Gerald Ajam

Library / Glossary / The craft glossary

Learning analytics glossary

40 terms from R15, Learning analytics — 22 defined in the guide itself and 18 more from the field around it. Every term the guide teaches links to the slide that teaches it.

The whole craft glossary

R15 · How to improve

Learning analytics

What can logs tell us about learning?

Every term below is defined in the words of learning analytics, guide R15 of craft guides for educational technologists, and opens the guide at the slide where it is taught. 18 of the 40 are the field’s vocabulary rather than the guide’s own: words a reader will meet around this subject, defined here because the guide assumes them. 4 terms are also defined by another guide in the series; where the two differ, both wordings are given. The whole craft glossary holds all of them together.

TermDefinitionReferred to inRead further
A
Academic analytics

Analytics applied at institution level to questions of management, such as enrolment, retention and resourcing, as distinct from analytics aimed at learning itself.

  • R15Learning analyticsFrom the field · not in the guide
  • Long, P., & Siemens, G. (2011). Penetrating the fog: Analytics in learning and education. EDUCAUSE Review, 46(5). er.educause.edu
  • Campbell, J. P., DeBlois, P. B., & Oblinger, D. G. (2007). Academic analytics: A new tool for a new era. EDUCAUSE Review, 42(4), 40–57.
Accuracy

The share of all students a model is right about. It means little without the base rate: if one student in 20 will leave, a model that flags nobody is 95% accurate.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
Activity data

Records a platform makes as a by-product of use: logins, clicks, page views, submissions and timestamps.

  • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends, 59(1), 64–71. doi
  • Gašević, D., Dawson, S., Rogers, T., & Gasevic, D. (2016). Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success. The Internet and Higher Education, 28, 68–84. doi
  • Kovanović, V., Gašević, D., Dawson, S., Joksimović, S., Baker, R. S., & Hatala, M. (2015). Penetrating the black box of time-on-task estimation. In Proceedings of the Fifth International Conference on Learning Analytics and Knowledge (pp. 184–193). ACM. doi
Alert threshold

The score above which a student is flagged. Moving it changes how many students are flagged and how many flags are wrong.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
Area under the curve (AUC)

A score from 0.5 (chance) to 1 (perfect) for how well a predictive model ranks students who had the outcome above those who did not, across all thresholds.

  • R15Learning analyticsFrom the field · not in the guide
  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. doi
At-risk student

A student a model or a teacher judges likely to fail, fall behind or leave without extra support. The label is a prediction, not a fact about the student.

  • R15Learning analyticsFrom the field · not in the guide
  • Arnold, K. E., & Pistilli, M. D. (2012). Course Signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 267–270). ACM. doi
  • Kuzilek, J., Hlosta, M., Herrmannova, D., Zdrahal, Z., Vaclavek, J., & Wolff, A. (2015). OU Analyse: Analysing at-risk students at The Open University. Learning Analytics Review, LAK15-1, 1–16. oro.open.ac.uk
B
Base rate

How common an outcome is in a group before any prediction is made.

R18 How common an outcome is in the population before any test or model is applied.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Gigerenzer, G., Gaissmaier, W., Kurz-Milcke, E., Schwartz, L. M., & Woloshin, S. (2007). Helping doctors and patients make sense of health statistics. Psychological Science in the Public Interest, 8(2), 53–96. doi
  • Meehl, P. E., & Rosen, A. (1955). Antecedent probability and the efficiency of psychometric signs, patterns, or cutting scores. Psychological Bulletin, 52(3), 194–216. doi
C
Campbell’s law

The more any quantitative social indicator is used for social decision-making, the more subject it is to corruption pressures, and the more it distorts the social processes it is meant to monitor (Campbell, 1979).

  • Campbell, D. T. (1979). Assessing the impact of planned social change. Evaluation and Program Planning, 2(1), 67–90. doi
Classroom orchestration

A teacher's real-time management of several activities, groups and tools in a lesson. Teacher dashboards are often designed to support it.

  • R15Learning analyticsFrom the field · not in the guide
  • Dillenbourg, P. (2013). Design for classroom orchestration. Computers & Education, 69, 485–492. doi
Closing the loop

Making sure analytics leads to an action that reaches learners (Clow, 2012).

