A Weakly-Supervised Attention-based Visualization Tool for Assessing Political Affiliation
This provides a tool for political analysts to interpret stance detection models, though it appears incremental in combining existing methods.
The researchers developed a weakly-supervised deep neural network with attention mechanisms to determine political affiliations from text, creating a web-based visualization tool for exploring the results.
In this work, we seek to finetune a weakly-supervised expert-guided Deep Neural Network (DNN) for the purpose of determining political affiliations. In this context, stance detection is used for determining political affiliation or ideology which is framed in the form of relative proximities between entities in a low-dimensional space. An attention-based mechanism is used to provide model interpretability. A Deep Neural Network for Natural Language Understanding (NLU) using static and contextual embeddings is trained and evaluated. Various techniques to visualize the projections generated from the network are evaluated for visualization efficiency. An overview of the pipeline from data ingestion, processing and generation of visualization is given here. A web-based framework created to faciliate this interaction and exploration is presented here. Preliminary results of this study are summarized and future work is outlined.