Data and information visualization: Difference between revisions

Revision as of 15:38, 27 June 2025

Revision as of 07:07, 11 July 2025

Line 10:

'''Information visualization''' deals with multiple, large-scale and complicated datasets which contain quantitative data, as well as qualitative, and primarily abstract information, and its goal is to add value to raw data, improve the viewers' comprehension, reinforce their cognition and help derive insights and make decisions as they navigate and interact with the graphical display. Visual tools used include [[map]]s for ___location based data; ''hierarchical''<ref>Heer, Jeffrey, Bostock, Michael, Ogievetsky, Vadim (2010) A tour through the visualization zoo, Communications of the ACM, Volume 53, Issue 6 Pages 59 - 67 https://doi.org/10.1145/1743546.1743567</ref> organisations of data; displays that prioritise ''relationships'' such as [[Sankey diagram]]s; [[flowchart]]s, [[timeline]]s.

[[Emerging technologies]] like [[virtual reality|virtual]], [[augmented reality|augmented]] and [[mixed reality]] have the potential to make information visualization more immersive, intuitive, interactive and easily manipulable and thus enhance the user's [[visual perception]] and [[cognition]].<ref>{{Citation |title=Visualizing Big Data with augmented and virtual reality: challenges and research agenda. |last1=Olshannikova |first1=Ekaterina |last2=Ometov |first2=Aleksandr |last3=Koucheryavy |first3=Yevgeny |last4=Ollson |first4=Thomas |journal=[[Journal of Big Data]] |volume=2 |issue=22 |year=2015 |article-number=22 |doi=10.1186/s40537-015-0031-2|doi-access=free }}</ref> In data and information visualization, the goal is to graphically present and explore abstract, non-physical and non-spatial data collected from [[database]]s, [[information system]]s, [[file system]]s, [[document]]s, [[Marketing information system|business data]], which is different from ''[[scientific visualization]]'', where the goal is to render realistic images based on physical and [[Geographic_data_and_information|spatial]] [[scientific data]] to confirm or reject [[hypotheses]].<ref>{{Citation |author=Card, Mackinlay, and Shneiderman |title=Readings in Information Visualization: Using Vision to Think |pages=6–7 |year=1999 |publisher=Morgan Kaufmann}}</ref>

Effective data visualization is properly sourced, contextualized, simple and uncluttered. The underlying data is accurate and up-to-date to ensure insights are reliable. Graphical items are well-chosen and aesthetically appealing, with shapes, colors and other visual elements used deliberately in a meaningful and non-distracting manner. The visuals are accompanied by supporting texts. Verbal and graphical components complement each other to ensure clear, quick and memorable understanding. Effective information visualization is aware of the needs and expertise level of the target audience.<ref name=IBM>{{Cite web |title=What is data visualization? |url=https://www.ibm.com/topics/data-visualization |website=IBM |date=28 September 2021 |access-date=27 March 2023}}</ref><ref name="Nussbaumer Knaflic"/> Effective visualization can be used for conveying specialized, complex, [[big data]]-driven ideas to a non-technical audience in a visually appealing, engaging and accessible manner, and ___domain experts and executives for making decisions, monitoring performance, generating ideas and stimulating research.<ref name=IBM/><ref name=HDSR/> Data scientists, analysts and data mining specialists use data visualization to check data quality, find errors, unusual gaps, missing values, clean data, explore the structures and features of data, and assess outputs of data-driven models.<ref name=HDSR>{{Cite journal |title=Why Is Data Visualization Important? What Is Important in Data Visualization? |author=Antony Unwin |journal=Harvard Data Science Review |url=https://hdsr.mitpress.mit.edu/pub/zok97i7p/release/4 |date=31 January 2020 |volume=2 |issue=1 |doi=10.1162/99608f92.8ae4d525 |access-date=27 March 2023|doi-access=free }}</ref> Data and information visualization can be part of ''data storytelling'', where they are paired with a [[narrative]] structure, to contextualize the analyzed data and communicate insights gained from analyzing it to convince the audience into making a decision or taking action.<ref name="Nussbaumer Knaflic"/><ref>{{Citation |title=Effective Data Storytelling: How to Drive Change with Data, Narrative and Visuals |author=Brent Dykes |publisher=John Wiley & Sons |page=16 |year=2019}}</ref> This can be contrasted with [[statistical graphics]], where complex data are communicated graphically among researchers and analysts to help them perform [[exploratory data analysis]] or convey results of such analyses, where visual appeal, capturing attention to a certain issue and storytelling are less important.<ref>{{Citation |title=Statistics: Concepts and Applications for Science |author=David C. LeBlanc |publisher=Jones & Bartlett Learning |year=2004 |pages=35–36}}</ref>

