Machine learning-powered native-language sentiment and media analytics platform. Novetta Mission Analytics delivers near real-time pattern and behavioral analysis of social, print, and broadcast media content. Its intelligent fusion of machine learning and human-in-the-loop processes creates structured data from multiple streams of publicly available information. Using native-language analysis of messaging and sentiment to discover trends and behavioral shifts, Novetta Mission Analytics provides quantitative visibility into threats and sources of influence. Click image to download.
Evidence-based Public Health Response
Resolving Dates with NLP
In newspaper articles, emails, and other texts, it is natural to reference dates in relation to the publication date. For example, you will commonly see phrases like “yesterday” and “two weeks ago.” However, if you read an article a year after it was published, these timeframes are not immediately clear. When analyzing articles using natural language processing (NLP) techniques, relative dates referenced in an article will not be interpreted properly, if at all, since there is no context for the models. Thus, in order to effectively use tools such as event extraction and question-answering engines, relative references need to be…
Russia, The Ironic Trickster
Using Pattern Analysis to Counteract Kremlin Propaganda
The Kremlin’s public messaging is an effective tool for informing Western officials how to counteract Russian disinformation. When Kremlin officials make statements, either through a press release or when quoted in Russian media, they spin global events in a way that portrays Russia favorably. At Novetta, we have compiled a database containing more than 237,000 quotations of Russian officials that appeared in Russian traditional media articles since July 2016. Using pattern analysis, we were able to outline Russia’s communication strategies and uncover insights into the Kremlin’s playbook which can inform the propaganda value of future events. Russia often plays the…
Judge an Outlet by its Owner
Russian Ties to Ukrainian News Reporting
On June 14, 2019, during a live appearance on Ukrainian tv network ZIK, popular journalist Dmitry Gordon declared, “I will stay for the rest of the program today… but I want to officially say: this is my final appearance on the television channel ZIK. I will never appear on channels that Medvedchuk has acquired. I call on all patriots of Ukraine, politicians, who want happiness for our country and who do not want Ukraine to be a satellite of the Russian Federation, to stop appearing on Medvedchuk’s channels.” News had just broken that ZIK and its online news service ZIK.UA…
Information Contagion
The Infectious Nature of Misinformation in a Pandemic
At the start of this global pandemic, the COVID-19 outbreak (also known as Coronavirus) was slow to pick up significant coverage in international media. In hindsight, a pivotal moment was missed to prepare and aggressively disseminate key messaging for international bodies to lead a cohesive, coordinated response. We now know the lethality rate of infected patients for COVID-19 is minimal compared to high-risk diseases such as Ebola. However, the global reach of COVID-19, due in part to the lack of attention and informative messaging, has made this outbreak more deadly than the most recent Ebola outbreak. In the initial alarm…
Media, Data, and Outbreaks: The UN’s Global Health Crises Task Force
The challenges that epidemics and other global health crises present to the international community are ever changing in each new environment that develops potential risk to the adequate containment and eradication of disease outbreaks. In an effort to find new procedures and practices to limit these risks in 2017 the UN Secretary General’s Global Health Crises Task Force created an independent monitoring and accountability body called the Global Preparedness Monitoring Board (GPMB). In its most recent report produced by the International Federation of the Red Cross and Red Crescent Societies in collaboration with Anthrologica, the GPMB focused on the need…
Deploying Advanced Machine Learning Models at Scale
Novetta is using deep learning to automate advanced analytic pipelines for our customers. These new capabilities identify important pieces of information across large text, image, and video data sets, a challenge faced by many of our Defense and Intelligence Community customers. We developed Argo, a standardized, Docker-based model training and deployment pipeline, to enable rapid evaluation and deployment of state-of-the-art deep learning models. Argo enables models to be deployed as endpoints and, when used with Amazon SageMaker, it forms the foundation for us to deploy, scale, and manage our deep learning models. Simplifying infrastructure setup through Docker and AWS allows…
Ebola in the Democratic Republic of Congo: Novetta Mission Analytics
How data analysis is helping mitigate the second largest outbreak in history.
The ongoing Ebola outbreak in eastern DRC has caused 1,522 deaths, making it the second largest in history. Understanding the causes and expressions of deep-seated local resistance to international response efforts is essential to shortening the outbreak and saving lives. Novetta is providing hands-on analysis via subject matter experts to our partners in the Ebola response community through the classification and analysis of sentiment and voice share in hyper-local and regional media content originating in the North Kivu Ebola hotspot. Novetta’s analysts identify distinct narratives and vectors of propagation from the voices of citizens, civil society stakeholders, Ebola response leadership,…
20% Accuracy Bump in Text Classification with ME-ULMFiT
Introduction In a previous post, we discussed an enhanced method of passing additional data to the ULMFiT1 algorithm for unstructured text classification, which improved accuracy by up to 9%. In follow-on experiments, we have demonstrated that this approach – in which we prepend metadata to the text to provide more information to the model – increased accuracy by up to 20%, in relative terms. This improvement required just a few lines of Python, such that the performance boost comes at essentially no cost. This blog post explains the findings of this more-detailed evaluation, where we have compared how the following…
