Machine Learning

Applied Machine Learning course: Forecasting Economic Aid Disbursements with Python

Social Media Mining: Spatiotemporal Twitter Analysis of the Venezuelan Food Crisis

(This research will be featured at the 2nd International Food Insecurity & Sustainability Conference in June 2017.)

Abstract
Social media from countries with limits to free speech is often the most reliable source of event occurrence and is a reliable alternative form of journalism. Spatiotemporal analysis of location-based social media data allows new ways to describe events. Almost 37,000 Spanish geo-tagged Tweets from the city of Caracas, Venezuela were used to observe reactions to the food shortage crisis within each of the city’s five municipalities. The number of Tweets over time is explored. The hypotheses of whether certain Tweets are particular to a municipality location is tested using multinomial naïve Bayes, logistic regression and k-nearest neighbor machine learning classifiers.

Classifier_accuracy

Infographic2

Week 9: Mulitnomial NB Classifiers

Week 7: Network X Example of my Twitter

m07-networkx-laurahkahnviz

Week 3: K-Nearest Neighbor Python Code

wk3-evaluatingclassifiers

Week 4: Linear Regression from SkLearn Module

wk3-evaluationcode

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s