Spatial Twitter Analysis

: In this lesson, we will explore methods for verifying the accuracy of choropleth maps.

Wednesday, April 28

Developer API

Prior to lab, you must have an approved Twitter developer account and a Twitter app.

• See instructions here: Creating a Twitter App
• The purpose of your ‘app’ can be to research and visualize spatial clustering of Twitter activity during natural disasters, e.g. coastal storms, pandemics, and earthquakes.

Lecture

Prior to class, please read:

Wang, Z., X. Ye, and M. H. Tsou. 2016. Spatial, temporal, and content analysis of Twitter for wildfire hazards. Natural Hazards 83 (1):523–540. DOI:10.1007/s11069-016-2329-6

Prepare a blog post of two paragraphs answering:

1. Summarize the analytical techniques applied and how the results of those techniques were communicated in text, numbers, tables, or data visualizations
2. Consder whether you consider this research paper to be reproducibile and whether you consider this paper to be replicable. Refer to the National Academies of Sciences, Engineering and Medicine definitions of reproducibility and replicability and our prior discussions about GIS as a Science.

Lab

Twitter analysis in R to be posted here! Similar to the strategy with Malcomb et al, we’ll first focus on executing and studying a worked example of code, and then we’ll focus on improving the analysis & applying to a new case: assessing whether the spatial distribution of original tweets represents a fake tweet storm or the real risk and impact of Hurricane Dorian

1. Please fork and then clone the RE-Dorian repository.
2. Download dorian_raw.RData into the data/raw/private folder
3. Download november.RData into the data/derived/private folder

Spatial Twitter Research Resources

Where to get free historic twitter data?

• GWU Libraries
• trackmyhashtag

Resources for using rtweet to drive the Twitter Search API (6-8 days of recent tweets)

• rtweet and its search_tweets function
• Twitter Search API
• Tweet objects
• Tweet object geospatial metadata
• Example tweet payload (with annotations): example_tweet.json
• rehydratoR: download tweets using tweet ID’s

Main Page