I-Corps: Translation Potential of an Online Healthcare Information (OHI) Trust Badge

The broader impact of this I-Corps project is the development of an online knowledge recommender tool and trust badge for consumers. Health misinformation remains a serious societal threat. Since the emergence of the COVID-19 pandemic, reports show on average that 8 out of 10 Americans search for online healthcare information (OHI), and 4 out of 10 Americans cannot correctly identify false healthcare claims.

The goal of the new technology is to help alleviate confusion amongst consumers caused by the overwhelming amount of OHI, and to help OHI providers boost their reputation as a trustworthy source. The tool is designed to combat misinformation by proactively serving a wide spectrum of stakeholders who regularly deal with OHI content. The I-Corps project will focus on the specific issues and public challenges of endorsements in addition to fact checking of OHI content and contributing to a better understanding of the needs of people who use and/or provide OHI content.

This solution serves as a foundation for a consultancy service providing platform offering advice plus training to OHI consumers and OHI providers.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of a software tool that will serve online healthcare information (OHI) users by providing machine learning-based classification and certification of OHI content trustworthiness. Research has shown that machine learning-based classifiers can process OHI claims and classify them as fact or fake, but such solutions have not been directly integrated into web browsers and have been trained with primarily textual cues from mostly unimodal datasets.

This technology addresses these limitations and is designed as a machine learning driven online knowledge recommender tool, prototyped as a web extension utility, which can be directly embedded into web browsers to seamlessly report trustworthiness of any OHI content. the solution is designed as a trust badge model for easy certification of web content and can function both as an online content classifier. This capability may allow both OHI consumers and OHI providers to validate and tag OHI websites' trustworthiness.

Additionally, the solution is trained with multimodal data, that includes both textual and visual cues (e.g., image elements, graphic contents, and infographics), unlike existing solutions that do not include visual cues or image artifacts.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.