Data visualisation in research

“A picture is worth more than thousand words.”

Maybe you are asked to demonstrate some complexity (not complication) in your research, and that complexity is achieved by being creative and innovative – for example, using or adopting a concept or a method by crossing the boundaries of the discipline. Writing clearly as well as visualising properly can help the reader to understand the complexity in your research.

In this blog, I shall discuss how to represent that complexity you want to see in your research, so it reads well and generates more interests. Also, I provide a list of references that might be useful (see bibliography below).

What is data visualisation?

Data visualisation is a graphical representation of some information, by using several visual elements such as figures and diagrams, but not limited to these (see examples below). Such graphical representation helps the reader to understand the complexity of the research, by identifying the processes implemented, relationships between terms and concepts, and patterns and trends within data. Data visualisation can be used to represent any sort of data, be they quantitative or qualitative data and be they primary or secondary data. Visualisation is a key tool to deal with big data (e.g., a corpus of emails or messages, a dataset of more than 200 conversations from Facebook groups, trillions of rows of data generated every day). You may also need some trainings sessions to know how to visualise the data in a proper way.

Where do we need data visualisation?

Researchers may find themselves visualising data in their research each time they discuss or present an idea. This is what we call ‘built up diagrams’ (e.g., adding an item to the diagram as the discussion continues). This can be found in any chapter in your thesis. The processes we implement in the research can also be visualised. PowerPoint Smart arts are excellent tools to represent the different processes.

When collecting data, researchers may need some visual aids that represent some information that help the participants to understand clearly the themes the researchers are investigating. In case researchers decide to use visual aids, they need to address the ethical considerations of the materials used before starting data collection.

For data analysis, diagrams are used to represent how data analysis was conducted, and figures to reveal the findings (bar charts, pie charts, scattered chart, etc.). Tables can also be used to summarise facts and statistics. Heat maps are another way of representing the findings (e.g., the distribution of languages within a corpus of conversations. Excel can be used to conduct a quantitative analysis (you need to install data analysis tool in your laptop) and to represent the findings (figures and heat maps). The selection of any type of data visualisation requires understanding the data.

Some examples of data visualisation

Area chart

    Bar chart

    Box-and-whisker plots

    Bubble cloud

    Bullet graph

    Cartogram

    Circle view

    Dot distribution map

    Gantt chart

    Heat map

    Highlight table

    Histogram

    Matrix

    Network

    Polar area

    Radial tree

    Scatter plot (2D or 3D)

    Streamgraph

    Text tables

    Timeline

    Treemap

    Wedge stack graph  

   Word cloud         

Needed for your career!

In the past, there was a sharp distinction between ‘creative storytelling’ and ‘technical analysis’. However, there has been a shift of interest towards a more inclusive framework which requires a combination of those. Data visualisation is both ‘analysis’ and ‘creativity’ that the modern world demands. Nowadays companies aim to recruit someone who is experienced in data visualisation. Despite the computerised visualisation tools available to date, one may still need to develop his/her skills regarding data visualisation, because ‘creativity’ and ‘criticality’ are required.

      ‘Aim for a proper data visualization’

• The colours used to represent different trends or patterns could be an issue for readers.
• The right diagram or figure also helps to understand the research better.
• A thorough understanding of the items or the data put for visualisation is important, because that helps to choose which type of data visualisation is needed.
• Avoid ambiguities: use the right arrows and shapes, and include proper wording in the diagram
• In figures, display some features that can be read, and those include percentages, frequencies, titles, and any other important feature
• Display structural features on maps, by using ‘R’ (a programming language and free software environment for statistical computing and graphics)
• Using a geographic information system (GIS) data to create high-resolution maps
• Drawing georeferenced maps (in linguistics) to mark specific areas on a map (e.g. a language location, isoglosses, etc.) and make them compatible with other geographical information discussed so far in the research (Bibico, 2012)

Bibliography

Here is a list of some references that you might consult to enrich your knowledge so as to demonstarte a proper data visualisation:

Bertin, J. (1982): Graphische Darstellungen. Graphische Verarbeitung von Informationen. Berlin/New York: de Gruyter.

