Вы находитесь на странице: 1из 3

Learning Analytics for the Social Media Age

Anatoliy Gruzd
Dalhousie University 6100 University Avenue, Suite 4010 Halifax, NS B3H 4R2 1-902-494-6119

Caroline Haythornthwaite
University of British Columbia 470 - 1961 East Mall Vancouver, BC Canada V6T 1Z1 1-604-827-4790

Drew Paulin
University of British Columbia 453C - 2053 Main Mall Vancouver, BC Canada V6T 1Z2 1-604-822-5344

gruzd@dal.ca Rafa Absar

University of British Columbia 470 - 1961 East Mall Vancouver, BC Canada V6T 1Z1 1-604-827-4322

c.haythorn@ubc.ca Michael Huggett

University of British Columbia 470 - 1961 East Mall Vancouver, BC Canada V6T 1Z1 1-604-822-2404


r.absar@ubc.ca ABSTRACT

by having access to social media, students can continue discussions started in one class and carry them over to another. Students also have a chance to view and build on conversations with others outside the classroom, such as practitioners and experts in the field or students who took the same class in a previous semester. Furthermore, social media can be used to create a community of learners, which persists beyond the current class, sustaining students as life-long learners. Recent research in this area suggests that whether one is submitting questions via Twitter, blogging about current events related to general themes of the class, or using Facebook to carry out class discussions, students class participation, engagement, and sometimes even performance, are likely to increase once social media are introduced into the mix [2], [13], [17]. However, how do educators and learners know that their particular use of social media is beneficial to their teaching or learning? This is a problem for many educators and researchers looking for validation that social media are truly aiding teaching and learning processes. The main objective of this research is to determine and evaluate measures that can help educators manage their use of social media for teaching and learning through the use of automated analysis of social media texts and networks. In a face-to-face class, it is relatively easy to see who is participating or not. It is also relatively easy in online classes to track progress and student participation with the help of reporting functionalities offered by modern Classroom Management Systems like Blackboard. However, when learners and educators are engaging with each other and with communities outside the classroom via social media, educators and researchers who are studying learning processes quickly find themselves inundated with datasets that dwarf more conventional survey- or interview-based datasets. Yet, data volume alone does not fully speak to the enormity of the task associated with analyzing online data. To exploit an online dataset fully, researchers often need to examine the same set of data in multiple passes, each time looking for different aspects of interaction and learning. Some of the many facets they can look at include common patterns of exchange, development of shared language and understanding, and the emergence of roles and positions that may be unique to online interactions. Multiple analyses such as these take a substantial amount of time to accomplish when managed by hand. Unfortunately, at this time there are no effective solutions that can help educators and

In just a short period of time, social media have altered many aspects of our daily lives, from how we form and maintain social relationships to how we discover, access and share information online. Now social media are also beginning to affect how we teach and learn in this increasingly interconnected and information-rich world. The panelists will discuss their ongoing work that seeks to understand the affordances and potential roles of social media in learning, as well as to determine and provide methods that can help researchers and educators evaluate the use of social media for teaching and learning based on automated analyses of social media texts and networks. The panel will focus on the first phase of this five-year research initiative Learning Analytics for the Social Media Age funded by the Social Science and Humanites Research Council of Canada (2013-2018).

Categories and Subject Descriptors

K.4.0 [Computer and Society]: General

Social Media, Learning Analytics, Learning Networks, Online Communities.

The use of social media has been growing in university classrooms, with some surveys reporting adoption rates as high as 80% among university classrooms in the United States [15]. Such use capitalizes on the wider social networks reachable via social media while simultaneously meeting the student population where it lives: i.e., online, in social networking sites and in the microforms of communication adopted in Twitter and texting. There are many potential benefits to using social media in association with education and classroom settings. For example,
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author. LAK '14, Mar 24-28 2014, Indianapolis, IN, USA ACM 978-1-4503-2664-3/14/03. http://dx.doi.org/10.1145/2567574.2576773

