• Publications
  • Influence
Predicting Post-Test Performance from Online Student Behavior : A High School MOOC Case Study
With the success and proliferation of Massive Open Online Courses (MOOCs) for college curricula, there is demand for adapting this modern mode of education for high school courses. Online and openExpand
  • 18
  • 2
  • PDF
Predicting Post-Test Performance from Student Behavior: A High School MOOC Case Study
TLDR
In this paper, we analyze student post-test performance to determine the success of a high school computer science MOOC, which we treat as a post test. Expand
  • 13
  • 1
  • PDF
A Socio-linguistic Model for Cyberbullying Detection
TLDR
We propose a socio-linguistic model which detects cyberbullying content in messages, discovers latent text categories, identifies participant roles and exploits social interactions. Expand
  • 13
  • 1
  • PDF
Disambiguating Energy Disaggregation: A Collective Probabilistic Approach
TLDR
We introduce a probabilistic framework which infers the energy consumption of individual appliances using a hinge-loss Markov random field (HL-MRF), which admits highly scalable inference. Expand
  • 10
  • 1
  • PDF
Sustainability at scale: towards bridging the intention-behavior gap with sustainable recommendations
TLDR
We propose a probabilistic framework that uses domain knowledge to identify sustainable products and customers, and uses these labels to predict customer purchases. Expand
  • 11
  • PDF
Rapidly Personalizing Mobile Health Treatment Policies with Limited Data
TLDR
We present IntelligentPooling, which learns personalized policies via an adaptive, principled use of other users' data. Expand
  • 2
  • PDF
The Impact of Environmental Stressors on Human Trafficking
TLDR
We investigate the potential impact of catastrophic storms on the criminal activity of human trafficking and provide evidence for each. Expand
  • 2
  • PDF
Intelligent Pooling in Thompson Sampling for Rapid Personalization in Mobile Health
TLDR
We use the data collected from a real-world mobile health study to build a generative model and evaluate the proposed algorithm in comparison with two natural alternatives: learning the treatment policy separately per person and learning a single treatment policy for all people. Expand
  • 2
  • PDF
IntelligentPooling: Practical Thompson Sampling for mHealth
TLDR
In mobile health (mHealth) smart devices deliver behavioral treatments repeatedly over time to a user with the goal of helping the user adopt and maintain healthy behaviors. Expand
  • 1
  • PDF
Detecting Cyber-bullying from Sparse Data and Inconsistent Labels
May 2017 Proposed Thesis: Probabilistic Methods for Data-Driven Social Good UC Santa Cruz, Santa Cruz Qualifying Exam Committee: Lise Getoor, Brent Haddad, John Musacchio, Rayid Ghani January 2013Expand
  • 2
  • PDF