Bibico, H. Visualisation and online presentation of linguistic data. Language Documentation & Conservation Special Publication, 3, pp.96-104.

Card, S. K. / Mackinlay, J. D. / Shneiderman, B. (1999): Readings in Information Visualization: Using Vision to Think. San Francisco: Morgan Kaufmann Publishers.

Carpendale, M. (2003): ‘Considering visual variables as a basis for information visualisation’, Dept. of Computer Science, University of Calgary, Canada, Tech. Rep. 2001-693-16.

Collins, C., Penn, G. and Carpendale, S. (2008). Interactive visualization for computational linguistics. ACL-08: HLT Tutorials. Retrieved from: http://www.cs.utoronto.ca/~ccollins/acl2008-vis.pdf. Access date: December 3, 2009.

Culy, C., Lyding, V., and Dittmann, H. 2011c. “Visualizing Dependency Structures” In: Proc. of the annual meeting of the Gesellschaft für Sprachtechnologie und Computerlinguistik (GSCL), Hamburg, Germany, 81-86.

Culy, C., Lyding, V., and Dittmann, H. 2011b. “xLDD: Extended Linguistic Dependency Diagrams”  in Proceedings of the 15th International Conference on Information Visualisation IV2011, 12, 13 – 15 July 2011, University of London, UK. 164-169.

Culy, C., Lyding, V., and Dittmann, H. 2011a. “Structured Parallel Coordinates: a visualization for analyzing structured language data” In: Proceedings of the 3rd International Conference on Corpus Linguistics, CILC-11, April 6-9, 2011, Valencia, Spain, 485-493.

Culy, C. and V. Lyding. 2011. “Corpus Clouds – Facilitating Text Analysis by Means of Visualizations” in Human Language Technology: Challenges for Computer Science and Linguistics, Zygmunt Vetulani (ed.). Berlin:Springer. 351-360.

C. Culy & V. Lyding. 2010.”Double Tree: An Advanced KWIC Visualization for Expert Users” In: Information Visualization, Proceedings of IV 2010, 2010 14th International Conference Information Visualization, 26-29 July 2010 London, United Kingdom, 98-103.

C. Culy & V. Lyding. 2010. “Visualizations for exploratory corpus and text analysis”. In: Proceedings of the 2nd International Conference on Corpus Linguistics CILC-10, May 13-15, 2010, A Coruña, Spain, pp. 257-268.

C. Culy & V. Lyding. 2009. “Corpus Clouds – facilitating text analysis by means of visualizations”. In: Proceedings of the 4th Language & Technology Conference, LTC’09 . Poznan, Poland, pp. 521-525.

Hearst, M. (2009): Search User Interfaces. Cambridge: Cambridge University Press. Hearst, M. A. (1995): ‘Tilebars: Visualization of term distribution information in full text information access’, In: Proc. CHI’95, Denver, Colorado, pp. 56-66.

Lyding, V.,  Lapshinova-Koltunski, E., Degaetano-Ortlieb, S.,  Dittmann, H.  and  Culy, C. (2012): ‘Visualising Linguistic Evolution in Academic Discourse’, In: Proceedings of the EACL 2012 Joint Workshop of LINGVIS & UNCLH, April 2012, Avignon, France, Association for Computational Linguistics, pp. 44-48.

Tufte, E. (1999): Envisioning Information. Cheshire, Connecticut: Graphics Press LLC. Tufte, E. (2006): Beautiful Evidence. Cheshire, Connecticut: Graphics Press LLC.

Todorovic, D. (2008): ‘Gestalt principles’. Scholarpedia, 3(12):5345, Retrieved from: http://www.scholarpedia.org/article/Gestalt_principles. Access date: December 4, 2009.

Wattenberg, M. / Viégas, F. B. (2008): The word tree, an interactive visual concordance. In: IEEE Trans. on Visualization and Computer Graphics, vol. 14(6), pp. 1221-1228, Nov.-Dec. 2008.