What is Adaptive Learning?
Adaptive learning technologies are popping up all over higher education. The premise is this: Students learn at different rates and some need more help than others. The adaptive component of these technologies means that the algorithm changes for each student based on how they answer questions. If a student answers many successive questions correctly, that student may complete the assignment after demonstrating for example expertise on 20 questions. However, if a student is struggling with a concept and answers several questions incorrectly, the program recognizes that the student needs additional learning opportunities and adds additional questions to the assignment. That student may need to answer 40 questions to complete the assignment. In addition to mastery assessment, these technologies are also typically sensitive to timing and engagement, ensuring that students cannot simply blindly click on answers in order to “finish” the assignment. The guiding principle being that assignment completion occurs only after a student has reached a specific level of proficiency with the material.
But beyond the hype, what are the scientific principles of how these adaptive technologies are helping students to better learn course material?
Immediate feedback boosts learning.
Feedback is necessary for correcting errors and effectively learning class material [1 – 2]. When students receive immediate feedback about an incorrect answer, they can immediately correct their misconceptions and stop to learn more about why they may have had those misconceptions. The longer misconceptions linger, the more permanent and harmful they become. Unfortunately, we cannot be by our students’ sides to provide immediate feedback 24/7 and by the time we review exams in class and work in class, it is often too late. The misconceptions have already taken their toll on students’ grades.
Research shows that immediate corrective feedback is much more effective than delayed feedback [3 – 4], and this is not always possible if we only provide feedback in class. Adaptive learning technologies are there for students 24/7 and provide immediate feedback on a question-by-question basis so that students can learn at their own pace and correct misconceptions as they progress through class material.
Repeated testing boosts learning.
Contrary to what students would like to hear, testing is a critical part of learning. A multitude of research studies show that students have greater learning outcomes when they take a formal test, not self-quizzing before they take a graded test for class [5 – 10]. In order to learn effectively, information must be entered, or encoded, into memory and then retrieved when it is time to recall it on an exam. When students learn, they are encoding the to-be-remembered information into memory. However, they rarely practice retrieving that information from memory. In essence, they spend a great deal of time pouring information into their brains but do not necessarily know how to find, or retrieve, it when they need it. Repeated testing provides opportunities for students to practice retrieving that information and correct any retrieval glitches before the big exam.
Low-stakes testing boosts learning…and confidence.
I recently polled my students to find out how many enjoy exams. Surprise, surprise: none of them enjoy exams. Instead, most students report experiencing test anxiety and dread exams. When adaptive learning assignments are due weekly, they become a regular part of classwork. Every week, students answer multiple-choice, fill-in-the-blank, multi-select, matching, etc. questions in a non-threatening, low-stakes situation. Engaging in a pseudo-testing situation on a regular basis de-stigmatizes test-taking and reduces overall test anxiety [11 – 12]. These assignments are not worth as many points as exams and as a result, students do not perceive them as threatening to their overall class grade. Frequently engaging in low-stakes quizzing also improves student learning by helping students to regularly assess what they have and have not learned [13 – 15].
Learning is best when the difficulty is just right.
Learning is a little like Goldilocks: students will not learn successfully if the material is too easy or too difficult. It must be just right. If the material is too easy, students will stop paying attention and tune out. If the material is too difficult, students will become cognitively overloaded, lose confidence, and will lose the motivation to learn. When the material is just difficult enough, students pay attention, engage in problem-solving to fill in gaps, and gain confidence when they overcome the challenge of learning the material [16 – 18]. It is impossible for us as teachers to know what the level of desirable difficulty there is for each student and on top of that to meet each student where they are one-on-one. Adaptive learning solves this problem. If Jenny knows all about this week’s material and answers several consecutive questions correctly, an adaptive learning program will adjust its algorithm and provide her with more challenging questions. If John is struggling with this week’s material and answers several consecutive questions incorrectly, an adaptive learning program will adjust its algorithm and provide him with less challenging questions until he has mastered the topic. Jenny and John will both master the material, but with their own custom algorithms that meet them where they are.
