The influence of font scale on semantic expression of word cloud
- PDF / 1,492,687 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 78 Downloads / 149 Views
R E G UL A R P A P E R
Lu Yang • Jie Li • Wenhuan Lu • Yi Chen • Kang Zhang • Yan Li
The influence of font scale on semantic expression of word cloud
Received: 14 October 2019 / Revised: 27 May 2020 / Accepted: 19 June 2020 Ó The Visualization Society of Japan 2020
Abstract Word cloud is a common text visualization technique. With the ability of presenting the keywords of a document in a direct way, it has been widely applied in many real-world situations. However, to better represent the main idea of a document, a critical aspect for word cloud design is to set an appropriate font size to facilitate semantic expression. In this paper, we explore the influence of font scale on semantic expression and evaluate font size of word cloud in a more systematic approach. To quantify semantic information of a document, we utilize an LDA ensemble-based method to support interactive selection of topics and obtain the semantics of documents in a scientific way. We conducted two pilot studies to decide important attributes of word clouds for the formal study. Through formal study 1, we find that the scale affects the semantic expression of word cloud, including accuracy, time and confidence in making judgments. In study 2, we explored different semantic expression patterns of word clouds under different document categories. Our findings aimed at optimizing the scale of word cloud and improving its semantic expressing ability. Keywords Visualization Word cloud Semantic expression LDA ensemble-based method
L. Yang J. Li W. Lu College of Intelligence and Computing, Tianjin University, Tianjin, China E-mail: [email protected] J. Li E-mail: [email protected] W. Lu E-mail: [email protected] Y. Chen Beijing Key Laboratory of Big Data Technology for Food Safety, Beijing Technology and Business University, Fangshan, China E-mail: [email protected] K. Zhang The University of Texas at Dallas, Richardson, USA E-mail: [email protected] Y. Li (&) University of Science and Technology of China, Hefei, China E-mail: [email protected]
L. Yang et al.
1 Introduction In an information overload society, the need for tools that present information and enable the visual exploration has grown, which drives the development of a variety of programming frameworks for information visualization (Li et al. 2018; Mei et al. 2018; Wei et al. 2020). Word cloud, as a classic text visualization technique, has been widely applied in many real-world situations in facilitating semantic understanding. A word cloud consists a set of words, whose font sizes reflect words’ relevance to the document (Xu et al. 2016). An important criterion to the quality of a generated word cloud is whether it grasps semantic meaning of the target document in an accurate way. As a result, the high-frequency words are usually presented in a strong and eye-catching text effect to help readers make quick and educated judgments about the main idea of the reading materials, as shown in Fig. 1 (a classroom scenario). In this paper, we choose font scale as the e
Data Loading...
