Chapter 14 : Provision of Data-Driven Student Feedback in LA & EDM

1 Faculty of Engineering and IT, The University of Sydney, Australia 2 Teaching Innovation Unit, University of South Australia, Australia 3 Connected Intelligence Centre, University of Technology Sydney, Australia data to increase insight about learning environments and improve the overall quality of instructional design, tutoring, student engagement, student success, emotional well-being, and so on. This chapter focuses on the potential of combining the knowledge from these combination with the ubiquitous presence of data about learners offers fertile ground to

Over the past two decades, education practice has cludes shifts in educational policy, the emergence of technology-rich learning spaces, advances in learning theory, and the implementation of quality assurance and assessment, to name but a few.These changes have all shifts in the education space, the key role of feedback in promoting student learning has remained essential to what is viewed as effective teaching.Moreover, with real-time feedback and actionable insights to both teachers and learners is becoming increasingly acute.As education embraces digital technologies, there is a widespread assumption that the incorporation of such technologies will further aid and promote student learning and address sociocultural and economic technologies can be adopted to enhance accessibility adaptive learning pathways.learning processes in order to develop more effective teaching practices (Baker & Siemens, 2014).The analysis of data evolving from student interactions with various technologies to provide feedback on the learner's progression has been central to LA and learning.As such, the overall quality of the learning salience of the feedback a student receives.Moreover, the provision of feedback is closely related to other approaches (Boud, 2000), the learning design (Lockyer, student self-regulation (Winne, 2014;Winne & Baker, 2013).Although the majority of the discussion in this chapter can be applied across all educational domains, the review focuses predominantly on post-secondary education and professional development.
in a framing of assessment and student achievement the primary role of feedback is to help the student the completion of an assessment item.Ironically, assessment scores and student achievement data have also become tools for driving political priorities and agendas, and are also used as indicators in quality assurance requirements.Assessment in essence is a two-edged sword used to foster learning as well as a tool for measuring quality assurance and establishing competitive rankings (Wiliam, Lee, Harrison, & Black, 2004).While acknowledging the importance of ason the value of feedback often associated with formative assessment or simply as a component of student completion of set learning tasks.Thus, this chapter facilitate the transformation of the essence of assessment practices by focusing on feedback mechanisms.With such a purpose, we highlight and discuss current approaches to the creation and delivery of data-enof research in learning analytics and educational data

Theoretical Models of Feedback
ses of its effects on learning have been undertaken (e.g., Evans, 2013;Hattie & Timperley, 2007;Kluger indicates that feedback is one of the most powerful majority of studies have concluded that the provision of feedback has positive impact on academic perforin certain cases, a negative impact has been noted.lack of relevance of the provided information, could have a negative effect on student performance.In this case, the authors distinguished between three levels of the locus of learner's attention in feedback: the task, the motivation, and the meta-task level.All three are equally important and can vary gradually in ing the provision of feedback such as its potential for negative impact, the connection with goal orientation, motivation, the presence in scaffolding mechanisms, timing, or different learner achievement levels.Shute in response to a learner's action should be non-eval-Early models relating feedback to learning largely aimed to identify the types of information provided to the student.Essentially, these studies sought to formation can play on student learning (Kulhavy & were driven by the differences in learning science desired state of the learner can be bridged (cf.historical to Mory (2004), contemporary models build upon a style of engaging with tasks in which students exercise a suite of powerful skills (Butler & Winne, 1995).These skills, setting goals, thinking about strategies, selecting the right strategies, and monitoring the effects of these strategies on the progress towards the goals are all associated with student achievement (Butler & Winne, their theoretical synthesis between feedback and self-regulated learning, Butler and Winne (1995, p. 248) embedded two feedback loops into their model.The cognitive system and refers to the capacity of individuals to monitor their internal knowledge and beliefs, goals, tactics, and strategies and change them as required by the learning scenario.The second loop occurs when the product resulting from a student engaging with a task is measured, prompting the creation of external feedback assessment score, or an instructor commenting upon the completion of a task.Hattie and Timperley (2007) have provided one of the achievement.The authors' conceptual analysis was the information provided by an agent regarding the performance or understanding of a student.The authors proposed a model of feedback articulated around the concept that any feedback should aim to reduce the discrepancy between a student's current understanding and their desired learning goal.As such, feedback can be framed around three questions: where am I going, how am I going, and where to next?Hattie and Timperley (2007) proposed that each of these questions should be applied to four different levels: learning task, learning process, self-regulation, and self.The learning task level refers the student if an answer is correct or incorrect.The learning process refers to general learning objec-

