AGORACOM Small-cap Investor Relations Blog

SPONSOR: Datametrex AI Limited (TSX-V: DM) A revenue generating small cap A.I. company that NATO and Canadian Defence are using to fight fake news & social media threats. The company is working with US Government agencies on Covid19 and Coronavirus fake news and disinformation Click here for more info.

Microsoft claims its AI framework spots fake news better than state-of-the-art baselines

• If the system’s accuracy is as claimed and it makes its way into production, it could help combat the spread of false and misleading information about U.S. presidential candidates and other controversial topics
• A survey conducted in 2018 by the Brookings Institute found that 57% of U.S. adults saw fake news during the 2018 elections and that 19% believe it influenced their vote

Kyle Wiggers

In a study published this week on the preprint server Arxiv.org, Microsoft and Arizona State University researchers propose an AI framework — Multiple sources of Weak Social Supervision (MWSS) — that leverages engagement and social media signals to detect fake news. They say that after training and testing the model on a real-world data set, it outperforms a number of state-of-the-art baselines for early fake news detection.

If the system’s accuracy is as claimed and it makes its way into production, it could help combat the spread of false and misleading information about U.S. presidential candidates and other controversial topics. A survey conducted in 2018 by the Brookings Institute found that 57% of U.S. adults saw fake news during the 2018 elections and that 19% believe it influenced their vote.

Many fake news classifiers in the academic literature rely on signals that require a long time to aggregate, making them unsuitable for early detection, the paper’s coauthors explain. Moreover, some rely solely on signals that are easily influenced by biased or inauthentic user feedback.

In contrast, the researchers’ system employs supervision from multiple sources involving users and their respective social engagements. Specifically, it taps a small amount of manually annotated data and a large amount of weakly annotated data — i.e., data with a lot of noise — for joint training in a meta-learning AI framework.

A module dubbed label weighting network (LWN) models the weight of the weak labels that regulate the learning process of the fake news classifier, taking what the researchers refer to as an instance — for example, a news piece — and its label as input. It outputs a value representing the importance weight for the pair, which determines the influence of the instance in training the fake news classifier. To allow information sharing among different weak signals, a shared feature extractor works alongside the LWN to learn a common representation and to use functions to map features to different weak label sources.

Above: Graphs comparing the performance of Microsoft’s AI with various baseline models.

The Microsoft researchers tapped the open source FakeNewsNet data set to benchmark their system, which contains news content (including meta attributes like body text) with labels annotated by experts from the fact-checking websites GossipCop and PolitiFact, along with social context information such as tweets about news articles. They enhanced it with a corpus of 13 sources, including mainstream British news outlets, such as the BBC and Sky News, and English-language versions of Russian news outlets like RT and Sputnik, with content mostly related to politics.

To generate weak labels, the researchers measured the sentiment scores for users sharing pieces of news and then determined the variance between those scores, such that articles for which the sentiments widely varied were labeled as fake. They also produced sets of people with known public biases and calculated scores based on how closely a user’s interests matched with those sets, operating on the theory that news shared by biased users was more likely to be fake. Lastly, they measured credibility by clustering users based on their meta-information on social media so that users who formed big clusters (which might indicate a bot network or malicious campaign) were considered less credible.

In tests, the researchers say the best-performing model, which incorporated Facebook’s RoBERTA natural language processing algorithm and trained on a combination of clean and weak data, accurately detected fake news in GossipCop and PolitiFact 80% and 82% of the time, respectively. That’s upwards of 7 percentage points better than the baseline models.

The team plans to explore other techniques in future work, like label correction methods for obtaining high-quality weak labels. They also hope to extend their framework to consider other types of weak supervision signals from social networks, leveraging the timestamps of engagements.

