Introduction to the Special Issue on Learning Analytics

Abstract

This introduction to the special issue on learning analytics provides an overview of the area, acknowledging the research traditions it emerges from, such as computer-supported collaborative learning, academic analytics, and educational data mining, and the way the field aims to bridge from technological innovation to learning purposes. The introduction provides examples of areas and educational stakeholders who are served by and can benefit from learning analytics initiatives, referring throughout to the articles in this special issue.

Keywords

learning analytics academic analytics educational data mining computer-supported collaborative learning networked learning

This special issue brings together articles that address the emerging and rapidly growing field of research and development known as learning analytics. This new field, like others emerging in the wake of massive computerized connectivity and data generation effects on social behavior, bridges from technological innovation to social purposes aimed at improving learning. In calling for papers at the 1st International Conference on Learning Analytics and Knowledge in 2011, organizer George Siemens captures this intent in defining the area this way:

Learning analytics is the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs. (Siemens, 2011)

This definition is broad but contains within it the essential drivers of data and optimization of learning and the bridging function of analysis to bring the potential of data about social behavior to the service of learning (see also Siemens, 2013). For this special issue, we have also adopted a broad view of learning analytics, acknowledging the range and extent of applications of analytics that can be brought to bear on the learning process—from evaluation of academic progress in formal educational settings to the discovery and definition of learning in informal and workplace conversation and communication.

The learning analytics area as a whole endeavor bears similarities to developments seen elsewhere that use “analytics” to understand and optimize business or social processes. In the domain of learning and professional development, major areas that intersect with learning analytics, and thus the scope of its application, include computer-supported collaborative learning (CSCL), networked learning, social learning analytics, academic analytics, educational informatics, and educational data mining (EDM).

CSCL has focused on computer support for learner interaction and the promotion and outcomes of a social learning perspective (Koschmann, 1996; Miyake, 2007; Stahl, Koschmann, & Suthers, 2006). The closely related area of networked learning has focused on the effect of computer networking and connectivity on social relationships and how this can be used to promote collaborative or cooperative connections between learners, their tutors, and their learning resources (de Laat & Schreurs, 2013; Dirckinck-Holmfeld, Hodgson, & McConnell, 2012; Steeples & Jones, 2002; Thompson et al., 2013). Synergistic with both these areas are studies that use social network analysis to examine the social networks formed by and among learners; studies of learning networks apply social network analysis to problems of learning and education (Daly, 2010; Dawson, Bakharia, & Heathcote, 2010; de Laat & Schreurs, 2013; Gašević, Zouaq, & Jenzen, 2013; Haythornthwaite, 2011, 2013; Haythornthwaite & de Laat, 2011; Lockyer, Heathcote, & Dawson, 2013). Together, these areas, with their emphasis on social relationships, form the basis of social learning analytics (Buckingham Shum & Ferguson, 2012). Work across these areas includes the following:

Development of systems that support, display, and/or analyze ongoing learning and group dynamic processes

Analysis of course design features and resulting outcomes in terms of collaborative practice

Development of learning communities, in formal or informal settings

Following, supporting, and evaluating progress and practice by individuals and among individuals as members of learning communities

Description and support of interlearner collaboration through system design, learner task design, group formation, or presentation of learner interaction networks

Design and development of social learning systems that utilize networked connectivity and learning partnerships

Analysis of formal and informal learning settings and design features in terms of networked learning practices.

Other initiatives capitalize on the “big data” aspect of the analytics area. Academic analytics harnesses institutional data to address primarily administrative, institutional, and/or cross-institution analysis (Campbell, DeBlois & Oblinger, 2007; Gašević et al., 2013; Goldstein & Katz, 2005; Long & Siemens, 2011). Efforts in this area include, but are not limited to, tracking and evaluation of student course-taking patterns, including course trajectories and associated outcomes, such as retention, choice of major, grades; course mapping for curriculum management, examining the way courses overlap, intersect, and provide foundations for later courses; and enrollment, curriculum, and resource planning based on analysis of course-taking patterns and trajectories. Definition and management of information on education has also been discussed under the heading of educational informatics (e.g., Ford, 2008; Levy et al., 2003). EDM (Hershkovitz, Baker, Gobert, Wixon, & Sao Pedro, 2013; Romero & Ventura, 2007, 2010) has a strong computer science orientation drawing on statistical, machine-learning, and data-mining techniques. The emphasis of EDM is on harnessing educational data to generate models of learning behavior, using these to test predictive models about educational outcomes.

