What happens if you take a huge cross-section of the world’s news (The GDELT Project), mix it with the biggest online discussion website, and try… Read More »Predicting social engagement for the world’s news with TensorFlow and Cloud Dataflow: Part 1
Uber lessened the anxiety of cab callers by providing time estimates and position of cars on the map. Standing in an early-morning Starbucks line waiting… Read More »Million Dollar Idea: Order Tracking at Starbucks
One of my trend calculation queries in the Opinion Analysis project started causing trouble recently. It would run for 270 seconds and break with an… Read More »How to speed up your BigQuery query 31x by replacing a self-join with two UNNEST() operations
I published an architecture of a serverless ETL solution for Sirocco on the GCP Big Data blog. This solution scales from a few news articles… Read More »Serverless ETL for Sirocco on Google Cloud
I got inspired to write this blog by a post I saw today on the French presidential election. Plutchik is really the strongest framework I… Read More »Opinion Analysis of Text using Plutchik
This is the part two blog post of the Sirocco “modernization” series. In the old, SharpNLP version of Sirocco, we used WordNet version 2.7 to… Read More »Selecting a Java WordNet API for lemma lookups
Tl;dr: Automatic conversion from C# to Java is possible! When we set out developing Cuesense in late 2000s, my partners and I standardized on the… Read More »Modernizing Sirocco from C# and SharpNLP to Java and Apache OpenNLP
It’s been a long time in making, but we are finally ready to release Sirocco — the opinion extraction library based on Robert Plutchik’s emotion framework — under the… Read More »Sirocco released under Apache 2.0 license to github