NetReAct: Interactive Learning for Network Summarization
This work provides an interactive method for improving network summaries, which is significant for intelligence analysts and others who need to make sense of complex document networks.
This paper addresses the challenge of generating useful network summaries by incorporating human feedback. It introduces NetReAct, an interactive network summarization algorithm that uses reinforcement learning to integrate user input, resulting in high-quality summaries and visualizations that reveal hidden patterns more effectively than non-trivial baselines across two datasets.
Generating useful network summaries is a challenging and important problem with several applications like sensemaking, visualization, and compression. However, most of the current work in this space do not take human feedback into account while generating summaries. Consider an intelligence analysis scenario, where the analyst is exploring a similarity network between documents. The analyst can express her agreement/disagreement with the visualization of the network summary via iterative feedback, e.g. closing or moving documents ("nodes") together. How can we use this feedback to improve the network summary quality? In this paper, we present NetReAct, a novel interactive network summarization algorithm which supports the visualization of networks induced by text corpora to perform sensemaking. NetReAct incorporates human feedback with reinforcement learning to summarize and visualize document networks. Using scenarios from two datasets, we show how NetReAct is successful in generating high-quality summaries and visualizations that reveal hidden patterns better than other non-trivial baselines.