While naming only a few areas, ideas of learning analytics also draws on much work done in support of the implementation and evaluation of the social and technical dimensions of online learning/e-learning programs (Allen & Seaman, 2011; Andrews & Haythornthwaite, 2007; Hiltz & Turoff, 2005) and on the long tradition of educational technology, including intelligent tutoring systems, games, and simulations.

Across these areas and interests, learning analytics serves a number of interconnected populations, with aggregation at different levels, over different time periods, and for different purposes. While many applications focus on learning in educational settings, the research agenda embraces learning across all arenas, with a particular challenge to understand how learning happens on, with, and through the Internet. Learning analytics supports the following:

Higher-education planners aiming to gain a comprehensive view of student populations, course requirements, and future enrollments; and curriculum planners aiming to evaluate current offerings for overlap and gaps

Teachers, students, and advisors aiming to understand the place of their course content within the larger picture of department- or institution-wide offerings and of courses taken and yet to be taken

Teachers aiming to understand the impact on student learning, interaction, or other outcomes of their pedagogical approaches, instructional designs, in- and out-of-class exercises and assignments

Learners aiming to understand their learning experience against that of a population of current or even past learners, for example, relative to this year’s class of fellow students or fellow learners in a massively open online class (MOOC)

Researchers in education, educational technology, information systems, library science, and information science interested in examining and analyzing new forms of teaching and learning, designing and implementing systems for existing and new forms of teaching and learning, and providing strategic access to learning resources

Researchers and policy makers interested in learning processes in society, with emphasis on informal and nonformal learning, lifelong learning, professional development, and the way this is supported through communities of inquiry

To be sure, the aims outlined in the examples above are not new, but what is new is the computerized record and attention to how this record can be applied to connect systems to practices—from course choice to course conduct to use of library and information resources. Learning analytics is both the continuation of educational technology development and the application of new analytics to the process and outcomes of educational and informal learning practices.

Further, as found in other fields harnessing analytics for analysis of social behavior, the potential of analyzing the data generated by online and academic systems is that it provides the ability to ask new questions and to ask old questions in new ways. The data generated in online learning platforms and social networking sites as side effects of the implementation of learning management systems, and the transcripts generated around online courses in discussion boards, blogs, wikis, and Twitter, open a new window through which to see teaching and learning that then influences the design and use of learning management systems. For example, learning analytics hold the promise of real-time feedback about personal and class learning, such as through dashboards that reflect and raise awareness about ongoing learning processes (de Laat & Schreurs, 2013; Siemens, 2013; Siemens et al., 2011; Verbert, Duval, Klerkx, Govaerts, & Santos, 2013). Such feedback applications aid individuals’ learning by managing information flows and providing understanding of their learning position relative to others, and aid teachers, tutors, instructors, and faculty by making visible formerly invisible or hard-to-assemble characteristics of learning activity and interaction. Real-time feedback holds the promise of more timely intervention in support of learning and course modification in contrast to the more typical post hoc student course evaluation (e.g., Lockyer et al., 2013).

Analytics also presents the opportunity to use new and different kinds of data not included in course evaluations, such as the extent of student interaction within a class at various stages during the course, student cross-class connectivity (Gašević et al., 2013), emotional barometers associated with learning (e.g., in mining for positive or negative affect), library or Internet resource views (and presumed use) during the term (e.g., in page views, time spent on page, or reading resource downloads), and more.

More sophisticated analytic discoveries and interventions provide means of understanding complex learner behaviors, such as reasons and motivations for student lack of faithful appropriation of educational practices (e.g., in “gaming the system” or making careless errors; Baker et al., 2008; Hershkovitz et al., 2013). Of particular importance in these analytics, which encompass model building and EDM techniques, is that the models built can then be assessed across multiple instances. As Hershkovitz and colleagues note, Baker and Gowda (2010, as cited in Hershkovitz et al., 2013) were able to capture and compare behaviors across an entire year, at three schools, with a million data points.