R22 Telling the person who reported a problem what happened to it, including when the answer is "not yet".

  • Clow, D. (2012). The learning analytics cycle: Closing the loop effectively. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 134–138). ACM. doi
  • Arizona State University. (2011). New customer-rage study: Fewer consumers satisfied than ever before [News release]. ASU News. news.asu.edu
  • Herodotou, C., Rienties, B., Boroowa, A., Zdrahal, Z., & Hlosta, M. (2019). A large-scale implementation of predictive learning analytics in higher education: The teachers’ role and perspective. Educational Technology Research and Development, 67, 1273–1306. doi
Course Signals

Purdue’s early-warning system, which gave students a red, yellow or green signal based on performance, effort and background. Its widely cited retention gain was a correlation, not an established effect (Arnold and Pistilli, 2012).

  • Arnold, K. E., & Pistilli, M. D. (2012). Course Signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 267–270). ACM. doi
  • Caulfield, M. (2013). Why the Course Signals math does not add up. Hapgood. hapgood.us
  • Clow, D. (2013). Looking harder at Course Signals. Doug Clow’s Imaginatively-Titled Blog. dougclow.org
D
Dashboard

A screen that summarises data for a teacher, a leader or a student.

  • Jivet, I., Scheffel, M., Specht, M., & Drachsler, H. (2018). License to evaluate: Preparing learning analytics dashboards for educational practice. In Proceedings of the 8th International Conference on Learning Analytics and Knowledge (pp. 31–40). ACM. doi
  • Clow, D. (2012). The learning analytics cycle: Closing the loop effectively. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 134–138). ACM. doi
E
Early-warning system

A tool that predicts which students may fail or leave, so that support can be offered early.

  • Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588–599. doi
  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Perdomo, J. C., Britton, T., Hardt, M., & Abebe, R. (2025). Difficult lessons on social prediction from Wisconsin public schools. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (pp. 2682–2704). ACM. doi
Educational data mining (EDM)

A sister field to learning analytics that develops methods for finding patterns in educational data, with an emphasis on automated discovery and modelling.

  • R15Learning analyticsFrom the field · not in the guide
  • Baker, R. S. J. d., & Yacef, K. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 1(1), 3–17. doi
  • Siemens, G., & Baker, R. S. J. d. (2012). Learning analytics and educational data mining: Towards communication and collaboration. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 252–254). ACM. doi
F
False alarm

A student flagged as at risk who would have been fine. Also called a false positive.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Feathers, T. (2023). False alarm: How Wisconsin uses race and income to label students “high risk”. The Markup. themarkup.org
G
Goodhart’s law

The observation that a measure used as a target stops being a good measure, in Strathern’s (1997) wording.

R18 When a measure becomes a target, people optimise the measure: logins rise and learning doesn't. Also known as Campbell's law, after the same point made about social indicators (Campbell, 1979).

  • Strathern, M. (1997). ‘Improving ratings’: Audit in the British university system. European Review, 5(3), 305–321. cambridge.org
  • Campbell, D. T. (1979). Assessing the impact of planned social change. Evaluation and Program Planning, 2(1), 67–90. doi
H
Human-centred learning analytics

An approach that designs analytics tools with the teachers and students who will use them, so that the tools fit their practice and needs.

  • R15Learning analyticsFrom the field · not in the guide
  • Buckingham Shum, S., Ferguson, R., & Martinez-Maldonado, R. (2019). Human-centred learning analytics. Journal of Learning Analytics, 6(2), 1–9. doi
I
Interval

The range within which an estimate plausibly lies. A narrow interval means more certainty.

  • Perdomo, J. C., Britton, T., Hardt, M., & Abebe, R. (2025). Difficult lessons on social prediction from Wisconsin public schools. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (pp. 2682–2704). ACM. doi
  • Cumming, G. (2012). Understanding the new statistics: Effect sizes, confidence intervals, and meta-analysis. Routledge. doi
Intervention

The action taken after analytics identifies a need, such as a tutor's call, a message or extra teaching. Analytics without one changes nothing for learners.

