This information is then sent via Socket.IO to a Python script within TouchDesigner, which uses the object name to search the Amazon marketplace. Using the Beautiful Soup library, the Python script parses the search results, selects a product, gathers some information about the product, and displays the results to the viewer onscreen.
Recommendations seeks to raise awareness of this trend by bringing a simplified form of the algorithmic suggestion process to the forefront.
Recommendations was built using TouchDesigner, Beautiful Soup (Python library), ml5.js (p5.js library) and Socket.IO. The installation uses a webcam connected to the ml5.js library via a locally hosted p5.js sketch to “recognize” objects in front of the camera. This information is then sent via Socket.IO to a Python script within TouchDesigner, which uses the object name to search the Amazon marketplace. Using the Beautiful Soup library, the Python script parses the search results, selects a product, gathers some information about the product, and displays the results to the viewer onscreen.