With such large data sets, and the desire to assess multiple kinds of interactions, visualizations become not just appealing but necessary. Real-time interventions cannot wait for long-term analysis, and neither can complex analyses be easily offered to students or teachers for response if the results cannot be conveyed in accessible forms. As several of the articles address, visualization of data is a major challenge, encompassing the underlying data collection, definition of metrics, and analysis processes but also data presentation that enlightens without obfuscating and presents honest and usable information. The newness of these procedures also calls for education in visual literacy for reading, critiquing, understanding, and making contextually based interpretations of visualizations (de Laat & Schreurs, 2013; Lockyer et al., 2013; Slade & Prisloo, 2013; Thompson et al., 2013).

Learning analytics is also driven by changes in social practices, notably in the rise of participatory culture and the “always-on” lifestyle, which has led to many changes, and many expectations of change, in how teaching, learning, and the taking of courses can happen. Examples include educational perspectives of CSCL, self-directed learning, and transformative learning; online courses and degree programs; blended learning and e-learning; widespread adoption of learning management systems; online information resources from online news to open access journals; and crowdsourced and participatory information practices, from Wikipedia to Facebook to the emerging trend of MOOCs.

The massive potential in what it is possible to do; where, when, and with whom; because of technology, big data, analytics, visualizations, and so on also drives the need for consideration of the relationship to changes to our social practices. The technical and social are mutually shaping, demonstrating a reciprocal coevolution of form and use that calls for a sociotechnical analysis of the impact of new analytic objects on learning practice (Andrews & Haythornthwaite, 2007; Haythornthwaite & Andrews, 2011). As Thompson et al. (2013) articulate, “every designed object in the material world can have effects on human perceptions and action” (p. 1402). Their detailed approach to the impact of artifacts, such as the use of pens and whiteboards in a study group and the implementation of icons to identify experts in a crowdsourced application, highlights how technical and social design actions are implicated in network outcomes, that is, in the formation of roles and relations among actors in relation to their tools and tool uses. de Laat and Schreurs (2013) approach sociotechnical outcomes from another level, using learning analytics techniques to reveal network patterns among teachers engaged in solving common problems but spread across various schools and their contexts. These authors stress how the organizational contexts need to be revealed and considered as part of the understanding of learning and the interpretation of results from learning analytic technologies.

With similar consideration of social outcomes from technological change, Slade and Prisloo (2013) ask us to get ahead of the sociotechnical changes and to take charge through early consideration and policy formation regarding appropriate data collection and data use. Their article raises issues associated with the practice of harvesting and managing data, including informed consent, data security, and data persistence; issues of interpretation, such as extrapolating to the whole of a student’s learning profile from the capture of data in a narrow sphere of interaction; and the potential for structuring of interpretations based on collected and/or collectable data. Their article shows how the field of learning analytics has the opportunity to engage with issues of data use and ethical practice and potentially to lead the way in addressing such considerations for other human-centered “big data” initiatives.

With the articles brought together here, this issue not only shows current developments in an emerging domain; it also shows how the ideas pursued by learning analytics research can help to design and facilitate learning in a complex connected world, analyzing the traces of social behavior generated in massive, connected systems to raise awareness about learning and social engagement.

Footnotes

Declaration of Conflicting Interests

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

Author Biographies

Caroline Haythornthwaite is Director and Professor, School of Library, Archival and Information Studies (The iSchool@UBC) at The University of British Columbia. She joined UBC in 2010 after 14 years in the Graduate School of Library and Information Science at the University of Illinois at Urbana-Champaign. In 2009-10, she was Leverhulme Trust Visiting Professor at the Institute of Education, University of London presenting and writing on learning networks; and in 2009 was a visiting researcher at the Brazilian Institute for Information in Science and Technology, Rio de Janeiro, Brazil. She has an international reputation in research on information and knowledge sharing through social networks, and the impact of computer media and the Internet on work, learning, and social interaction. She is also a founding member of the Society for Learning Analytics Research (SoLAR), an organization focused on bringing big data applications to learning and academic achievement. Major publications include The SAGE Handbook of E-learning Research (2007, with Richard Andrews), and E-learning Theory and Practice (2011, with Richard Andrews).