  • R15Learning analyticsFrom the field · not in the guide
  • Clow, D. (2012). The learning analytics cycle: Closing the loop effectively. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 134–138). ACM. doi
  • Arnold, K. E., & Pistilli, M. D. (2012). Course Signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 267–270). ACM. doi
L
Lag

The delay between a signal and the outcome it is meant to predict or improve.

  • Perdomo, J. C., Britton, T., Hardt, M., & Abebe, R. (2025). Difficult lessons on social prediction from Wisconsin public schools. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (pp. 2682–2704). ACM. doi
Learner model

A system's running estimate of what a student knows, can do or prefers, updated from their responses and used to adapt tasks or report progress.

  • R15Learning analyticsFrom the field · not in the guide
  • Corbett, A. T., & Anderson, J. R. (1995). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278. doi
Learning analytics

The measurement, collection, analysis and reporting of data about learners and their contexts, to understand and improve learning (Long and Siemens, 2011).

  • Long, P., & Siemens, G. (2011). Penetrating the fog: Analytics in learning and education. EDUCAUSE Review, 46(5). er.educause.edu
  • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends, 59(1), 64–71. doi
  • Ferguson, R. (2012). Learning analytics: Drivers, developments and challenges. International Journal of Technology Enhanced Learning, 4(5/6), 304–317. doi
Learning analytics cycle

Learners generate data, the data becomes metrics or visualisations, and those lead to interventions that affect learners. A dashboard nobody acts on stops the cycle halfway (Clow, 2012).

  • Clow, D. (2012). The learning analytics cycle: Closing the loop effectively. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 134–138). ACM. doi
Learning design

The planned sequence of tasks, resources and support in a course. Analytics can only be interpreted against what the design intended students to do.

  • R15Learning analyticsFrom the field · not in the guide
  • Gašević, D., Dawson, S., Rogers, T., & Gasevic, D. (2016). Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success. The Internet and Higher Education, 28, 68–84. doi
  • Lockyer, L., Heathcote, E., & Dawson, S. (2013). Informing pedagogical action: Aligning learning analytics with learning design. American Behavioral Scientist, 57(10), 1439–1459. doi
Learning evidence

Information designed to show what a student understands or can do, such as answers to well-designed questions.

  • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends, 59(1), 64–71. doi
  • Gašević, D., Dawson, S., Rogers, T., & Gasevic, D. (2016). Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success. The Internet and Higher Education, 28, 68–84. doi
Learning management system (LMS)

The platform through which an institution delivers courses, materials, assignments and grades, and the main source of activity data. Called a virtual learning environment (VLE) in the UK.

  • R15Learning analyticsFrom the field · not in the guide
  • Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588–599. doi
Learning record store (LRS)

A database that receives, stores and returns records of learning activity sent as xAPI statements from many tools.

  • R15Learning analyticsFrom the field · not in the guide
  • IEEE. (2023). IEEE standard for learning technology: JavaScript Object Notation (JSON) data model format and Representational State Transfer (RESTful) web service for learner experience data tracking and access (IEEE 9274.1.1-2023).
M
Missed case

A student who went on to fail or leave but was never flagged. Also called a false negative.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
Multimodal learning analytics

Analytics that combines log data with other sources, such as video, audio, gesture, eye tracking or sensor data, to study learning that happens away from a screen.

  • R15Learning analyticsFrom the field · not in the guide
  • Blikstein, P. (2013). Multimodal learning analytics. In Proceedings of the Third International Conference on Learning Analytics and Knowledge (pp. 102–106). ACM. doi
N
Nudge

A small prompt or change in how choices are presented, such as a reminder message, meant to steer behaviour without removing options.

  • R15Learning analyticsFrom the field · not in the guide
  • Thaler, R. H., & Sunstein, C. R. (2008). Nudge: Improving decisions about health, wealth, and happiness. Yale University Press.
O
OU Analyse

The Open University’s system that predicts which students are at risk of failing their next assignment, with predictions updated weekly for course tutors and student support teams (The Open University, n.d.).

