Machine Vision

Project Goals:
The Machine Vision Learning (MVL) search tool enables users to search historical video collections to find unique moments or objects. MVL also contributes to the archival community by adding to the metadata through object tagging. The Media Ecology Project (MEP) and the Visual Learning Group at Dartmouth are building a system to provide access to primary moving image materials and motivate new forms of scholarly research. This Machine Vision Learning tool uses a mix of machine learning methods and Google search to find specific moments and objects within an archived film, such as a handshake, a phone call, or a martini. To make the system smarter, users can also tag metadata easily.  The MVL search tool was mostly built, but was divided into two separate elements, and needed a way to explain the goals and usability of the system to funders and scholars. 

DALI's work answered the question: How might we make the MVL system easier to understand and use in order to generate interest from scholars who can tag and use data, and funders who can advance the development and deployment of this tool.

 

Our Solution:
When we began, there were essentially two tools--a film search engine and a tagging system.  We merged these into a single prototype to tell the story of the potential of this tool. The new MVL website establishes search and annotation interfaces, includes a user tutorial, and a robust "About" page that explains the neural network technology and project.

The Impact:
We completed the website, funded by the Knight Foundation and the DALI Lab, and provided a demonstration tool the Media Ecology Project can use to raise interest and funding. 

Tech Stack

Making It Stick

User-Test-Results.jpg

The Problem:
People don't remember what they have learned and it is affecting our finances. Savings rates are down and financial education doesn't seem to have the desired impact.  Cognitive Science research reveals that information taught in a compressed timeframe, such as a short course or single-session workshop, is usually forgotten, regardless of how engaging the instruction. Strategies to improve retention include periodic review of the material, retrieval practice (testing oneself), and elaborated feedback (explanations for correct/wrong answers). How might we use this Cognitive Science research in collaboration with technology to enhance the impact of financial education?

Tech Stack: React Native, Firebase

Our Solution:
We designed a mobile application to supplement financial education and support a study of the ways technology can improve retention. Our app tracks information retrieval and retention, to track successful methods and best practices. It prompts users to review the material via push notifications and encourage users to stay involved with the study through a monetary reward system. The app can differentiate between two user groups: a group which receives quizzes every few months to promote recollection, and a control group which does not. 

Impact:
Effective financial education changes the way people spend, save, and handle their money.  This can have a big impact on the individual savings rate and help people make better financial decisions. We gather valuable metrics on how periodic recollection impacts over-all learning. The data we collect is used in Cognitive Science and Educational studies.