Novetta

NOVETTA NEXUS
Open Source / Media Analytics

Introducing Metadata Enhanced ULMFiT

Category: Advanced Analytics / Data Analytics / Novetta Nexus / Open Source / Media Analytics Tag(s):  /  /  /  /  /  /  /  /  /  /  /  /

by Matt Teschke, Brian Sacash

Introduction Since its release in 2018, Novetta’s Machine Learning Center of Excellence has evaluated the performance of Universal Language Model Fine-Tuning (ULMFiT)1 against many customer use cases. We have found that automated labeling of unstructured text helps analysts be more efficient, freeing them up to focus on higher-value tasks. We have been so impressed with its accuracy that we have deployed ULMFiT against a dataset in a production system, with plans to expand it to dozens of other datasets. While ULMFiT’s performance has been impressive on all the datasets we’ve tested, we thought it could do more. Our first use...

Read More

Detecting Disinformation in Russian Election Coverage

Category: Novetta Nexus / Open Source / Media Analytics Tag(s):  /  /  /  /  /  /  /

by

State actors, marketers, and fringe voices use the media – television, radio, print, and online – to achieve influence and shift perceptions. In many cases, this takes the form of disinformation that causes influence without facts, evidence, or logic. Drawing on subject matter expertise and intuition, an observer watching for the dissemination of such messages can sometimes spot examples to support their conclusions. However, identifying this kind of media strategy is incredibly challenging, labor-intensive, and prone to omission and confirmation bias. As analysts working to help our customers manage and mitigate media disinformation, we have found that automated tools provide...

Read More

Accelerating OSINT Analytics through AWS Machine Learning Services & AWS Neptune

Category: Open Source / Media Analytics Tag(s):  /  /  /  /  /  /  /  /

by

Novetta’s business covers a diverse mix of public and private sector customers. While mission objectives vary, we are seeing an increasing need to extract meaning from high-velocity open source (OSINT) information. Historically, deriving intelligence from open source digital content has been complex and time consuming, particularly when high-accuracy results are required. Generating meaningful signals from data sources such as web content and open source video has required substantial labor on the part of analysts. We are working to significantly reduce the effort required to gather and exploit OSINT through a combination of machine learning, graph database technologies, and Amazon Web...

Read More