Maarten de Laat is full Professor at LOOK, a research centre on teacher professional development, at the Open Universiteit of the Netherlands. He is director of the Social and Networked Learning research program, which concentrates on exploring social learning strategies and networked learning relationships that facilitate professional development in the workplace. His research is focused on informal learning in the workplace, lifelong learning, professional development and knowledge creation through (online) social networks and communities and the impact technology, learning analytics and social design has on the way these networks and communities work, learn and create value. He is co-chair of the international Networked Learning Conference as well as co-chair of the minitrack on Learning Analytics & Networked Learning at the HICSS conference and a member of the steering committee of SoLAR (Society for Learning Analytics Research).

Shane Dawson is the Deputy Director of the Learning and Teaching Unit, and Associate Professor of Technology Enhanced Learning at the University of South Australia. His research activities focus on learning analytics and social networks to inform educational theory and practice. Shane has also been involved in developing pedagogical models for enhancing creative capacity in undergraduate students. He is a co-founder and executive member of the Society for Learning Analytics research.

References

Allen

I. E.

Seaman

(2011). Going the distance: Online education in the United States, 2011. Babson Park, MA: Babson Survey Research Group.

Andrews

Haythornthwaite

(2007). Introduction to e-learning research. In Andrews

Haythornthwaite

(Eds.), Handbook of e-learning research (pp. 1-52). London, UK: Sage. Retrieved from http:/hdl.handle.net/2142/8974

Baker

R. S. J. d.

Walonoski

Heffernan

Roll

Corbett

Koedinger

(2008). Why students engage in “gaming the system” behavior in interactive learning environments. Journal of Interactive Learning Research, 19(2), 185.

Buckingham Shum

Ferguson

(2012). Social learning analytics. Journal of Educational Technology and Society, 15(3), 3-26.

Buckingham Shum

Gašević

Ferguson

(2012). Proceedings of the 2nd international conference on learning analytics and knowledge. New York, NY: ACM.

Campbell

J. P.

DeBlois

P. B.

Oblinger

D. G.

(2007). Academic analytics: A new tool for a new era. EDUCAUSE Review, 42(4), 42-57.

Conole

Gašević

(2011). Proceedings of the 1st international conference on learning analytics and knowledge. New York, NY: ACM.

Daly

A. J.

(Ed.). (2010). Social network theory and educational change. Cambridge, MA: Harvard Education Press.

Dawson

Bakharia

Heathcote

(2010, May). SNAPP: Realising the affordances of real-time SNA within networked learning environments. Paper presented at the Networked Learning-Seventh International Conference, Aalborg, Denmark.

10.

de Laat

Schreurs

(2013). Visualizing informal professional development networks: Building a case for learning analytics in the workplace. American Behavioral Scientist.

11.

Dirckinck-Holmfeld

Hodgson

McConnell

(Eds.). (2012). Exploring the theory, pedagogy and practice of networked learning. New York, NY: Springer-Verlag.

12.

Ford

(2008). Web-based learning through educational informatics: Information science meets educational computing. Hershey, NY: Information Science.

13.

Gašević

Zouaq

Jenzen

(2013). Choose your classmates, your GPA is at stake! The association of cross-class social ties and academic performance. American Behavioral Scientist.

14.

Goldstein

P. J.

Katz

R. N.

(2005). Academic analytics: The uses of management information and technology in higher education. Retrieved from http://www.educause.edu/ir/library/pdf/ers0508/rs/ers0508w.pdf

15.

Haythornthwaite

(2011). Learning networks, crowds and communities. In Proceedings of the 1st learning analytics and knowledge conference (pp. 18-22). New York, NY: ACM.

16.

Haythornthwaite

(in press). Learning networks. In Alhajj

Rokne

(Eds.) Encyclopedia of social network analysis and mining. New York, NY: Springer Science+Business Media.

17.

Haythornthwaite

Andrews

(2011). E-learning theory and practice. London, UK: Sage.

18.

