Adverse drug reaction detection on social media with deep linguistic features

A novel textual data augmentation method for identifying comparative text from user-generated content

“…To summarize types of syntactic structures of a specific corpus, we generate and observe the syntactic structures of a small part of comparative text randomly selected from the training dataset. We adopt Stanford Parser 6 , which is widely used for syntactic structure generation (Zhang et al, 2020), to extract dependency tree of key syntactic elements for comparative text. As shown in Fig.…”

Social Media for Exploring Adverse Drug Events Associated with Multiple Sclerosis

“…Some studies on ADEs proposed and implemented near real-time pipelines and models for ADE detection and prediction [18], [21]. ADEs studies utilized a variety of techniques such as but not limited to; association rule mining [20], natural language processing (NLP) and deep learning [22], extracting deep linguistic features [23], ensemble classification [24], statistical modeling [25], and topic modeling.…”

A two-layer nested heterogeneous ensemble learning predictive method for COVID-19 mortality

“…When constructing a time series forecasting model, we divide the data set into two parts: the training set and test set. The training set is used to train the model, while the test set is used to test the performance of the model [34]. For traditional time series forecasting models, the original time series data can be used directly to construct the model.…”