Polyfeed was developed based on stakeholder (e.g., students, educators, LA researchers) requirements and state of art feedback research such as feedback literacy, dialogic feedback, and learner-centred feedback. Morethan 1500 students and 300 teachers have been engaged in the desing process and the tool was developed using desing thinking approach.
PolyFeed Student won the Best Demo award at the 15th International Learning Analytics and Knowledge Conference. The demo "PolyFeed: A Student-Facing Feedback Analytics Tool to Facilitate Feedback Processes," showcased the features and functionalities of PolyFeed for students, along with findings from our pilot study.
PolyFeed Teacher won the Best Poster award at the 15th International Learning Analytics and Knowledge Conference. The poster "Developing a Feedback Analytics Tool with Educators to Support Dialogic Feedback," presents how we applied a design thinking approach to create PolyFeed for educators, supporting dialogic feedback.
PolyFeed student consists of a Chrome browser extension and a Dashboard.
Students can highlight and label feedback as strength, weakness, suggestion, confusion, or other
Students can make reflective notes or action plans.
Students can view patterns emerged from their interactions with feedback.
PolyFeed Teacher consists of a browser extension and a dashboard.
Teachers can evaluate their feedback for the alignment with learner-centred feedback elements.
Teachers can use the suggestions from PolyFeed evaluation and GenAI to improve the feedback
Teachers can view insights derived from students interactions with feedback at different class levels.
Authors: Flora Ji-Yoon Jin, Wei Dai, Bhagya Maheshi, Roberto Martinez-Maldonado, Dragan Gašević, Yi-Shan Tsai
Abstract: Feedback is essential in education, yet often studied within isolated educational sectors. This study investigates feedback practices across K-12 and higher education by surveying 254 educators to explore perceptions of effective feedback, student barriers, and methods for tracking feedback impact. Our findings reveal that higher education educators prioritise cognitive and structural feedback elements, emphasising actionable suggestions and timely delivery. In contrast, K-12 educators focus on social-affective aspects, such as feedback tone, to support a nurturing learning environment. Despite these sector-specific preferences, discrepancies exist between educators' beliefs and practices, highlighting a need for enhanced feedback literacy.
Authors: Hua Jin, Roberto Martinez-Maldonado, Tony Li, Philip Wing Keung Chan, Yi-Shan Tsai
Abstract: Feedback plays a crucial role in learning. Yet, higher education continues to face challenges regarding facilitating effective feedback processes. One of the challenges is the difficulty to track how students interact with feedback and the impact of feedback on learning outcomes. Learning analytics (LA) has opened up opportunities to enhance feedback practice with a wide array of data. However, most research seeks to deliver data-driven feedback rather than understanding how students make use of feedback and how educators can use learning analytics to support students in this process. As a first step to address this gap, our study investigated educators' views of challenges and elements of effective feedback processes in addition to their perceptions of data-driven feedback. The study found that feedback design (e.g., feedback purpose, content, and structure), educator-related factors (e.g., time constraints and resource limitations), and student-related factors (e.g., disposition, self-regulation, and sense-making) can have positive or negative impacts on the feedback process. It also highlights the need for the development of student feedback literacy. Based on the findings, we proposed ideas for an LA-based feedback tool that can be used to facilitate a dialogic feedback process and address challenges with feedback.
Authors: Flora Ji-Yoon Jin, Bhagya Maheshi, Roberto Martinez-Maldonado, Dragan Gašević, Yi-Shan Tsai
Abstract: Feedback is essential in learning. The emerging concept of feedback literacy underscores the skills students require for effective use of feedback. This highlights students' responsibilities in the feedback process. Yet, there is currently a lack of mechanisms to understand how students make sense of feedback and whether they act on it. This gap makes it hard to effectively support students in feedback literacy development and improve the quality of feedback. As a specific application of learning analytics, feedback analytics (analytics on learner engagement with feedback) can offer insights into students' learning engagement and progression, which can in turn be used to scaffold student feedback literacy. This study proposes a feedback analytics tool, designed with students, aimed at aiding students to synthesize feedback received from multiple sources, scaffold the sense-making process, and prompt deeper reflections or actions on feedback based on data about students' interactions with feedback. We held focus group discussions with 38 students to learn about their feedback experiences and identified tool features. Based on identified user requirements, a prototype was developed and validated with 16 students via individual interviews. Based on the findings, we envision a feedback analytics tool with the aim of scaffolding student feedback literacy
Authors: Bhagya Maheshi, Wei Dai, Roberto Martinez-Maldonado, Yi-Shan Tsai
Abstract:
Background: Feedback is central to formative assessments but
aligns with a one-way information transmission perspective
obstructing students' effective engagement with feedback.
Previous research has shown that a responsive, dialogic
feedback process that requires educators and students to
engage in ongoing conversations can encourage student active
engagement in feedback. However, it is challenging with larger
student cohorts. Learning Analytics (LA) provides promising
ways to facilitate timely feedback at scale by leveraging
large datasets generated during students' learning. However,
current LA design and implementation tend to treat feedback as
a one-way transmission rather than a two-way process.
