Lee, Alwyn Vwen Yen

Idea development is an important process within a knowledge-building discourse and it is crucial to understand the dynamics of idea development throughout the discourse, such as the growth, flourishing or fading of ideas. This study proposes a framework called Idea Pipeline that explores and tracks the dynamics of idea development within a knowledge-building discourse. This pipeline consists of three phases: discovery, identification and analysis, and ‘rise above’ of ideas. Each phase of the pipeline will be illustrated using findings from a comparison study of two online knowledge building discourses. During the discovery phase, a text miner is used to identify groups of related keywords from the discourse; this is represented as keyword graphs with weighted frequencies to show the diversity of ideas that were embedded within the knowledge-building discourse. In the idea identification and analysis phase, network analysis was conducted to help label key ideas that were promising to the discourse community; this would provide the community with information to decide which ideas to pursue so that advancement of communal knowledge could be achieved leading to the ‘rise above’ phase. This Idea Pipeline framework can be an additional method for the temporal analysis of a computer-supported collaborative learning discourse over a longer duration of weeks or even months.

Cultivating students' data science knowledge and skills is pressing and challenging, given its interdisciplinary nature, students' limited prior knowledge, and teachers' insufficient training. In data science learning, students may experience various academic emotions. Understanding what emotions students experience, how these emotions are associated with their perceived learning, and under what conditions they experience intensive emotions is critical to informing the design of data science programs and better supporting students. This study collected 839 emotion survey responses from 67 secondary school students in two cycles of a two-day out-of-school data science program. The program engaged students in collaborative inquiries on authentic problems through data science practices with the support of teachers, researchers and facilitators. We found that frustration, interest, surprise and happiness positively predicted students' perceived learning, whereas anxiety negatively predicted perceived learning. Students experienced peaks of positive emotions after an expert's enthusiastic introduction talk to data science in the first cycle and after one-to-one face-to-face consultations with data science experts in the second cycle. However, sharing their progress and challenges with the data science expert in the first cycle and preparing for presentations in both cycles made them experience intense negative emotions such as anxiety, frustration, and confusion. These findings provide implications for designing data science programs to elicit students' positive learning experiences and reduce intensive negative emotions.

Although artificial Intelligence (AI) is prevalent and impacts facets of daily life, there is limited research on responsible and humanistic design, implementation, and evaluation of AI, especially in the field of education. Afterall, learning is inherently a social endeavor involving human interactions, rendering the need for AI designs to be approached from a humanistic perspective, or human-centered AI (HAI). This study focuses on the use of essays as a principal means for assessing learning outcomes, through students’ writing in subjects that require arguments and justifications, such as ethics and moral reasoning. We considered AI with a human and student-centric design for formative assessment, using an automated essay scoring (AES) and feedback system to address issues of running an online course with large enrolment and to provide efficient feedback to students with substantial time savings for the instructor. The development of the AES system occurred over four phases as part of an iterative design cycle. A mixed-method approach was used, allowing instructors to qualitatively code subsets of data for training a machine learning model based on the Random Forest algorithm. This model was subsequently used to automatically score more essays at scale. Findings show substantial agreement on inter-rater reliability before model training was conducted with acceptable training accuracy. The AES system’s performance was slightly less accurate than human raters but is improvable over multiple iterations of the iterative design cycle. This system has allowed instructors to provide formative feedback, which was not possible in previous runs of the course.

The theory and practice of knowledge building is one of the most well-known and influential educational approaches seeking to foster a culture of creativity, collaboration, and innovation in classrooms. To date, knowledge building research has focused on the sociocognitive and technological dynamics required to sustain knowledge building but has not focused specifically on the unique infrastructures that enable them. To contribute new ideas that can advance our understanding of what and how infrastructures enable knowledge building, this workshop will explore and synthesize ongoing research that includes a variety of examples that deal with and conceptualize knowledge building infrastructures. The workshop is organized into four sections, with both pre- and post-activities, and have three types of participants: invited speakers; key contributors; and active participants. Ultimately, the goal is to find ways to widen participation in knowledge building endeavors within existing or new implementations across the world.

This paper presents a study of temporal analytics and discourse analysis of an online discussion, through investigation of a group of 13 in-service teachers and 2 instructors. A discussion forum consisting of 281 posts on an online collaborative learning environment was investigated. A text-mining tool was used to discover keywords from the discourse, and through social network analysis based on these keywords, a significant presence of relevant and promising ideas within discourse was revealed. However, uncovering the key ideas alone is insufficient to clearly explain students’ level of understanding regarding the discussed topics. A more thorough analysis was thus performed by using temporal analytics with step-wise discourse analysis to trace the ideas and determine their impact on communal discourse. The results indicated that most ideas within the discourse could be traced to the origin of a set of improvable ideas, which impacted and also increased the community’s level of interest in sharing and discussing ideas through discourse.

