Multi-dimensional Features for Prediction with Tweets
This work addresses the problem of predicting HIV outbreaks for public health officials in specific U.S. regions, but it is incremental as it builds on existing Twitter NLP methods by adding location-based features.
The paper tackled predicting HIV new diagnosis rates per county using Twitter data by developing multi-dimensional features that combine text and location information, showing that this approach significantly improves predictive power compared to using text-based features alone.
With the rise of opioid abuse in the US, there has been a growth of overlapping hotspots for overdose-related and HIV-related deaths in Springfield, Boston, Fall River, New Bedford, and parts of Cape Cod. With a large part of population, including rural communities, active on social media, it is crucial that we leverage the predictive power of social media as a preventive measure. We explore the predictive power of micro-blogging social media website Twitter with respect to HIV new diagnosis rates per county. While trending work in Twitter NLP has focused on primarily text-based features, we show that multi-dimensional feature construction can significantly improve the predictive power of topic features alone with respect STI's (sexually transmitted infections). By multi-dimensional features, we mean leveraging not only the topical features (text) of a corpus, but also location-based information (counties) about the tweets in feature-construction. We develop novel text-location-based smoothing features to predict new diagnoses of HIV.