Fact-O-Meter-Scale (Green = Facts / Yellow = Discutable / Red = Strong danger of Fake News)
Value Proposition (at a glance)
Problem Statement & Why it is important
Part of the Business Model
Milestones (We plan fast feasable results)
Some captions of the solutions (Mobile & Desktop Version)
First Marketing Add
The story of Pinocchio and his nose:
Fake News are spreading on Social Media & Newspages and are a danger for democracies (e.g. election influence), societies (e.g. hate speech) and even our health (e.g. wrong treatments for Covid19). Even if people do not want to spread fake news, it is often hard to detect what is real or fake nowadays - and mostly it is hard to get a second opinion. How great would it be, if we could tell, if we read facts or fakes/lies - like you could tell, when you look at Pinocchio's Nose… oh wait! There is Fact-O-Meter! --> The introduced Browser-Extension with the Pinocchio-Pin shows the users the likelihood, that the article is based on facts (short nose/green) or on fake news (long nose/red sign) in real time based on a neural network. It checks fact and information on Social Media and News Networks - as a Browser-Addon with the possibility to get further trustworthy source advises - so we go even further than just detecting Fake news, what makes our solution in the field of Browser extensions and its scalability unique.
‘Fake news’ has rapidly become a problem that affects us on an everyday basis. It changes discussion cultures, leads to an increase of hate speech and makes it difficult to trust sources and information. Especially currently it is dangerous, when people do not get trustworthy information about the Covid-19-situation. We wanted to make a positive impact by building a collaborative platform so everyone can help to spot the fake news and to prevent next ones about the credibility of the article. We want to have it helpful, easily reachable and not distracting the normal interaction with browsers and mobile versions. We wanted to focus on the whole costumer journey, that as many people at possible are using Fact-O-Meter in the future.
What it does
Veracity of news from articles and social media platforms could theoretically be ascertained by human interventions. However, data is generated constantly on a big scale - so it would not be feasible. That is why we build on a recurrent neural network-approach, which we want to introduce on a first step as a browser-addon, which shows you constantly (like Grammerly for Grammer) the likelihood that the article / social media entry can be trusted. Our clear focus was that it is easy and helpful for the costumer, so that it does not disturb the normal reading experience. In addition it is coherent with the current GDPR-regulation and recommends also additional trusted news. As mentioned in the beginning this is - as far as we know after our marketresearch - unique. Let us look deeper on the USPs of Fact-O-Meter:
Value Proposition (Customer Usability & Centricity)
• Not just detecting FakeNews – Fact-O-Meter shows references for facts: We offer trusted alternative to get further information or as a second opinion on the reading • Accessibility (mobile phone & desktop): Everybody is able to use fact-O-meter (up to 85 % of all users) • Simplicity (browser scrolling down and showing icons): Addon does not disturb the customer, but gives signs if Fake News are detected and offers additional information if wanted • Customer Experience: Customer experience builds on a storyline of Pinocchio, gives helpful recommendations for trusted information and combines it with actual data
Value Proposition (Innovative Solutions with unique features)
• Real time fact checks, based on a neural network engine (with daily increasing training data) • Add-On-for Browsers solutions (planned for all major browser types (reach of more than 85% all users) • Python-Webserver with Machine Learning-Technology • High impact with a high reach, but not cost- and time-intensive solution. Neural networks are low cost
Value Proposition (General Business Model)
• High scalable Business Model with no high entry costs • Users support to train our service and make the service better (Power-User benefits – See Business Model-Slide) • Cheap Maintenance of neural costs lead to low end user costs • Fast feasible introduction: We are able to provide the solution fast (working environment in 3 weeks) (See Milestones-Slides) • Future planned add-on: “Ask the Expert-Button” where the user can ask for additional information to specific topics (currently Out-of-Scope)
How We built it
The Software consists of two separate modules, therefore we will describe them separately:
The neural network is build with python and uses the Tensorflow library. The library is well documented and there are plenty of examples and good tutorials all around the internet. We trained the network with this Dataset: ”https://www.kaggle.com/c/fake-news/overviewd”. To be compliant with the GDPR we had to set up a reverse proxy with apache2 to encrypt the traffic via SSL (The webserver of python does not support SSL encryption).
BTW: We used mainly open-source-software with MIT license or better (ready for commerical use)
Challenges We ran into
The neural network was quite slow initially and each request had an average response time from 5 seconds. Properly initializing the network and tweaking a few optimizations gave us a really performant server and reduced the response time to milliseconds. At the moment we are not finally satisfied with the accuracy of the neural network (also if it is clearly distinguish if some information is clearly fake-news - we just have to train the final threshold. More training and/or another model is neccessary for the release.
Accomplishments that We are proud of
We are proud that we brought this idea so far that it can be directly implemented, with a small team of 3 people in this short timeframe Happy that we brought so many components in one overall solution together (possibility to detect fake news, offer additional source ideas for a second opinion and even think about a “ask an expert”-button on a future stage. Current pilots can be rolled out to 85 % of all desktop users and 75 % of all mobile users within some weeks. A first version on Chrome browser is already working.
What We learned
- We learned how to make Chrome Extensions (we never did that bevore) and did research for how to adapt it into other browsers so we can get Fact-O-Meter running for 85 % of all desktop and more than 75 % of all mobile users.
- How to build a functioning prototype in python
- We've learned a lot about neural networks and how big the online community is that shares network models and various datasets.
What's next for Fact-O-Meter
First, we want to develop fully functional extensions for all common browsers, because the prototype is only available as a Chrome extension. Next, we want to tune our neural network model so it's at least 95% accurate. After that, a continuous automatic online learning mechanism would be beneficial to guarantee good accuracy also for the latest topics. And as a final step, we want to port the system to the mobile platform.
An ultimate goal would be the direct implementation of our service into the browsers by the company itself.
Further Information if interested:
What you have done during the weekend
Developing the whole customer Journey (Customer Journey is Key) Developing a marketing strategy (Pinocchio and its potential to combine it with story elements) 40+ hours on teamspeak/voice chat and insightful checkpoints with our mentor And now: We are having our first beer and looking proudly our Fact-O-Meter-Video #EUvsVirus
The solution’s impact to the crisis
Less uninformed people lead to a less uninformed society, which helps to achieve a better social and political cohesion, and better information for health concerns, less hate speech and a better informed community. So the people tend to trust trustworthy information, know which treatments can and will not help when you are ill and which actions could help to overcome the crisis as soon as possible - together.
The value of your solution(s) after the crisis
Fake News is a problem which goes by far beyond this current crisis. To fight sustainable against the threat of Fake News for democracy, society and health issues a long-term-tool is needed, which helps to filter facts from fake news and helps people to get easier access to further information on controversial topics. Fact-O-Meter is a customer focused tool which has the potential to be a partner in dies field - so that in the world hopefully less Pinnochios are around in the future.