Bibliographic record
Abstract
Considering the increasing use of Twitter for both formal and informal learning, the primary goal of this project is to design a Learning Analytics (LA) dashboard to support instructors’ evaluation of Twitter-based teaching. To achieve this goal, we conducted an online survey involving 54 higher education instructors who have used Twitter in their past teaching. The main purpose was to identify why instructors use Twitter and what types of analytics they would consider valuable. The results of the survey evidence that instructors use Twitter to help students engage with class material, promote discussion, and build learning communities. Instructors expressed interest in analytical tools to help them quantitatively and qualitatively interpret Twitter data. Coupled with an in-depth literature review in this area, we relied on the survey data to prototype a Learning Analytics dashboard (https://dashboard.socialmediadata.org/educhat). Our online dashboard uses a simple, easy-to-read interface in accordance with previous successful dashboard implementations. Graphical visualizations allow instructors to monitor discussion patterns, such as the frequency and times of posting. Visual content breakdowns by number of retweets, original posts, and topics in the form of hashtags and named entities reveal the constituents of students’ posts. The dashboard provides additional analysis in the form of sentiment and subjectivity ranking as a way to contextually aid qualitative assessment. To support instructors’ awareness of class participation, we incorporated two visualizations that highlight the most active users and individuals who are most frequently mentioned in others’ tweets. Instructors can use the dashboard to gauge the participation at the individual- or classroom-level, and further discover what topics and links students discuss and share on Twitter. Three instructors piloted the LA dashboard over a 4-month semester in the Fall of 2017. Following their use, we conducted evaluation interviews with these instructors. Instructor evaluations confirmed that the proposed design is aligned with their pedagogical needs; they favored an intuitive interface that combined summative metrics for the entire class and personalized assessment of individual students. Based on instructors’ feedback, our future work will iteratively refine the design by integrating additional interactive features to adjust time scales of the output, investigate source data, collect data from lists of Twitter users (as opposed to a single hashtag), and further integrate the dashboard with other LMS (Learning Management System) data.
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 | 0.004 | 0.022 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.030 | 0.010 |
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".