Visual Computing

University of Konstanz
IEEE Transactions on Visualization and Computer Graphics

Visual Analytics for Topic Model Optimization based on User-Steerable Speculative Execution

M. El-Assady, F. Sperrle, O. Deussen, D. Keim, C. Collins
Teaser of Visual Analytics for Topic Model Optimization based on User-Steerable Speculative Execution

The Tree-Speculation View is used to compare two topic models and shows the differences. Deleted branches are blurred, while moved, newly added and removed nodes and keywords are highlighted. To efficiently guide users towards perceivable model quality improvements, our system automatically proposes optimizations like the merge of two topics depicted here. By visualizing model uncertainties and low quality topics, we foster trust in the model and empower users to directly address these shortcomings

Material

Paper (.pdf, 3.4 MB)

Abstract

To effectively assess the potential consequences of human interventions in model-driven analytics systems, we establish the concept of speculative execution as a visual analytics paradigm for creating user-steerable preview mechanisms. This paper presents an explainable, mixed-initiative topic modeling framework that integrates speculative execution into the algorithmic decision- making process. Our approach visualizes the model-space of our novel incremental hierarchical topic modeling algorithm, unveiling its inner-workings. We support the active incorporation of the user’s domain knowledge in every step through explicit model manipulation interactions. In addition, users can initialize the model with expected topic seeds, the backbone priors. For a more targeted optimization, the modeling process automatically triggers a speculative execution of various optimization strategies, and requests feedback whenever the measured model quality deteriorates. Users compare the proposed optimizations to the current model state and preview their effect on the next model iterations, before applying one of them. This supervised human-in-the-loop process targets maximum improvement for minimum feedback and has proven to be effective in three independent studies that confirm topic model quality improvements.

BibTeX

@article{ElAssady2018VisualAnalytic,
  author     = {M. El-Assady and F. Sperrle and O. Deussen and D. Keim and C. Collins},
  journal    = {IEEE Transactions on Visualization and Computer Graphics},
  title      = {Visual Analytics for Topic Model Optimization based on User-Steerable Speculative Execution},
  volume     = {to appear},
  year       = {2018},
  url        = {http://graphics.uni-konstanz.de/publikationen/ElAssady2018VisualAnalytic},
}