Spread the truth
Trucan was a 10-week project held entirely online due to COVID-19. While there were some limitations as to what could be accomplished with this restraint, the team adopted a problem space that aligned with our current situation. The project required an application of Artificial Intelligence. My role in this project comprised of crafting a vision video, UI design, navigation flows, content strategy, branding, low-fidelity iterations, and high-fidelity mockups.
Social media users are overwhelmed with the excess of information available online, and therefore often fall victim to misinformation; consequently sharing the same information, creating an inevitable cycle.
Access to the right information, at the right time, in the right format is critical. We set out to create a platform that enables social media users to be better informed about the information they encounter through an unintrusive and consistent method with the help of Artificial Intelligence.
We conducted qualitative and quantitative research to learn from what already exists in our chosen problem space. This was a starting point so we could stand on the shoulders of giants when we start our primary research.
Social media platforms can be breeding grounds for misinformation. All it takes is for someone to share an initial post, and the spreading of lies ensues. Another issue is that misinformation can come in many forms; whether it be a text post, image, video, or even a comment. If we cannot easily distinguish a truth from a lie, what can?
Bot/spam detection
Information that is produced repeatedly and autonomously is detected and flagged as a bot produced faster than
Reputation Calculating
Using predictive analytics backed by Machine Learning, a website’s reputation can be predicted through considering multiple features like domain name and Alexa web rank.
Stance Detection
AI retrieves documents that are relevant to the claim, detecting the stance of those documents with respect to the claim. It can determine whether a certain document agrees, disagrees, or takes no stance on a specific claim.
As of now, many social media platforms have put measures in place to fight the spread of misinformation. One notable effort is from Facebook, who has a task force dedicated to identifying, analyzing, and minimizing misinformation on their services.
In the fact-checking space, there are a variety of services actively fighting the spread of misinformation. Not all of these services are utilizing AI technologies in their platforms. One of the more notable services is The Factual, which is a news-aggregate that utilizes AI to provide an unbiased, informative information source.
The team collected 120 survey responses, conducted 42 user interviews , 2 expert interviews, and performed a misinformation test. This variety of research methods were used to better understand and design for our target audience.
Key Insights
Survey
Users understand social media is full of opinions, and they tend to look towards the source when determining credibility. Interest in the context of a post motivated users to click and learn more. Many respondents noted that social media has a strong impact and influence on the information they view, whether it be true or not.
Expert Interviews
Between the AI Expert and the Cognitive/Educational Psychologist, they both expressed how concerning the current COVID-19 'infodemic' was. There’s a popular theory where humans believe what they initially hear, and it then takes an extra mental process to evaluate and disprove it internally. This can prove to be dangerous with regards to misinformation.
AI can be reliable but it can also be manipulated. The only way to find out if information is incorrect is by having the system interact with the outside world. While AI can be used, it would not be wise to rely solely on AI to separate fact from fiction. Users should still have the final say as to what they should believe.
User Interviews
A few interviewees mentioned that they only trust a post if it has mass coverage and it is backed by popularity and many sources. They do not want to start a chain reaction of sharing misinformation If they are initially misinformed. One interviewee mentioned that “If It looks real, that’s because it's something we'd like to see.”
Misinformation test
One interesting takeaway from our observations was that older adults would focus towards text, while younger adults would focus on the image/icon. Different age groups perceived information differently, which pushed us towards focusing on combatting textual misinformation.
A fact-checking mobile application for social media that searches for, as well as analyzes for accurate sources of information for safe accreditation using Artificial Intelligence.
Spread the truth with Trucan!
A fact-checking mobile app
TRUCAN is a fact-checking mobile application that promotes a fact-first social media environment. The app offers features for users that search, analyze, and intuitively display accurate sources of information for safe accreditation. Spread the truth with TRUCAN!
Social media users are overwhelmed with the excess of information available online, and therefore often fall victim to misinformation; consequently sharing the same information, creating an inevitable cycle.
With TRUCAN, social media users and influencers can focus on what matters most by learning and educating others of the truth. As of now, social media platforms are bringing very little to the table to help curb the spread of misinformation. A recent MIT study concluded that false news travels 6 times faster on Twitter than truthful news, and human users seem to be more at fault.
Verify information from a source by pasting the source's URL within TRUCAN's Source Visualizer. The app receives key points from within the source that detail it’s summary with the ability to provide accreditation for the source. Trucan then puts the source up against related publications to verify the source's claims. Information like the source's language composition, citations, and summaries are displayed in a visually pleasing and informative fashion.
Trucan has the ability to compare and contrast the data of two sources to detail which source is more reliable. The user can provide one or both articles to compare. If only one is provided, Trucan will find a credible source to either verify or discredit the information presented in the user's provided source. Trucan's source suggestions will always be backed by a large foundation of accreditation from multiple sources.
Use the Claim Maker to write a supporting stance, backed by related sources of information through AI. The supporting sources are cited within the claim and can be shared with text-based social media platforms, such as Twitter.
Claim Maker provides the ability to keep writing without searching for sources, which promotes the user to focus on their writing. The app will also recognize if the user references a credible source, and will suggest adding a citation to support their arguments.
TruType uses AI to offer articles related to what the user types, as well as an analysis of your writing performance to enable confidence before sharing a post or comment; directly through the keyboard. It takes all that is great about TRUCAN and consolidates it for use in Android keyboards.
