Selected Publications

In this paper, we introduce Tweedr, a Twitter mining tool that extracts actionable information for disaster relief workers during natural disasters. The Tweedr pipeline consists of three main parts: classification, clustering andextraction. In the classification phase, we use a variety of classification methods (sLDA, SVM, and logistic regression) to identify tweets reporting damage or casualties. In the clustering phase, we use filters to merge tweets that are similar to one another; and finally, in the extraction phase, we extract tokens and phrases that report specific information about different classes of infrastructure damage, damage types, and casualties. We empirically validate our approach with tweets collected from 12 different crises in the United States since 2006.

Recent Publications

Recent Talks

Recent Posts

In AP Calculus, my teacher introduced me to Euler’s formula, and he proved this equality by breaking up the Taylor Series representation of the exponential function into the Taylor Series of cosine and sine. This algebraic proof is simple, and I’ve included it below for readers who are not familiar with it: $$e^{ix} = \sum_{n=0} ^{\infty} \dfrac{(ix)^n}{n!} = \dfrac{(ix)^0}{0!} + \dfrac{ix}{1!} + … + \dfrac{(ix)^n}{n!} + ..$$ We can split this series into two summations, one for the odd terms and the other for evens.



Various projects I have worked on


User and Entity Behavior Analysis software I helped design.

A/B Testing with Hierachical Models in Python

Using Beta Binomial Hierachical Models to perform AB Testing.

Density Based Clustering

An exploration of different probabilistic density clustering algorithms


Resume available on request