Answers to "What about qualitative data in learning analytics?"
Topic Editor: Dr. Martin Pusic, New York University
Qualitative data and research are usually characterized by textual data with analysis yielding meanings, concepts, themes and eventually new theories. They are not generally amenable to numerical manipulation or summarization. As such, one would think them as being beyond the reach of learning analytics with its considerable emphasis on algorithms and computation. However, the digitization of text, speech and video has made the data increasingly available to computational approaches. Insofar as Learning Analytics is used to enhance the process of understanding, digital processes can be helpful along the full spectrum of data types. A simple example is the Word Cloud where words are counted and then visualized according to their frequency.
As processes for Natural Language Processing techniques improve, multimodal analysis will become increasingly tractable. For example sentiment analysis can rate snippet of text as to their emotional tone, allowing generalized approaches across a large corpus of text as seen in an Electronic Health Record. Below is a screen capture of an experimental dashboard that extracts textual student feedback from the evaluation system and assigns a "sentiment score" represented numerically and with colour in the right-hand column. (Screen capture courtesy of Marina Marin, New York University.)
Finally, we point out that even with the numerical analyses that are typical of Data Science generally, the results frequently only rise to the level of hypothesis generation, requiring complementary meaning-making using mixed methods processes. (Ellaway 2014)
Ellaway, R. H., Pusic, M. V., Galbraith, R. M., & Cameron, T. (2014). Developing the role of big data and analytics in health professional education. Medical Teacher, 36(3), 216-222.
McNamara D, Allen L, Crossley S, Dascalu M, Perret C. Natural Language Processing and Learning Analytics. Chapter 8 (pp 93-104) In Lang, Charles, George Siemens, Alyssa Wise, and Dragan Gasevic, eds. Handbook of learning analytics. SOLAR, Society for Learning Analytics and Research, 2017.