Rapid understanding of scientific paper collections: Integrating statistics, text analytics, and visualization

Abstract

Keeping up with rapidly growing research fields, especially when there are multiple interdisciplinary sources, requires substantial effort for researchers, program managers, or venture capital investors. Current theories and tools are directed at finding a paper or website, not gaining an understanding of the key papers, authors, controversies, and hypotheses. This report presents an effort to integrate statistics, text analytics, and visualization in a multiple coordinated window environment that supports exploration. Our prototype system, Action Science Explorer (ASE), provides an environment for demonstrating principles of coordination and conducting iterative usability tests of them with interested and knowledgeable users. We developed an understanding of the value of reference management, statistics, citation text extraction, natural language summarization for single and multiple documents, filters to interactively select key papers, and network visualization to see citation patterns and identify clusters. A three‐phase usability study guided our revisions to ASE and led us to improve the testing methods.

Information and the gaining of understanding

“…This is exemplified by the system of Donne, Shneiderman, Gove, Klavans, and Dorr [14], which explicitly claims to aid the rapid understanding of set of literature.…”

Exploring Scholarly Data with Rexplore

“…For instance, in the example given in Section 1, where a research area needs to be investigated in the context of making a decision about a special issue proposal, what is needed from a system is the ability to support the user in identifying quickly the important trends in the area -such as, whether it is growing (and in this case where are the new researchers coming from) or shrinking (and in this case where are the researchers migrating to), rather than following citation links or locating a specific paper. Another negative side-effect of this 'bias' is the aforementioned problem highlighted by Dunne et al [1], concerning the lack of an integrated environment, supporting a seamless exploration of the space of scholarly data, as opposed to providing 'atomic' functionalities, to do with static visualizations or search and citation services, which is the situation with most current systems.…”

“…Nevertheless, as Dunne et al point out [1], there is still a need for an integrated solution, where the different scholarly tasks are provided in a coherent manner, through an environment able to support a seamless navigation between different views and functionalities. In addition, as discussed in detail in the next section, we believe that there are also a number of important functionalities, which are crucial to providing effective support for exploring and making sense of scholarly data, but are currently missing from existing solutions.…”

A “Look” into the IS Discipline through the Lens of MIS Quarterly: A Visual Examination of Scholar Characteristics

“…Previous research has been done in the area of text analysis and visualization [24][25][26] of trends on a collection of published work of researchers over a certain timeline [27 & 28]. This is one of the very interesting topics to study, when a field of research is growing at a very fast pace, as is the case with information systems research.…”