The value of learning analytics to networked learning on a personal learning environment

Abstract

Abstract. Some might argue that the analytics tools at our disposal are currently mainly used for boring purposes, such as improving processes and making money. In this paper we will try to define learning analytics and their purpose for learning and education. We will ponder on the best possible fit of particular types of research methods and their analysis. Methodological concerns related to the analysis of Big Data collected on online networks as well as ethical and privacy concerns will also be highlighted and a case study of the use of learning analytics in a Massive Open Online Course explored. . As educational practice and the settings in which learning takes place have changed with the proliferation of the Internet and its available tools, careful thought about these tools and considerations of the processes and means with which data is being collected and analyzed is once again required [4]. Lazer et al. [4] stress that social scientists have lagged behind researchers in other fields, for instance in fields such as biology and physics, and that it is unavoidable for analytics to become part of social science research. Moreover, they emphasise the urgency for a data-driven computational social science to develop "based in an open academic environment", rather than in the domain of private companies such as Google and Yahoo, and government agencies who are currently the main players in the analytics field. They answer the question: "What value might a computational social science -based in an open academic environment -offer society, by enhancing

A Multi-dimensional Investigation of Self-regulated Learning in a Blended Classroom Context: A Case Study on eLDa MOOC

“…This study proposes a multidimensional learning evaluation from an online blended seminar classroom different mode of studying. Learning analytics has shown the various course units that need improvement [2]. This however helps to inform a better course delivery.…”

“…The data is further analysis for academics and educational online blended system using a statistical package for the social sciences (SPPS) tool. Learning analytics has shown the various course units that need improvement [2], this however helps to inform a better course delivery. The use of learning technology as a catalyst towards enhancing the learning process for learners in educational contexts thus involves an investigation of the learners themselves, the content to which they have engage with in this context, the learning platform environment itself and the components that comprised in this environment.…”

Improving academic outcomes: does participating in online discussion forums payoff?

“…The analysis of data from different elements of online learning has identified that there are patterns of engagement that are reflected in academic outcomes. These include patterns that identify perceived sense of community (Dawson, 2008), participation and social connections (Fournier et al, 2011) disconnected students and student-to-student communication (Macfadyen and Dawson, 2010). Learning analytics data and methods can be employed to identify the potential impact of the socialising efforts of active participation in the online discussion forum on the student's final mark.…”

“…In the context of a social learning pedagogy, learning analytics have been used to identify perceived sense of community (Dawson, 2008), participation and social connections (Fournier et al, 2011) and identify disconnected students and patterns of student-to-student communication (Macfadyen and Dawson, 2010). The data gathered can guide the use of limited resources allowing faculty to customise instruction and improve teaching and learning environments (Ferguson, 2012, Johnson et al, 2012.…”

Understanding Learning and Learning Design in MOOCs: A Measurement-Based Interpretation

“…Log stream data does not provide a complete picture of all learner behaviours; for example, it e xcl udes those forms of engagement with learning that occurs off-line or may not leave a digital trace, such as i n some forms of emotional engagement (Fournier, Kop, & Sitlia, 2011;Veletsianos, Colleer, & Schne i der, 2015). The data are rarely designed for research purposes, and have been found variously to b e too granular or not granular enough for some purposes (Kizilcec, Piech, & Schneider, 2013), or too patchy or incomplete, or too inaccurate, confounded, or corrupted with data unrelated to learning (Dringus, 2012;Greller & Draschler, 2012;Siemens & Long, 2011).…”