Faculty Research and Creative Profiles

In addition to being excellent teachers and mentors, our faculty are on the frontier of research with the goal of expanding the overall knowledge and understanding of mass media and communications.

PAPER: Augmented Co-Creation: Using Artificial Intelligence and Neural Network Algorithms to Support Design Collaboration

This is a photo of Stephen Masiclat

Stephen Masiclat

Director, New Media Management

New Media Management

Augmented Co-Creation: Using Artificial Intelligence and Neural Network Algorithms to Support Design Collaboration.

Authors: K. Brandt, B. Lonsway, S. Masiclat
Corresponding author: S. Masiclat

This research project developed a web portal to serve as a nexus between the broader technology community and social organizations (nonprofits, NGOs, social enterprises, etc.) in need of technology. The team was asked to go beyond developing a searchable code repository and understand the organizational, structural and technological challenges of connecting social sector organizations to a globally distributed community of technologists who spoke different professional languages.

In this project it was important to design a system that did not attempt singular perfect matches between problem statements and software descriptions. To accomplish this, we used Self-Organizing Map (SOM) algorithms. SOMs allow for a complete and robust representation of highly complex data, but as they are intentionally constructed to avoid computing a single “correct” result, they are considered less accurate than other neural networks based on gradient descent back propagation. We employed a Latent Semantic Indexing technique as a placeholder for a variety of NLP pre-formatting techniques, representing unstructured text inputs in a bi-gram vector form. We then used these bi-gram vectors as inputs to the SOM to perform unsupervised training on the computational neural network such that it formed a representation of the topology (geometric inter-relations) of the input data.

Using the open-source d3js (Data Driven Documents) javascript library, we represented the SOM output in a proof-of-concept UI demonstrating matches between unstructured problem statements (arbitrary document A) and structured descriptions of code bases (arbitrary document B). The resulting UI allowed matching of applicable code resources to problem descriptions even when the Jaccard coefficient between documents was zero: Jµ [A,B]=0.

This research was sponsored by a grant from JP Morgan Chase.

Published in "Proceedings of the Design Management Institute," 2016  pp 1503-1528

This is a photo of Stephen Masiclat

About Stephen Masiclat

Stephen Masiclat has professional experience as an interface designer, Macintosh programmer, graphic designer and art director. He teaches web and interactive media design, introductory graphic design, typography and content management systems.

View full profile