Document Type

Conference Paper

Publication Date

2016

Publication Title

LIVVIL: Logging Interactive Visualizations & Visualizing Interaction Logs. Workshop IEEE VIS 2016

Pages

24-28

Conference Name

LIVVIL: Logging Interactive Visualizations & Visualizing Interaction Logs. Workshop IEEE VIS 2016, October 23, 2016, Baltimore, Maryland, USA

Abstract

After data analysis, recalling and communicating the steps and rationale followed during the analysis can be difficult. This paper explores the use of interaction logs to generate summaries of an analyst's interest based on interactions with specific data items in a text analysis scenario. Our approach uses data-interaction events as a proxy for user interest in and experience of information. Logging can produce verbose logs that detail all available readable content, so the discussed approach uses topic modeling (LDA) over different time segments to summarize the verbose information and generate visualizations of the history of user interest. Our preliminary results motivate a discussion on potential benefits and challenges of using interaction data to generate provenance visualizations for text analytics.

Comments

Publisher landing page: "https://inria.hal.science/hal-01535913/"

Rights

© The Authors.

Distributed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Original Publication Citation

Linder, R., Peña, A., & Jayarathna, S. (2016). Results and challenges in visualizing analytic provenance of text analysis tasks using interaction logs [Conference paper]. LIVVIL: Logging Interactive Visualizations & Visualizing Interaction Logs. Workshop IEEE VIS 2016, Baltimore, Maryland, USA. https://inria.hal.science/hal-01535913/file/proceedings.pdf#page=25

ORCID

0000-0002-4879-7309 (Jayarathna)

Download

Share

COinS