researchers to deal with such large datasets in the context of studying learning processes that are occurring in social media. The research conducted by the panelists contributes to the emerging field of learning analytics [12], [18]. It adds understanding, methods, and tools for learning analytics by developing and testing automated measures to study learning processes occurring in social media, based on the discovery and analysis of social structures among class participants. In particular, this research focuses on developing and evaluating new approaches for the discovery of learning networks generated from social media activities by class participants. Such networks signal engagement through interaction and discussion with fellow learners and instructors. Once discovered and properly evaluated, these networks offer efficient and effective ways to assess learning (especially collaborative learning) and teaching effectiveness: first by making the dataset more manageable, and then by identifying patterns in the data and creating effective modes of evaluation or intervention. The panel will report on the progress of the first year of this fiveyear research initiative with a particular focus on the lessons learned during the data collection phase. Specifically, the panelists will discuss two main data collection instruments that are currently being used by the research team: (1) the development and roll out of the online survey designed to discover different approaches to social media integration and evaluation for teaching among educators and (2) the automated collection of publicly available interaction data generated by MOOC participants to study social interactions among online learners. Below is a brief description of each data collection instrument. The presentation will conclude with a general discussion of what can be learned from data collected from the perspectives of researchers, instructors, students and administrators.

Since there is a general lack of knowledge regarding how and to what extent instructors integrate social media in their teaching, the first year of this initiative focuses on completing a comprehensive survey of different approaches to social media integration for teaching. To accomplish this goal, we are conducting an online survey among instructors around the globe to survey their teaching methods with social media. The aim is to understand how they align social media with the learning objectives of their classes and what kind of formal assessment criteria for the use of social media instructors use. The goal is to collect as many case studies as possible. The primary research questions that will be addressed by the survey are as follows: What specific social media are being used for teaching, and for what intended learning outcomes? What are the common assessment strategies of social media use for teaching and learning used by instructors? The panel will discuss the implementation and roll out of the survey.

worldwide. For example, in the United States, MOOCs are being offered by institutions such as MIT, Harvard, and Berkeley. In Canada, the leader in offering MOOCs is the Technology Enhanced Knowledge Research Institute (TEKRI) at Athabasca University. As a case, we are collecting and examining publicly available user-generated data from a number of MOOCs offered by TEKRI including courses on Connectivism and Connective Knowledge (CCK), Personal Learning Environments and Knowledge (PLEK), Learning Analytics (LAK). The user-generated data collected during this step will be used to discover and study emerging learning networks. Social Network Analysis (SNA) will be used as the primary method to analyze these networks. SNA has emerged as a leading method for studying online social interactions at an individual level and group level, as well as for studying learning networks [7], [8], [10], [11]. SNA seeks to represent datasets in the form of social networks; where nodes represent group members and edges (or ties) connect people by means of various types of relations. For example, individual Twitter users may be viewed as nodes, and the messages shared between them may be seen as edges. These network representations of social interactions provide researchers with an effective mechanism for studying collaborative processes in learning communities, such as knowledge construction, influence and support [1], [9], [16]. However, to study online communities using SNA, social network data about connections among members of a particular community needs to be collected. Until recently, capturing such information has been resource-intensive and primarily done via time-consuming and intrusive social network surveys administered to network participants. The advantage of studying learning communities that use a social media platform is that most of their social interactions are recorded and can be used to study the groups underlying social structures automatically. Once a social network among group members is discovered, it can be used to understand how group dynamics (e.g., active and outlier participation) relate to learning, and how the formation of shared norms and other social processes in online communities relates to successful learning outcomes. One of the reasons automated discovery of social networks is currently an emerging area of research is that it tends to be unobtrusive, scalable and fast. Automated network data collection is also not encumbered with many of the difficulties related to traditional qualitative data collection: i.e., respondents may provide partial answers, exaggerate interactions, forget people, or perceive events differently from other network participants (see discussions by [14]). With these difficulties in mind, this initiative focuses on new ways of discovering online social networks automatically. In particular, the panelists will discuss some of the common automated approaches for social network discovery from social media data, such as Twitter, blogs, social bookmarking data and forums in the learning context (see, for example, [3], [4], [5], [6]).

This work is supported by a Social Sciences and Humanities Research Council (SSHRC) Insight grant, Learning Analytics for the Social Media Age, PI: Anatoliy Gruzd; co-PI: Caroline Haythornthwaite; collaborator: George Siemens.

