Bridging Text Visualization and Mining: A Task-Driven Survey

Abstract

Visual text analytics has recently emerged as one of the most prominent topics in both academic research and the commercial world. To provide an overview of the relevant techniques and analysis tasks, as well as the relationships between them, we comprehensively analyzed 263 visualization papers and 4,346 mining papers published between 1992-2017 in two fields: visualization and text mining. From the analysis, we derived around 300 concepts (visualization techniques, mining techniques, and analysis tasks) and built a taxonomy for each type of concept. The co-occurrence relationships between the concepts were also extracted. Our research can be used as a stepping-stone for other researchers to 1) understand a common set of concepts used in this research topic; 2) facilitate the exploration of the relationships between visualization techniques, mining techniques, and analysis tasks; 3) understand the current practice in developing visual text analytics tools; 4) seek potential research opportunities by narrowing the gulf between visualization and mining techniques based on the analysis tasks; and 5) analyze other interdisciplinary research areas in a similar way. We have also contributed a web-based visualization tool for analyzing and understanding research trends and opportunities in visual text analytics.

Privacy‐Preserving Data Visualization: Reflections on the State of the Art and Research Opportunities

“…Except for Dhotre et al [DBKO17], we sensed a lack of quality in the visual communication of information extracted from policy text. We believe that recent advances in text visualization and topic modeling [LWC*18] can have a significant effect on improving visualization techniques for communicating privacy parameters and their dependencies, as extracted from policy descriptions, and make that information accessible and actionable, especially for data subjects, who might not have appropriate levels of data literacy to comprehend the privacy risks and policies.…”

VIANA: Visual Interactive Annotation of Argumentation

“…To achieve reliable performance in these complex tasks, modern systems rely on the analysis of the underlying linguistic structures that characterize successful argumentation, rhetoric, and persuasion. Consequently, to distill the building blocks of argumentation from a text corpus, it is not sufficient to employ off-the-shelf Natural Language Processing techniques [65], which are typically developed for coarser analytical tasks (see [42] for an overview), such as with the high-level tasks of topic modeling [19] or sentiment analysis [5]. * e-mail: firstname.lastname@uni-konstanz.de Hence, to master the challenge of identifying argumentative substructures in large text corpora, computational linguistic researchers are actively developing techniques for the extraction of argumentative fragments of text and the relations between them [41].…”

Interactive Steering of Hierarchical Clustering

“…The gap between unsupervised hierarchical clustering algorithms and task-relevant user needs calls for a visual analysis solution that involves users in the hierarchy building process [7]. Our analysis of current challenges to fill the gap leads to the arXiv:2009.09618v1 [cs.LG] 21 Sep 2020 identification of two key requirements for improving the initial algorithmically constructed hierarchies and reducing user efforts in refining them.…”