Rian Mustafa Bahran

Twitter Geolocation: A Hybrid Approach

Geotagging Twitter messages is an important tool for event detection and enrichment. Despite the availability of both social media content and user network information, these two features are generally utilized separately in the methodology. In this article, we create a hybrid method that uses Twitter content and network information jointly as model features. We use Gaussian mixture models to map the raw spatial distribution of the model features to a predicted field. This approach is scalable to large datasets and provides a natural representation of model confidence. Our method is tested against other approaches and we achieve greater prediction accuracy. The model also improves both precision and coverage.

Pictures from VIP Tour During CNEC and CVT Measurements 2016

Below are pictures from the VIP tour on July 13, 2016 at the DAF and Sedan Crater. The tour occurred during the CNEC and CVT Year Two measurements.

Pictures from Year Two CNEC and CVT Measurements

Below are all of the pictures for the CNEC and CVT measurements performed at the DAF in July 2016. In total there are 165 pictures. The photos on pages 2-105 were taken during the first week of measurements and the photos on pages 106-165 were taken during the second week of measurements. Many photos are applicable to both sets, which is why it is best to keep the entire set together. For most configurations, a description of the configuration was written on a white board; photos of the measurement setup were taken, then a photo of the white board was taken. For example, the pictures on pages 6-19 (which precede a white board picture on page 20) are of the configuration with Rocky Flats Shells 1-2 surrounded by 4 AmLi sources, which is listed on the white board picture on page 20. In some cases, the white board picture precedes the configuration pictures.

Working Group on Social Internet Data Mining and Analytics for Nuclear Nonproliferation

We examined publicly accessible Wikipedia access logs to determine if safeguard relevant events would be evident through increases in visits to articles related to that event.