Adaptive technologies build metacognitive awareness.
Quick! What is the capital city of Alaska? Are you sure? How confident are you in your answer?
The answer, by the way, is Juneau. Did you answer correctly?
Some people are confident that they know the answer right away, whereas others may have guessed at the answer but were unsure if they were correct. When you assessed your confidence, you engaged in metacognitive awareness. Metacognitive awareness is simply thinking about your thoughts and is critical for learning [19 – 23]. Adaptive learning technologies can promote increased metacognitive awareness by prompting students to think about how well they know a piece of information before they answer a question. Engaging in this cognitive process across many questions builds the skill of metacognitive awareness. If students are aware of what they know and what they do not know, they can make better decisions about what they need to study. This skill will also transfer to exams. Rather than just barreling through questions as quickly as they can, students will be more reflective of their answers before moving on.
Adaptive technologies keep students motivated.
We all face the challenge of motivating our students throughout the semester. A good student may fall behind and lose confidence. A struggling student may never quite “get” the material. Adaptive learning can help motivate students to achieve their goals and keep them motivated throughout the semester. Through repeated quizzing, students learn that they can conquer testing and that they do not have to fear it. By personalizing the learning experience, adaptive learning technologies empower students to realize that they can successfully learn class material as long as they show persistence. Pursuing and achieving these small goals across the semester builds grit and confidence that carries through to other learning experiences. [See 24 – 28.]
Adaptive learning technologies provide an equal opportunity for learning experiences.
Adaptive learning technologies can help students learn the material more efficiently and effectively. It helps target the learning experience to the needs of each student. Students who need extra help receive additional learning opportunities and students who quickly demonstrate their expertise do not need to expend extra time. All students, regardless of their prior knowledge, experience, background, and skill level have opportunities to achieve the same goal: to successfully learn the material and do well in class.
1. Brosvic, G. M., Epstein, M. L., Cook, M. J., & Dihoff, R. E. (2005). Efficacy of error for the correction of initially incorrect assumptions and of feedback for the affirmation of correct responding: Learning in the classroom. The Psychological Record, 55(3), 401-418.
2. Roberts, K. J., Revenson, T. A., Urken, M. L., Fleszar, S., Cipollina, R., Rowe, M. E., ... & Lepore, S. J. (2016). Testing with feedback improves recall of information in informed consent: a proof of concept study. Patient education and counseling, 99(8), 1377-1381.
3. Dihoff, R. E., Brosvic, G. M., Epstein, M. L., & Cook, M. J. (2004). Provision of feedback during preparation for academic testing: Learning is enhanced by immediate but not delayed feedback. The Psychological Record, 54(2), 207-231.
4. Epstein, M. L., Lazarus, A. D., Calvano, T. B., Matthews, K. A., Hendel, R. A., Epstein, B. B., & Brosvic, G. M. (2002). Immediate feedback assessment technique promotes learning and corrects inaccurate first responses. The Psychological Record, 52(2), 187-201.
5. Johnson, C. I., & Mayer, R. E. (2009). A testing effect with multimedia learning. Journal of Educational Psychology, 101(3), 621.
6. McDaniel, M. A., Anderson, J. L., Derbish, M. H., & Morrisette, N. (2007). Testing the testing effect in the classroom. European Journal of Cognitive Psychology, 19(4-5), 494-513.
7. Roediger III, H. L., & Karpicke, J. D. (2006). Test-enhanced learning: Taking memory tests improves long-term retention. Psychological science, 17(3), 249-255.
8. Thomas, R. C., Weywadt, C. R., Anderson, J. L., Martinez-Papponi, B., & McDaniel, M. A. (2018). Testing Encourages Transfer Between Factual and Application Questions in an Online Learning Environment. Journal of Applied Research in Memory and Cognition, 7(2), 252-260.
9. Trumbo, M. C., Leiting, K. A., McDaniel, M. A., & Hodge, G. K. (2016). Effects of reinforcement on test-enhanced learning in a large, diverse introductory college psychology course. Journal of Experimental Psychology: Applied, 22(2), 148.