THE ROLE OF DATA-DRIVEN FEEDBACK IN LEARNING
tives, including various tasks at different times.The on the learning goals, choosing the right strategy, and monitoring the progress towards those goals.Finally, the self level refers to abstract personality traits that process and regulation levels are argued to be the most effective in terms of promoting deep learning and mastery of tasks.Feedback at the task-level is effective only as a supplement to the previous two levels; feedback at the self-level has been shown to be the least effective.These three questions and four levels of feedback provide the right setting to connect feedback with other aspects such as timing, positive vs. negative messages (also referred to as polarity), and the consequences of including feedback as part of an assessment instrument.These aspects have been shown to have a interdependent effect that can be In reviewing established feedback models, Boud and Molloy (2013) argued that they are at times based on unrealistic assumptions about the students and the educational setting.Commonly, due to resource constraints, the proposed feedback models or at least the mechanism for generating non-evaluative, supportive, practical or at least not sustainable in contemporary irregular and unidirectional state to an active dialogue between agents.improve aspects of learning can be traced to areas such as adaptive hypermedia sa, 2007), intelligent tutoring systems (ITSs) (Corbett, 2012), and academic analytics (Baepler & Murdoch, common interest in data-intensive approaches to the research of educational setting, with the purpose of advancing educational practices (Baker & Inventado, 2014).While these communities have many similarities, there are some acknowledged differences between methods for discovery, as opposed to LA's human-led and Inventado (2014) noted that the main differences methodologies, but in the focus, research questions, and eventual use of models.
back, the research approaches differ in relation to the direction and recipient of feedback.For instance, LA initiatives generally provide feedback aimed towards developing the student in the learning process (e.g., self-regulation, goal setting, motivation, strategies, on the provision of feedback to address changes in the learning environment (e.g., providing hints that modify a task, recommending heuristics that populate the environment with the relevant resources, et cetera).
The following section further unpacks the work in both of feedback to aid student learning.

DATA-SUPPORTED FEEDBACK
includes the forward-oriented efforts for building an understanding of how such models can be enhanced ing future systems.In other words, algorithms could design of new systems that provide better feedback.suggested a need to move beyond the provision of better algorithms and understand how task-level feedback is In other words, the feedback at the level of learning process, or information about self-regulation skills, can help frame feedback at the task level.
A large portion of the studies related to adaptive feedback have been developed through intelligent tutoring systems (ITSs; e.g., Abbas & Sawamura, 2009;Eagle & Barnes, 2013;Feng et al., 2009)

