Guest Editorial-Learning and Knowledge Analytics
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The early stages of the internet and world wide web drew attention to the communication and connective capacities of global networks. The ability to collaborate and interact with colleagues from around the world provided academics with models of teaching and learning. Today, online education is a fast growing segment of the education sector. A side effect, to date not well explored, of digital learning is the collection of data and analytics in order to understand and inform teaching and learning. As learners engage in online or mobile learning, data trails are created. These data trails indicate social networks, learning dispositions, and how different learners come to understand core course concepts. Aggregate and large-scale data can also provide predictive value about the types of learning patterns and activity that might indicate risk of failure or drop out. The Society for Learning Analytics Research defines learning analytics as the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs (http://www.solaresearch.org/mission/about/). As numerous papers in this issue reference, data analytics has drawn the attention of academics and academic leaders. High expectations exist for learning analytics to provide insights into educational practices and ways to improve teaching, learning, and decision-making. The appropriateness of these expectations is the subject of researchers in the young but rapidly growing learning analytics field. Learning analytics currently sits at a crossroads between technical and social learning theory fields. On the one hand, the algorithms that form recommender systems, personalization models, and network analysis require deep technical expertise. The impact of these algorithms, however, is felt in the social system of learning. As a consequence, researchers in learning analytics have devoted significant attention to bridging these gaps and bringing these communities in contact with each other through conversations and conferences. The LAK12 conference in Vancouver, for example, included invited panels and presentations from the educational data mining community. The SoLAR steering committee also includes representation from the International Educational Data mining Society (http://www.educationaldatamining.org). This issue reflects the rapid maturation of learning analytics as a domain of research. The papers in this issue indicate LA as a field with potential for improving teaching and learning. Less clear, currently, is the long-term trajectory of LA as a discipline. LA borrows from numerous fields including computer science, sociology, learning sciences, machine learning, statistics, and big data. Coalescing as a field will require leadership, openness, collaboration, and a willingness for researchers to approach learning analytics as a holistic process that includes both technical and social domains. This issue includes ten articles: Buckingham Shum and Fergusson describe social learning analytics (SLA) as a subset of learning analytics. SLA is concerned with the process of learning, instead of heavily favoring summative assessment. SLA emphasizes that new skills and ideas are not solely individual achievements, but are developed, carried forward, and passed on through interaction and collaboration. As a consequence, analytics in social systems must account for connected and distributed interaction activity. Hung, Hsu, and Rice explore the role of data mining in K-12 online education program reviews, providing educators with institutional decision-making support, in addition to identifying the characteristics of successful and at-risk students. Greller and Drachsler propose a generic framework for learning analytics, intended to serve as a guide in setting up LA services within an educational institution. …
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it