Automated detection of eating disorders in dieting forums

Social media is fostering a dieting culture that encourages eating disorders. A better labeled dataset is in need for machine learning algorithms to identify high-risk posts in dieting forums. Help us examine these posts for early detection and intervention!

Watch the tutorial.

‘ED Safe Space’–Deploy NLP Classifier on Android

ED Safe Space There are five Stages of Change that occur in the recovery process of eating disorders: Pre-Contemplation, Contemplation, Preparation, Action, and Maintenance (NEDA). Pre-Contemplation is the stage where individuals have no intention to change behavior in the foreseeable future. Many of them are unaware or under-aware of their problems. This stage is alsoContinue reading “‘ED Safe Space’–Deploy NLP Classifier on Android”

Deep NLP Classifiers — CNN vs. RNN

In this blog, we will train multiple deep learning NLP classifiers to predict which kind of forum a post most likely comes from — dieting, eating disorders, general health or irrelevant forums. These models are baseline prompts waiting for better labeled training data. Please click here to help: https://www.zooniverse.org/projects/joyqiu/edetectives. Transfer GloVe embeddings GloVe word embeddingContinue reading “Deep NLP Classifiers — CNN vs. RNN”

Time Series 3 — Granger Causality Test

Let’s revisit the two time series (Figure 1) — weekly post submissions to eating disorders forums(‘ed’) and weekly post submissions to dieting forums(‘diet’). Our task is to reveal relationships between these time series and conduct granger causality test. Stationarity Before using cross-correlation function to explore relationships between two time series or conducting any temporal causalityContinue reading “Time Series 3 — Granger Causality Test”