Predicting Opioid Overdose Crude Rates with Text-Based Twitter Features (Student Abstract)

Nupoor Gandhi, Alex Morales, Sally Man-Pui Chan, Dolores Albarracin, ChengXiang Zhai

AAAI 2020 pp. 13787-13788

doi:10.1609/AAAI.V34I10.7165 /aaai/2020/gandhi2020aaai-predicting/

Abstract

Drug use reporting is often a bottleneck for modern public health surveillance; social media data provides a real-time signal which allows for tracking and monitoring opioid overdoses. In this work we focus on text-based feature construction for the prediction task of opioid overdose rates at the county level. More specifically, using a Twitter dataset with over 3.4 billion tweets, we explore semantic features, such as topic features, to show that social media could be a good indicator for forecasting opioid overdose crude rates in public health monitoring systems. Specifically, combining topic and TF-IDF features in conjunction with demographic features can predict opioid overdose rates at the county level.

PDF AAAI Semantic Scholar

Cite

Text

Gandhi et al. "Predicting Opioid Overdose Crude Rates with Text-Based Twitter Features (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7165

Markdown

[Gandhi et al. "Predicting Opioid Overdose Crude Rates with Text-Based Twitter Features (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/gandhi2020aaai-predicting/) doi:10.1609/AAAI.V34I10.7165

BibTeX

@inproceedings{gandhi2020aaai-predicting,
  title     = {{Predicting Opioid Overdose Crude Rates with Text-Based Twitter Features (Student Abstract)}},
  author    = {Gandhi, Nupoor and Morales, Alex and Chan, Sally Man-Pui and Albarracin, Dolores and Zhai, ChengXiang},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13787-13788},
  doi       = {10.1609/AAAI.V34I10.7165},
  url       = {https://mlanthology.org/aaai/2020/gandhi2020aaai-predicting/}
}