Dynamic Wordclouds and Vennclouds for Exploratory Data Analysis
By Glen A. Coppersmith, E. Kelly. 2014
22 citations recorded by the source corpus.
The wordcloud is a ubiquitous visualization of human language, though it falls short when used for exploratory data analysis. To address some of these shortcomings, we give the viewer explicit control over the creation of the wordcloud, allowing them to interact with it in real time‐ a dynamic wordcloud. This allows iterative adaptation of the visualization to the data and inference task at hand. We next present a principled approach to visualization which highlights the similarities and differences between two sets of documents ‐ a Venncloud. We make all the visualization code (primarily JavaScript) freely available.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Percy Liang
- Mohit Bansal
- Devi Parikh
- Soujanya Poria
- Louis-philippe Morency
- Erik Cambria
- Dhruv Batra
- Jianfeng Gao
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Devi Parikh
- Dacheng Tao
- Xiaogang Wang
- Jitendra Malik
- Li Fei-Fei
- Ming-Hsuan Yang
In Statistical and Nonlinear Physics
In Human-Computer Interaction
- Percy Liang
- Soujanya Poria
- Erik Cambria
- Amir Zadeh
- Louis-philippe Morency
- Devi Parikh
- C. Lawrence Zitnick
- Saleema Amershi
Citations in the corpus
- VQA: Visual Question Answering (2015, background): “7], and can function as complementary to one another. We illustrate the similarities and differences between the word distributions in captions versus questions & answers as Vennstyle word clouds [8] with size indicating the normalized count. These are shown in Fig.8(nouns), Fig.9(verbs), and Fi”
- Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph (2018, background): “The topics covered in the final set of videos are shown in Figure 1 as a Venn-style word cloud (Coppersmith and Kelly, 2014) with the size proportional to the number of videos gathered for that topic.”
- FeatureInsight: Visual support for error-driven feature ideation in text classification (2015, methodology): “For text data, possible visual summaries range from complex techniques, as in visualizations of topic models [31], to simpler techniques like " word clouds " [32], [33].”