Objectives:
This case study aims to improve LA design and practice to
align with dialogic feedback principles by exploring an
authentic dialogic feedback practice at scale.
Methods:
We explored a dialogic feedback practice of a course having
700 undergraduate students. The case study used quantitative
and qualitative analysis methods to investigate what students
expect from feedback, how educators respond to students'
feedback requests, and how students experience feedback.
Results and Conclusions:
The results emphasise the need to focus on cognitive,
relational and emotional aspects of the feedback process. In
aligning LA with dialogic feedback principles, we propose that
LA should promote the following objectives: reflection,
adaption, personalisation, emotional management, and
scaffolding feedback provision.
Authors: Bhagya Maheshi, Mikaela Elizabeth Milesi, Hiruni Palihena, Aaron Zheng, Roberto Martinez-Maldonado, Yi-Shan Tsai
Abstract: Feedback is an essential process of learning in higher education. Yet, capturing students' interactions with feedback is challenging, which makes it difficult to evaluate its impact. Learning Analytics (LA) is a potential solution to address this issue as it is capable of capturing and analysing learners' activities in a technology-enabled learning environment. LA often use dashboards to deliver insights derived from educational data, yet questions remain on how to most effectively communicate key insights to students. Data Storytelling (DS) is a promising technique to address this challenge by combining data, visuals and narrative to convey key insights. Co-design can facilitate the crafting of visualisations and data stories that best aligns with goals of the students. This study presents the preliminary findings from a design sprint conducted with students to co-design a prototype for a dashboard of an LA solution – PolyFeed – that captures and analyses students' interactions with feedback. In developing the dashboards, students used DS principles – Explanatory titles, Annotations, Highlighting important data points, and Decluttering – to improve the selected visualisations. The results show that the student groups perceived visualising strengths and weaknesses identified in feedback, action plans based on feedback, and trends in their performance as key aspects to include in FA dashboard. However, they primarily used two DS principles: explanatory titles and highlighting key data points to improve visualisations because the dataset was pre-dominantly qualitative. Therefore, the effective use of DS to support qualitative data should be further explored.
Workshop Link: https://ceur-ws.org/Vol-3667/
Chief Investigator
Senior Resercher
Senior Resercher
Senior Resercher
PhD Candidate
PhD Candidate
PhD Candidate
PhD Candidate
Project Manager
Software Developer
Collaborator
Collaborator
Collaborator
Collaborator
We also would like to remeber Dr. Shaveen Singh, Minhua Zhou, Aaron Zheng, Caleb Ooi, Andrew Pham, Winnie Chui, Max Verheof, Phakhanan Rataphaibul, and Assoc. Prof. Wenhua Lai who were part of the PolyFeed team and contributed in desinging, developing, and evaluating it.
For research collaboraitons and further information contact fit-polyfeed@monash.edu or Dr. Yi-Shan Tsai
PolyFeed is committed to protecting the privacy of its users. This Privacy Statement explains how we collect, use, and safeguard your information when you use PolyFeed Chrome extensions.
Users log in using their Monash University Google accounts, with authentication managed securely through Google's authentication services, including two-step verification. The single sign on capability will allow users to access the polyfeed extension as well as the polyfeed dashboard.
PolyFeed-student store users' interaction with moodle feedback they received. The highlights, notes, to-do lists, and responses from ChatGPT will be stored in a secure relational database. When a record is deleted by a user, it is marked as inactive in the database rather than being permanently removed.
PolyFeed-teacher stores user's feedback written in the extension. The learner-centricity analysis results, tips and ChatGPT improvements will be stored in a secure relational database.
The data collected using polyfeed and polyfeed-teacher is used to generate visualisations on the PolyFeed dashboards (separate web pages that can be accessed through the extension). Polyfeed-teacher dashboard offers insights about student interactions with feedback, showing common strengths, weaknesses and confusions across the entire student cohort and a particular teacher's students, and also shows student centricity analysis of the feedback they constructed using polyfeed teacher extension. PolyFeed-student dashboard offers insights about interactions with feedback, common strengths and weaknesses across units and assignments, and monitoring the progression of action plans based on received feedback
We collect logs of user activity to analyse behaviour and improve the functionality of the tool. This data helps us understand how users interact with PolyFeed, allowing us to enhance user experience and service quality.
We employ robust security measures to protect the data we handle. These include using HTTPS protocols on our website and securing all data transmissions to prevent unauthorised access, alteration, or destruction.
PolyFeed is dedicated to upholding the highest standards of data protection and ethical conduct. We regularly review our compliance policies and engage with legal and data protection experts to ensure that we meet all regulatory requirements and ethical standards in our operations.
We may update this Privacy Statement periodically to reflect changes in our practices. We will notify users of any significant changes and indicate the date of the latest revision.
If you have any questions or concerns about this Privacy Statement or our data practices, please contact us at fit-polyfeed@monash.edu
This Privacy Statement is effective as of 19-08-2024