Haythornthwaite

De Laat

(2011). Social network informed design for learning with educational technology. In Olofsson

A. D.

Lindberg

J. O.

(Eds.), Informed design of educational technologies in higher education: Enhanced learning and teaching (pp. 352-374). Hershey, PA: IGI Global.

19.

Hershkovitz

Baker

R. S. J. d.

Gobert

Wixon

Sao Pedro

(2013). Discovery with models: A case study on carelessness in computer-based science inquiry. American Behavioral Scientist.

20.

Hiltz

S. R.

Turoff

(2005). Education goes digital: The evolution of online learning and the revolution in higher education. Communications of the ACM, 48(10), 59-64.

21.

Koschmann

(Ed.). (1996). CSCL: Theory and practice of an emerging paradigm. Mahwah, NJ: Lawrence Erlbaum.

22.

Levy

Ford

Foster

Madden

Miller

Nunes

M. B.

Webber

(2003). Educational informatics: An emerging research agenda. Journal of Information Science, 29(4), 298-310.

23.

Lockyer

Heathcote

Dawson

(2013). Analytics to inform learning contexts. American Behavioral Scientist.

24.

Long

P. D.

Siemens

(2011). Penetrating the fog: Analytics in learning and education, EDUCAUSE Review, 46(5), 30-32, 34, 36, 38, 40. Retrieved from http://www.educause.edu/ero/article/penetrating-fog-analytics-learning-and-education

25.

Miyake

(2007). Computer supported collaborative learning. In Andrews

Haythornthwaite

(Eds.), Handbook of e-learning research (pp. 263-280). London, UK: Sage.

26.

Romero

Ventura

(2007). Educational data mining: A survey from 1995 to 2005. Expert Systems with Applications, 33(1), 135-146.

27.

Romero

Ventura

(2010). Educational data mining: A review of the state of the art. IEEE Transactions on: Systems, Man, and Cybernetics, Part C: Applications and Review, 40(6), 601-618.

28.

Siemens

(2011). About: Learning analytics and knowledge. In 1st International Conference on Learning Analytics and Knowledge, 2011. Retrieved from https://tekri.athabascau.ca/analytics/about

29.

Siemens

(2013). Learning analytics: The emergence of a discipline. American Behavioral Scientist.

30.

Siemens

Gašević

(2012). Special issue on learning and knowledge analytics [Special issue]. Journal of Educational Technology and Society, 15(3). Retrieved from http://www.ifets.info/journals/15_3/ets_15_3.pdf

31.

Siemens

Gašević

Haythornthwaite

Dawson

Buckingham Shum

Ferguson

Baker

R. S. J. d.

(2011). Open learning analytics: An integrated and modularized platform. Proposal to design, implement and evaluate an open platform to integrate heterogeneous learning analytics techniques. Retrieved from http://solaresearch.org/OpenLearningAnalytics.pdf

32.

Slade

Prinsloo

(2013). Learning analytics: Ethical issues and dilemmas. American Behavioral Scientist.

33.

Stahl

Koschmann

Suthers

(2006). Computer-supported collaborative learning: An historical perspective. In Sawyer

R. K.

(Ed.), Cambridge handbook of the learning sciences (pp. 409-426). Cambridge, UK: Cambridge University Press.

34.

Steeples

Jones

(Eds.). (2002). Networked learning: Perspectives and issues. London, UK: Springer.

35.

Suthers

Verbert

Duval

Ochoa

(2013) (Eds.) Proceedings of the Third International Conference on Learning Analytics and Knowledge. Retrieved from http://dl.acm.org/citation.cfm?id=2460296

36.

Swan

(2012). A special issue on learning analytics [Special issue]. Journal of Asynchronous Learning Networks, 16(3).

37.

Thompson

Ashe

Carvalho

Goodyear

Kelly

Parisio

(2013). Processing and visualizing data in complex learning environments. American Behavioral Scientist.

38.

Verbert

Duval

Klerkx

Govaerts

Santos

J. L.

(2013). Learning analytics dashboard applications. American Behavioral Scientist.

Introduction to the Special Issue on Learning Analytics

Abstract

Keywords

Footnotes

Further Reading

Declaration of Conflicting Interests

Funding

Author Biographies

References