These researchers aren’t the only ones attempting to combat the spread of fake news with AI, of course. In a recent study, MIT’s Computer Science and Artificial Intelligence Laboratory developed an AI system to spot misleading news articles. Jigsaw late last year released Assembler, an AI-powered suite of fake news-spotting tools for media organizations. AdVerif.ai, a software-as-a-service platform that launched in beta last year, parses articles for misinformation, nudity, malware, and other problematic content and cross-references a regularly updated database of thousands of fake and legitimate news items. For its part, Facebook has experimented with deploying AI tools that “identify accounts and false news.”

Source: https://venturebeat.com/2020/04/07/microsoft-ai-fake-news-better-than-state-of-the-art-baselines/

• Established a join venture (JV) with LOTTE to co-bid on contracts with the Ministry of Health in South Korea
• This is to improve accuracy and transparency in the middle of COVID-19 catastrophe on media, social media, and various other data sources

TORONTO, April 06, 2020 — Datametrex AI Limited (the “Company” or “Datametrex”) is pleased to announce that it has established a join venture (JV) with LOTTE to co-bid on contracts with the Ministry of Health in South Korea. This is to improve accuracy and transparency in the middle of COVID-19 catastrophe on media, social media, and various other data sources.

On April 2, 2020, Datametrex announced that it was awarded preferred vendor status with LOTTE. One of the many benefits of being a preferred vendor is the opportunity to create JV’s and co-bid on contracts with LOTTE’s support. Datametrex and LOTTE recently agreed to create a JV using its AI and other relevant technologies to improve the accuracy and transparency of data which includes ability to filter disinformation for the Ministry of Health Department in South Korea. This opportunity was initiated due to the Coronavirus and COVID-19 catastrophe. South Korea’s health department has been the leader in screening and flattening the curve and is a role model for other countries on how to manage the COVID-19 pandemic.

The Company was successful in pitching the opportunity and create a JV with LOTTE largely due to the work it has done for the US Federal Government on COVID-19 and Coronavirus.   Datametrex released a report on April 1, 2020 which clearly identified Chinese authorities manipulating social media surrounding Coronavirus and COVID-19. Their intent was to sway public opinion to negatively impact the United States Government and President Trump while positively impacting China and President Xi.

Please click the link below to view the report:

“I am thrilled to share this update with shareholders, our team has done a fantastic job fast tracking with LOTTE. The work we have done this past year training our technology in various languages such as Korean, Chinese, French, and Russian is really starting to pay off,” says Marshall Gunter, CEO of the Company

About Datametrex AI Limited

Datametrex AI Limited is a technology focused company with exposure to Artificial Intelligence and Machine Learning through its wholly owned subsidiary, Nexalogy (www.nexalogy.com).
Additional information on Datametrex is available at: www.datametrex.com

For further information, please contact:

Marshall Gunter – CEO
Phone: (514) 295-2300
Email: [email protected]

Jeff Stevens- Co-Founder
Phone: (647) 400-8494
Email: [email protected]

Neither the TSX Venture Exchange nor its Regulation Services Provider (as that term is defined in the policies of the TSX Venture Exchange) accepts responsibility for the adequacy or accuracy of this release.

Forward-Looking Statements

This news release contains “forward-looking information” within the meaning of applicable securities laws.  All statements contained herein that are not clearly historical in nature may constitute forward-looking information. In some cases, forward-looking information can be identified by words or phrases such as “may”, “will”, “expect”, “likely”, “should”, “would”, “plan”, “anticipate”, “intend”, “potential”, “proposed”, “estimate”, “believe” or the negative of these terms, or other similar words, expressions and grammatical variations thereof, or statements that certain events or conditions “may” or “will” happen, or by discussions of strategy.

Readers are cautioned to consider these and other factors, uncertainties and potential events carefully and not to put undue reliance on forward-looking information. The forward-looking information contained herein is made as of the date of this press release and is based on the beliefs, estimates, expectations and opinions of management on the date such forward-looking information is made. The Company undertakes no obligation to update or revise any forward-looking information, whether as a result of new information, estimates or opinions, future events or results or otherwise or to explain any material difference between subsequent actual events and such forward-looking information, except as required by applicable law.