Grasping students' emotions, especially those relating to learning, in a collaborative setting is no easy feat for teachers. The quality of collaboration comprises both visible behavior and emotion and the less visible emotional traits relating to engagement and motivation. Teachers often rely on their experience and intuition when it comes to these invisible traits. In this study, we collected multimodal data from a collaborative knowledge building classroom to analyze when and how students' emotions transpire during the working and improvement of ideas. Data included textual data, self-reports from surveys, interviews, and physiological data from face-to-face and online knowledge building discourse of 17 students in a 2.5-hour Social Studies lesson. We found shifts in epistemic emotions during idea improvement activities, and the students explained these shifts in understanding the discussion and engaging in idea-centric processes. We discuss findings for ongoing work to develop multimodal analytics for knowledge building practice.

The use of Artificial Intelligence (AI) in education is no longer science fiction but becoming a reality in these unprecedented times of dynamic changes. This field encompasses a wide range of techniques, algorithms, and solutions that may resolve current predicaments and problems in today’s classroom. This paper discusses how AI that is supporting the existing world can be extended into the fields of education and addresses the existing challenges of using AI within classrooms across Singapore.

The understanding of online classroom talk is a challenge even with current technological advancements. To determine the quality of ideas in classroom talk for individual and groups of students, a new approach such as precision education will be needed to integrate learning analytics and machine learning techniques to improve the quality of teaching and cater interventive practices for individuals based on best available evidence. This paper presents a study of 20 secondary school students engaged in asynchronous online discourse over a period of two weeks. The online discourse was recorded and classroom talk was coded before undergoing social network analysis and k-means clustering to identify three types of ideas (promising, potential, and trivial). The quality and distribution of ideas were then mapped to the different kinds of talk that were coded from the online discourse. Idea Progress Reports were designed and trialed to present collective and individual student’s idea trajectories during discourse. Findings show that the majority of ideas in exploratory talk are promising to the students, while ideas in cumulative and disputational talks are less promising or trivial. Feedback on the design of the Idea Progress Reports was collected with suggestions for it to be more informative and insightful for individual student. Overall, this research has shown that classroom talk can be associated with the quality of ideas using a quantitative approach and teachers can be adequately informed about collective and individual ideas in classroom talks to provide timely interventions.

Educational research may have established intricate connections between student achievements and emotions, but there remains a need to conduct more research on the crucial role of students’ epistemic emotions during learning. The emergence of global knowledge societies has nudged researchers to delve deeper into the understanding of students’ epistemic emotions within evolving learning environments, such as knowledge building environments that encourage complex learning and knowledge creation. This study addresses this gap via a naturalistic study of students' epistemic emotions in a student Knowledge Building Design Studio (sKBDS). We aim to illuminate the intersections between epistemic emotions and knowledge building activities, with findings to inform the design of more rigorous studies and designs to advance knowledge building practices. An Epistemic Emotion Survey (EES) was adapted for gathering students’ epistemic emotions and to align with knowledge building activities in the sKBDS. A total of 1,022 sets of epistemic emotion data from 73 primary and secondary school students were collected from two runs of the sKBDS, compiled into a single repository for descriptive analysis. Findings show that students experienced heightened curiosity, interest, excitement, and were generally happy to participate in activities at the sKBDS, while demonstrating relatively less anxiety, frustration, and confusion when undergoing knowledge building activities. Throughout the sKBDS, students also exhibited surprise at planned activities and what they have discovered and worked on. In addition, knowledge building activities also had varying effects on students' emotions, ranging from tiredness and hunger to occasional positive feelings. Overall, the findings from this study will be used for improving knowledge building practices and designs in future design studios, with implications for educators, students, and researchers.

Utilizing generative artificial intelligence, especially the more popularly used Generative Pre-trained Transformer (GPT) architecture, has made it possible to employ AI in ways that were previously not possible with conventional assessment and evaluation technologies for learning. As educational use cases and academic studies become increasingly prevalent, it is critical for education stakeholders to discuss design considerations and ideals that are key in supporting and augmenting learning via quality classroom discourse that sets the climate for student learning and thinking, and teachers’ transmission of expectations. In this paper, we seek to address how emergent technological advancements such as GPT, can be considered and utilized in designs that are consistent with the ideals of sustainable student discourse and knowledge creation. We showcase contemporary exemplars of possible designs and practices that are based on the pedagogy of knowledge building, with recent illustrations of how GPT may be utilized to sustain students’ knowledge building discourse. We also examine the potential effects and repercussions of technological utilization and misuse, along with insights into GPT’s role in supporting and enhancing knowledge building practices. We anticipate that the findings, through our exploration of designs and practices for knowledge creation, will be able to resonate with a broader audience and instigate meaningful change on issues of teaching and learning within smart learning environments.