In parallel to conducting the survey, we are also reviewing a number of case studies involving the implementation of social media in the context of higher education, specifically focusing on a number of Massive Open Online Courses (MOOCs). MOOC is an emerging format of online courses designed for a large number of participants that uses an open access, web-based platform and a set of social media tools to conduct a class. This new format of distance and distributed learning is rapidly gaining in popularity

[1] Cho, H., Gay, G., Davidson, B. and Ingraffea, A. 2007. Social Networks, Communication Styles, and Learning Performance in a CSCL Community. Computers and Education, 49, 2, 309-329.

[2] Ebner, M., Lienhardt, C., Rohs, M., and Meyer, I. 2010. Microblogs in Higher Education A chance to facilitate informal and process-oriented learning? Computers and Education, 55, 1, 92100. [3] Gruzd, A. 2009. Studying Collaborative Learning Using Name Networks. Journal of Education for Library and Information Science, 50, 4, 243-253. [4] Gruzd, A. 2011. Exploring Virtual Communities with the Internet Community Text Analyzer (ICTA). In Ben Kei Daniel (Ed.), Handbook of Research on Methods and Techniques for Studying Virtual Communities: Paradigms and Phenomena. IGI Global, 205-223. [5] Gruzd, A. and Sedo, D.R. 2012. #1b1t: Investigating Reading Practices at the Turn of the Twenty-first Century. Journal of Studies in Book Culture / Mmoires du Livre 3, 2. [6] Gruzd, A., Wellman, B., and Takhteyev, Y. 2011. Imagining Twitter as an Imagined Community. American Behavioral Scientist, 55, 10, 1294-1318. http://abs.sagepub.com/content/early/2011/07/23/000276421 1409378.abstract [7] Haythornthwaite, C. 1998. A Social Network Study of the Growth of Community among Distance Learners. Information Research, 4, 1, 4-1. [8] Haythornthwaite, C. 1999. Collaborative Work Networks among Distributed Learners. Proceedings of the 32nd Hawaii International Conference on System Sciences. Los Alamitos, CA: IEEE Computer Society. [9] Haythornthwaite, C. 2001. Exploring Multiplexity: Social Network Structures in a Computer-Supported Distance Learning Class. The Information Society, 17, 3, 211-226. [10] Haythornthwaite, C. (forthcoming). Learning Networks. Encyclopedia of Social Networks and Data Mining. Springer. [11] Haythornthwaite, C. and de Laat, M. 2011. Social Network Informed Design for Learning with Educational Technology.

In A.D. Olofsson and J. O. Lindberg, (Eds.) Informed Design of Educational Technologies in Higher Education: Enhanced Learning and Teaching. IGI Global, 352-374. [12] Haythornthwaite, C., de Laat, M. and Dawson, S. (Eds.) 2013. Learning Analytics. American Behavioral Scientist, whole issue. [13] Junco, R., Elavsky, C. M., and Heiberger, G. 2012. Putting Twitter to the Test: Assessing Outcomes for Student Collaboration, Engagement and Success. British Journal of Educational Technology. [14] Lange, D. D., Agneessens, F. and Waege, H. 2004. Asking Social Network Questions: A Quality Assessment of Different Measures. MetodolokiZvezki, 1, 2, 351-378. [15] Moran, M., Seaman, J., and Tinti-Kane, H. 2010. Teaching, Learning and Sharing: How Todays Higher Education Faculty Use Social Media. Pearson Learning Solutions. Retrieved May 10, 2011 from http://www.pearsonlearningsolutions.com/educators/pearsonsocial-media-survey-2011-color.pdf [16] Reyes, P. and Tchounikine, P. 2005. Mining Learning Groups Activities in Forum-Type Tools. Proceedings of the 2005 Conference on Computer Support for Collaborative Learning: Learning 2005: the Next 10 Years! International Society of the Learning Sciences, 509-513. [17] Schroeder, A., Minocha, S., and Schneider, C. 2010.The Strengths, Weaknesses, Opportunities and Threats of Using Social Software in Higher and Further Education Teaching and Learning. Journal of Computer Assisted Learning, 26, 3, 159174. [18] Siemens, G. 2010. What are Learning Analytics? Retrieved October 6, 2012 from http://www.elearnspace.org/blog/2010/08/25/what-arelearning-analytics/