Data and information visualization is interdisciplinary, it incorporates principles found in [[descriptive statistics]],<ref>{{cite journalbook|last1=Grandjean|first1=Martin|author1-linktitle=Handbook of Digital Public History |titlechapter=Data Visualization for History |journalauthor1-link=Handbook of Digital Public History|date=2022|volume=|issue=|pages=291–300|doi=10.1515/9783110430295-024|isbn=9783110430295 |url=https://shs.hal.science/halshs-03775019/document}}</ref> [[visual communication]], [[graphic design]], [[cognitive science]] and, [[interactive computer graphics]] and [[human-computer interaction]].<ref>{{Citation |title=A Framework for Visualizing Information |author=E.H. Chi |publisher=Springer Science & Business Media |year=2013 |page=xxiii}}</ref> Since effective visualization requires design skills, statistical skills and computing skills, it is both an art and a science.<ref name="Gershon">{{cite journal |last1=Gershon |first1=Nahum |last2=Page |first2=Ward |title=What storytelling can do for information visualization |journal=Communications of the ACM |date=1 August 2001 |volume=44 |issue=8 |pages=31–37 |doi=10.1145/381641.381653|s2cid=7666107 }}</ref> [[Visual analytics]] marries statistical data analysis, data and information visualization and human analytical reasoning through interactive visual interfaces to help users reach conclusions, gain actionable insights and make informed decisions which are otherwise difficult for computers to do. Research into how people read and misread types of visualizations helps to determine what types and features of visualizations are most understandable and effective.<ref name="Mason">{{Cite journal |first1=Betsy |last1=Mason |title=Why scientists need to be better at data visualization |url=https://knowablemagazine.org/article/mind/2019/science-data-visualization |journal=Knowable Magazine |date=November 12, 2019 |doi=10.1146/knowable-110919-1 |doi-access=free|url-access=subscription }}</ref><ref name="O'Donoghue">{{cite journal |last1=O'Donoghue |first1=Seán I. |last2=Baldi |first2=Benedetta Frida |last3=Clark |first3=Susan J. |last4=Darling |first4=Aaron E. |last5=Hogan |first5=James M. |last6=Kaur |first6=Sandeep |last7=Maier-Hein |first7=Lena |last8=McCarthy |first8=Davis J. |last9=Moore |first9=William J. |last10=Stenau |first10=Esther |last11=Swedlow |first11=Jason R. |last12=Vuong |first12=Jenny |last13=Procter |first13=James B. |title=Visualization of Biomedical Data |journal=Annual Review of Biomedical Data Science |date=2018-07-20 |volume=1 |issue=1 |pages=275–304 |doi=10.1146/annurev-biodatasci-080917-013424 |url=https://www.annualreviews.org/doi/full/10.1146/annurev-biodatasci-080917-013424 |access-date=25 June 2021|hdl=10453/125943 |s2cid=199591321 |hdl-access=free }}</ref> Unintentionally poor or intentionally misleading and deceptive visualizations can function as powerful tools which disseminate [[misinformation]], manipulate public perception and divert [[public opinion]].<ref>{{Citation |title=Misinformed by Visualization: What Do We Learn From Misinformative Visualizations? |author1=Leo Yu-Ho Lo |author2=Ayush Gupta |author3=Kento Shigyo |author4=Aoyu Wu |author5=Enrico Bertini |author6=Huamin Qu}}</ref> Thus data visualization literacy has become an important component of [[data literacy|data]] and [[information literacy]] in the [[information age]] akin to the roles played by [[literacy|textual]], [[numeracy|mathematical]] and [[visual literacy]] in the past.<ref>{{Citation |author1=Börner, K. |author2=Bueckle, A. |author3=Ginda, M. |year=2019 |title=Data visualization literacy: Definitions, conceptual frameworks, exercises, and assessments |journal=Proceedings of the National Academy of Sciences |volume=116 |issue=6 |pages=1857–1864|doi=10.1073/pnas.1807180116 |doi-access=free |pmid=30718386 |bibcode=2019PNAS..116.1857B |pmc=6369751 }}</ref>

== Overview ==