10. Schwieren, J., Barenberg, J., & Dutke, S. (2017). The Testing Effect in the Psychology Classroom: A Meta-Analytic Perspective. Psychology Learning & Teaching, 16(2), 179-196.
11. Dibattista, D., & Gosse, L. (2006). Test anxiety and the immediate feedback assessment technique. The Journal of experimental education, 74(4), 311-328.
12. Khanna, M. M. (2015). Ungraded pop quizzes: Test-enhanced learning without all the anxiety. Teaching of Psychology, 42(2), 174-178.
13. Davis, K. A. (2013). Using low-and no-stakes quizzing for student self-evaluation of readiness for exams. International Journal of Construction Education and Research, 9(4), 256-271.
14. Metcalfe, J. (2017). Learning from errors. Annual review of psychology, 68, 465-489.
15. Simon-Campbell, L., & Phelan, J. (2016). Effectiveness of an adaptive quizzing system as an institutional-wide strategy to improve student learning and retention. Nurse educator, 41(5), 246-251.
16. Bjork, E. L., Little, J. L., & Storm, B. C. (2014). Multiple-choice testing as a desirable difficulty in the classroom. Journal of Applied Research in Memory and Cognition, 3(3), 165-170.
17. Bjork, E. L., Soderstrom, N. C., & Little, J. L. (2015). Can multiple-choice testing induce desirable difficulties? Evidence from the laboratory and the classroom. The American journal of psychology, 128(2), 229-239.
18. Diemand-Yauman, C., Oppenheimer, D. M., & Vaughan, E. B. (2011). Fortune favors the (): Effects of disfluency on educational outcomes. Cognition, 118(1), 111-115.
19. Azevedo, R., Johnson, A., Chauncey, A., & Burkett, C. (2010). Self-regulated learning with MetaTutor: Advancing the science of learning with MetaCognitive tools. In New science of learning (pp. 225-247). Springer New York.
20. Littrell‐Baez, M. K., Friend, A., Caccamise, D., & Okochi, C. (2015). Using retrieval practice and metacognitive skills to improve content learning. Journal of Adolescent & Adult Literacy, 58(8), 682-689.
21. Karpicke, J. D. (2009). Metacognitive control and strategy selection: deciding to practice retrieval during learning. Journal of Experimental Psychology: General, 138(4), 469.
22. Tullis, J. G., Finley, J. R., & Benjamin, A. S. (2013). Metacognition of the testing effect: Guiding learners to predict the benefits of retrieval. Memory & cognition, 41(3), 429-442.
23. Snow, E. L., McNamara, D. S., Jacovina, M. E., Allen, L. K., Johnson, A. M., Perret, C. A., ... & Weston, J. L. (2015, June). Promoting metacognitive awareness within a game-based intelligent tutoring system. In International Conference on Artificial Intelligence in Education (pp. 786-789). Springer, Cham.
24. Clark, I. (2012). Formative assessment: Assessment is for self-regulated learning. Educational Psychology Review, 24(2), 205-249.
25. Harkin, B., Webb, T. L., Chang, B. P., Prestwich, A., Conner, M., Kellar, I., ... & Sheeran, P. (2016). Does monitoring goal progress promote goal attainment? A meta-analysis of the experimental evidence. Psychological bulletin, 142(2), 198.
26. Wickline, V. B., & Spektor, V. G. (2011). Practice (rather than graded) quizzes, with answers, may increase introductory psychology exam performance. Teaching of Psychology, 38(2), 98-101.
27. Soderstrom, N. C., Yue, C. L., & Bjork, E. L. (2016). 11 Metamemory and Education. The Oxford Handbook of Metamemory, 197.
28. Healy, A. F., Jones, M., Lalchandani, L. A., & Tack, L. A. (2017). Timing of quizzes during learning: Effects on motivation and retention. Journal of Experimental Psychology: Applied, 23(2), 128.