Approaches to Feedback in Learning Analytics
Within the research in LA, a focus on feedback is generally interpreted as the need to communicate a student's state of learning to various stakeholders, i.e., teachers, students, or administrators.Early LA research (e.g., LAK 2011 and 2012 conference proceedings) did not focus that needed to close the loop via scalable feedback processes (Clow, 2012;Lonn, Aguilar, & Teasley, 2013) conveyed through a multitude of disciplinary voices to humans with varying understandings of the agency with that, Wise ( 2014) urged the design of data-driven learning interventions with awareness of how they are and interpretation of data-supported feedback has been a distinct theme within LA feedback-related research.The LA community has searched for evidence and practices to ensure that the dialogue between the analytics and the stakeholders is taking place as imagined by the researchers.For instance, Corrin and de Barba ( 2015 Feedback aimed towards developing student self-reguapproach to formative feedback embraces the self and various aspects of the learning process to support the cent development includes the provision of feedback feedback were less bored and more consistently ontask than a comparative peer group receiving feedback only related to their performance.In essence, the authors demonstrate that the automated provision of feedback relating to a student's affective state can feedback about student emotions and their evolution throughout the course.In this instance, the authors used the provision of self-reported emotional states and course designs.However, these studies also demonstrate that any noted success appears to be largely dependent on the learners' competence to self-regulate using the feedback from such learning analytics applications.Less reliance on the assumed level of students' competence is found when learning design or technology affordances prompt learner be offered.essay grading, has been tackled by various initiatives as writing analytics, this area has a strong presence discourse analysis, and computational linguistics analytics offers feedback regarding the quality of aspects of writing as a domain skill, e.g., the quality of insight, genre, and so on (e.g., Crossley, Allen, Snow, McNamara, 2015;Whitelock, Twiner, Richardson, Field, offering formative feedback on learner's competency ment with both the content and process of learning.
ence, feedback, within the current research space of are transformed by algorithm-produced feedback.Furthermore, the relationship between the type of interventions that can be derived from data analysis and adequate forms of feedback remains inadequately area needs to be revisited with comprehensive data sets derived from technology mediation in learning learning scenarios, the increase in workload and limited instructor time are affecting the quality of feedback received by students.New emerging scenarios such high quality feedback to large student cohorts.LA and and propose new paradigms in which feedback is both scalable and effective.Although the initiatives in both communities have a strong connection with feedback, they differ in the areas of focal interest within which each discipline is devising its solutions.These foci are complementary, and often build upon each other.comprehensive view of the role that feedback plays in a generic learning scenario, the elements involved, and the ultimate goal of prompting changes in the stufrom adopting a more comprehensive framework for feedback that supports a more effective integration across disciplines as well as the combination of humans and technology.

CONCLUSION REFERENCES
) inquired into student perceptions of achievement goal orientations perceived dashboard feedback in the same way; and a few studies investigated ways of making generated research more meaningful by combining qualitative interviews or the work of human interpreters with the data-driven analyses or indicators of their activity cannot be connected proposed byHattie and Timperley (2007).However, dashboards usually contain task level information, as inferring information about the learning process or self-regulation skills is much more challenging.the provision of automated, scaled and real-time feedback to learners for self-monitoring and self-regulation byHattie and Timperley (2007).Such direction has been well-captured through a steady growth of LA task-level feedback is of less prominence than in human-agency involved in interpreting and acting upon feedback.LA tends to promote process-level instance, learning dashboards capture data sources, such as time spent, resources used, or social interprogress towards these goals (for further review see dashboards are shifting from the count of time or use within competence graphs (Kickmeier-Rust, Steiner, Heathcote, 2010), as a part of social learning analytics (e.g.,Ferguson & Buckingham Shum, 2012), remain a popular type of feedback on the social interaction in distributed social media, such as Twitter or Facehave also been offered to groups as representations of collective knowledge construction.
Proceedings of the Workshop on Visual Aspects of Learning Analytics Proceedings of the 2nd International Conference on Learning Analytics and Knowledge Proceedings of the 4th International Conference on Learning Analytics and Knowledge -Handbook of human-computer interaction Proceedings of the 5 th International Conference on Learning Analytics and Knowledge automatic essay scoring than just you!Proceedings of the 5 th International Conference on Learning Analytics and Knowledge (Eds.),Proceedings of the 7 th International Conference on Educational Data Mining itoring online student networking.British Journal of Educational Technology, 41 -& T. Ryberg (Eds.),Proceedings of the 7 th International Conference on Networked Learning Proceedings of the 1 st International Conference on Learning Analytics and Knowledge The internal structure of learning power.British Journal of Educational Studies, 63 Proceedings of the 6 th International Conference on Educational Data Mining Mavrikis, & B. M. McLaren (Eds.),Proceedings of the 7 th International Conference on Educational Data Mining