Proceedings of the 1st International Conference on Learning Analytics and Knowledge
Bibliographic record
Abstract
We welcome you to the 2012 Learning Analytics and Knowledge conference, being held in the beautiful city of Vancouver, Canada. Before you explore the city and the University of British Columbia, please join us in acknowledging that Vancouver and UBC are located on the traditional, ancestral, and unceded territory of the Canadian First Nations Musqueam people, and to thank the Musqueam people for their hospitality. Vancouver is a city rich in cultures, including people of First Nations, Asian, British, and many other origins and areas from the original Gastown to Granville Island, and from the high rise towers of downtown to the beaches of Kitsilano. Residents are an active group, with trails facilitating bicycling in the city, mountains close at hand for skiing and hiking, and the sea for boating of all kinds. At very close hand to the conference is the famed Stanley Park with its 22 kilometer (13.7 miles) seawall for walking, jogging or bicycling. For the more hardy, at little further off is Grouse Grind where you can test yourself against the mountains with 2,830 steps, and an 853 meter (2,800 feet) vertical ascent to a magnificent view of the Vancouver area. Or, stroll the streets of Vancouver, visit the UBC campus and perhaps you'll see some familiar spaces and places from the many films made here We hope you'll be able to make the most of your visit to Vancouver and of your time at the LAK12 conference. At time of writing, a number of weeks before the conference, we are sold out! This signals to us the importance of this emerging area of learning analytics and of the conference. We are pleased to be involved and helping to promote this new and exciting area of research and practice. We also want to thank those involved in helping make the conference such a success. Establishing a new research conference with proceedings published in the ACM Digital Library demands an extremely competent Program Committee, and we are indebted to our colleagues for their commitment to LAK12. A rigorous review process ensured that each paper was evaluated by at least three program committee members, and in many cases by four. Each paper was discussed in the online forum, with the authors having the option to reply to comments as distilled by the Program Chairs before a final decision was reached. Over our three days, we'll hear from three keynote speakers and an international set of authors in the field of learning analytics. The adjudicated papers include 14 Full Papers accepted from 36 submissions (39%). Of these a further six were accepted in briefer form as Short Papers and two as Design Briefings. We also invited authors to submit Short Papers that share preliminary conceptual, technical and empirical contributions: of the 26 submissions, 15 were accepted (58%). The program also includes three panels aimed to provide more discursive forums. As well as papers, the program includes two full-day and two half-day workshops taking place on April 29th on the UBC campus. In one year we have doubled the conference size. At LAK11, held in Banff in 2011, there were 17 adjudicated papers in a single track. LAK12 more than doubles in size to 40 in two parallel tracks, plus the pre-conference workshops. We have every confidence that this year's LAK will be a great success and will grow in size and reputation as at the end of LAK12 we will pass the torch on to the LAK13 organizers.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.013 | 0.011 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.137 | 0.070 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".