  • The Open University. (n.d.). OU Analyse. Retrieved September 17, 2026, from research.stem.open.ac.uk
  • Kuzilek, J., Hlosta, M., Herrmannova, D., Zdrahal, Z., Vaclavek, J., & Wolff, A. (2015). OU Analyse: Analysing at-risk students at The Open University. Learning Analytics Review, LAK15-1, 1–16. oro.open.ac.uk
  • Herodotou, C., Rienties, B., Boroowa, A., Zdrahal, Z., & Hlosta, M. (2019). A large-scale implementation of predictive learning analytics in higher education: The teachers’ role and perspective. Educational Technology Research and Development, 67, 1273–1306. doi
P
Precision

Of the students flagged, the share who really had the outcome.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. doi
Predictive analytics

The use of past data to estimate the probability of a future outcome for each student, such as failing a module or withdrawing.

  • R15Learning analyticsFrom the field · not in the guide
  • Herodotou, C., Rienties, B., Boroowa, A., Zdrahal, Z., & Hlosta, M. (2019). A large-scale implementation of predictive learning analytics in higher education: The teachers’ role and perspective. Educational Technology Research and Development, 67, 1273–1306. doi
  • Macfadyen, L. P., & Dawson, S. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588–599. doi
Proxy

A measure that stands in for something harder to observe, such as time online standing in for effort.

  • Campbell, D. T. (1979). Assessing the impact of planned social change. Evaluation and Program Planning, 2(1), 67–90. doi
  • Strathern, M. (1997). ‘Improving ratings’: Audit in the British university system. European Review, 5(3), 305–321. cambridge.org
  • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends, 59(1), 64–71. doi
S
Self-regulated learning (SRL)

Learning in which students set goals, plan, monitor their progress and adjust their approach. Much learning analytics research tries to measure or support it.

  • R15Learning analyticsFrom the field · not in the guide
  • Gašević, D., Dawson, S., & Siemens, G. (2015). Let’s not forget: Learning analytics are about learning. TechTrends, 59(1), 64–71. doi
  • Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory Into Practice, 41(2), 64–70. doi
Sensitivity

Of the students who had the outcome, the share the flag caught.

  • Bowers, A. J., Sprott, R., & Taff, S. A. (2013). Do we know who will drop out? A review of the predictors of dropping out of high school: Precision, sensitivity, and specificity. The High School Journal, 96(2), 77–100. doi
  • Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. doi
Social network analysis (SNA)

The study of patterns of connection between people. In learning analytics it maps who interacts with whom, for example in discussion forums.

  • R15Learning analyticsFrom the field · not in the guide
  • Wasserman, S., & Faust, K. (1994). Social network analysis: Methods and applications. Cambridge University Press. doi
Student engagement

A student's involvement in learning, usually split into behavioural, emotional and cognitive parts. Activity data captures mainly the behavioural part.

  • R15Learning analyticsFrom the field · not in the guide
  • Fredricks, J. A., Blumenfeld, P. C., & Paris, A. H. (2004). School engagement: Potential of the concept, state of the evidence. Review of Educational Research, 74(1), 59–109. doi
Student retention

The share of students who continue on a course or at an institution from one period to the next. It is the outcome most early-warning systems aim to improve.

  • R15Learning analyticsFrom the field · not in the guide
  • Arnold, K. E., & Pistilli, M. D. (2012). Course Signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 267–270). ACM. doi
  • Tinto, V. (1993). Leaving college: Rethinking the causes and cures of student attrition (2nd ed.). University of Chicago Press. doi
T
Time on task

Time a student is estimated to have spent on an activity, usually inferred from gaps between logged actions (Kovanović et al., 2015).

R05 How long a participant takes to complete a task, a measure of efficiency.

  • International Organization for Standardization. (2018). Ergonomics of human-system interaction — Part 11: Usability: Definitions and concepts (ISO Standard No. 9241-11:2018). iso.org
  • Kovanović, V., Gašević, D., Dawson, S., Joksimović, S., Baker, R. S., & Hatala, M. (2015). Penetrating the black box of time-on-task estimation. In Proceedings of the Fifth International Conference on Learning Analytics and Knowledge (pp. 184–193). ACM. doi
  • Sauro, J., & Lewis, J. R. (2016). Quantifying the user experience: Practical statistics for user research (2nd ed.). Morgan Kaufmann. shop.elsevier.com

Nearby

The guide itself, and the ones either side

Read learning analytics (opens in a new tab)Data strategy and governance AI in learning products All 21 guides
Singapore