Intent-Aware Visualization Recommendation for Tabular Data

Atsuki Maruta, Makoto P. Kato

Abstract: This paper proposes a visualization recommender system for tabular data with a visualization intent (e.g., “population trends in Italy” and “smartphone market share”). The proposed method predicts the most suitable visualization type (e.g., line, pie, and bar charts) and visualized columns (columns used for visualization) based on statistical features extracted from the tabular data, as well as semantic features derived from the visualization intent. To predict an appropriate visualization type, we propose a bi-directional attention (BiDA) model that identifies important table columns by the visualization intent, and important parts of the intent by table headers. To identify visualized columns, we employ a pre-trained neural language model to encode both visualization intents and table columns, and estimate which columns are the most likely to be used for visualization. Since there is no available dataset for this task, we developed a new dataset consisting of over 100K tables and their appropriate visualization. The experiments revealed that our proposed methods accurately estimated suitable visualization types as well as visualized columns. The code is available at https://github.com/kasys-lab/intent-viz .

External IDs:dblp:conf/wise/MarutaK21