Tutorial: Text Analytics for Simulation with Python

Abstract

Text-based data analytics offers many opportunities related to simulation practice.This tutorial describes these with three primary examples: (1) using sentiment analysis to drive a simulation; (2) using social network analytics to structure a simulation; and, (3) developing model timelines using Twitter analysis.The tutorial includes all aspects of data analytics including data collection, cleaning, analysis and use---all specifically adapted to simulation practitioners.The tutorial uses a hands-on approach with Python in Jupyter notebook and Spyder environments and data sources as JSON, CSV, Twitter/social media, and web scraping/crawling.Other techniques such as setting up a cloud-based data collection platform are also described.The three examples use VADERsentiment, Pandas, word clouds, text analytics, topic modeling, social network analytics and other tools.Example code is provided during the tutorial.Those attending the tutorial will learn ways to enhance the human element in their models based on real-world data sources.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 2 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.