Abstract:
Adverse event detection is essential for identifying product defects, disasters, and major socio-political events. Adverse drug events cause many hospitalizations and deaths annually. Search query logs are a key detection channel because users start their information searches online.
However, search context—including query intent and user behavior heterogeneity—is crucial for extracting information from search queries, but measuring and analyzing these aspects has prevented their use in previous studies.
DeepSAVE, a novel deep learning framework, detects adverse events from user search query logs. DeepSAVE addresses the context challenge of search-based adverse event detection using an enriched variational autoencoder with a novel query embedding and user modeling module.
DeepSAVE outperforms existing detection methods and deep learning auto encoders on three large event datasets. Ablation analysis shows that each DeepSAVE component significantly improves its performance. The results show that the search query log architecture can detect adverse events.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
