Abstract
The aim of this research is to predict learners’ achievement by using a data mining technique: Random Forest (RF). For this purpose, learners eye movements were recorded by an eye-tracker and their answers to questions were collected via an online assessment tool. Online tests were administered to the students and computer interface was divided into two equal parts, which includes web browser and image processing software. Questions were asked through the browser and participants pencil usage (mouse click counts) was recorded by graphic tablet via the software. Results showed that eye metrics and mouse click counts can be used to predict the answer correctness. While mouse click counts were found to be an important factor for predicting answers in questions that require quantitative operations, fixation count and visit duration metrics are found to be important in questions which include visual elements like graphics. Total fixation duration, number of mouse clicks, fixation count and visit duration were found being the most important eye metrics that predict answers in reasoning questions. Results also showed that changing the presentation modality of a question causes changes in relative importance of each eye metric.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- AOI:
-
Area of interest
- CART:
-
Classification and regression trees
- GA:
-
Genetic algorithm
- GRE:
-
Graduate record examinations
- LMS:
-
Learning management systems
- MCAS:
-
Massachusetts comprehensive assessment system
- mtry:
-
Number of descriptors randomly sampled for potential splitting
- RF:
-
Random forest
- SIS:
-
Student information systems
References
Chuang, H.H., Liu, H.C.: Effects of different multimedia presentations on viewers’ information-processing activities measured by eye-tracking technology. J. Sci. Educ. Technol. 21(2), 276–286 (2012)
Tsai, M.J., Hou, H.T., Lai, M.L., Liu, W.Y., Yang, F.Y.: Visual attention for solving multiple-choice science problem: an eye-tracking analysis. Comput. Educ. 58(1), 375–385 (2012)
Buckingham, S.S., Ferguson, R.: Social learning analytics. Educ. Technol. Soc. 15(3), 3–26 (2012)
Abdous, M., He, W., Yen, C.J.: Using data mining for predicting relationships between online question theme and final grade. Educ. Technol. Soc. 15(3), 77–88 (2012)
Xu, B., Recker, M.: Teaching analytics: a clustering and triangulation study of digital library user data. Educ. Technol. Soc. 15(3), 103–115 (2012)
Verbert, K., Manouselis, N., Drachsler, H., Duval, E.: Dataset-driven research to support learning and knowledge analytics. Educ. Technol. Soc. 15(3), 133–148 (2012)
Hung, J.L., Hsu, Y.C., Rice, K.: Integrating data mining in program evaluation of K-12 online education. Educ. Technol. Soc. 15(3), 27–41 (2012)
Pardos, Z.A., Heffernan, N.T., Anderson, B.S., Heffernan, C.L.: Using fine-grained skill models to fit student performance with Bayesian networks. In: Romero, C., Ventura, S., Pechenizkiy, M., Baker, R.S.J.D. (eds.) Handbook of Educational Data Mining, Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, pp. 417–426. CRC Press, Boca Raton (2010)
Minaei-Bidgoli, B., Kashy, D.A., Kortemeyer, G., Punch, W.F.: Predicting student performance: an application of data mining methods with the educational web-based system LON-CAPA. In: ASEE/IEEE Frontiers in Education Conference, pp. 1–6. IEEE Press, New York (2003)
Solso, R.L., Maclin, M.K., Maclin, O.H.: Cognitive Psychology. Pearson Education, Old Tappan (2007)
Salah, A.A., Saygin, A.P.: Retinotopy and selective visual attention in humans and computers. In: Signal Processing. Communication and Applications Conference, pp. 1–6. IEEE Press, New York (2008)
Tsotsos, J.K., Culhane, S.M., Wai, W.Y.K., Lai, Y., Davis, N., Nuflo, F.: Modeling visual attention via selective tuning. Artif. Intell. 78(1–2), 507–545 (1995)
Mayer, R.E.: Multimedia Learning. Cambridge University Press, Cambridge (2001)
Anderson, J.R.: Cognitive Psychology and Its Implications. Worth Publishers, New York (2005)
Baddeley, A.D., Hitch, G.J.L.: Working memory. Psychol. Learn. Motiv.: Adv. Res. Theor. 8, 47–89 (1974)
Poole, A., Ball, L.J., Phillips, P.: In search of salience: a response time and eye movement analysis of bookmark recognition. In: Fincher, S., Markopoulos, P., Moore, D., Ruddle, R. (eds.) People and Computers XVIII—Design for Life, pp. 363–378. Springer, London (2004)
Hyöna, J., Nurminen, A.: Do adult readers know how they read? Evidence from eye movement patterns and verbal reports. Br. J. Psychol. 97(1), 31–50 (2006)
Goldberg, H.J., Kotval, X.P.: Computer interface evaluation using eye movements: methods and constructs. Int. J. Ind. Ergon. 24(6), 631–645 (1999)
Duchowski, A.T.: Eye Tracking Methodology: Theory and Practice. Springer, Heidelberg (2003)
Rayner, K.: Eye movements in reading and information processing: 20 years of research. Psychol. Bull. 124(3), 372–422 (1998)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Tobii User Manuals http://www.tobii.com/Global/Analysis/Downloads/User_Manuals_and_Guides/Tobii_Studio2.2_UserManual.pdf
Svetnik, V., Liaw, A., Tong, C., Culberson, J.C., Sheridan, R.P., Feuston, B.P.: Random forest: a classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci. 43(6), 1947–1958 (2003)
Dahinden, C.: An improved random forests approach with application to the performance prediction challenge datasets. In: Guyon, I., Cawley, G., Dror, G., Saffari, A. (eds.) Hands-On Pattern Recognition: Challenges in Machine Learning, vol. 1, pp. 223–230. Microtome Publishing, Brookline (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Supplementary
Appendix: Supplementary
1.1 Question-1
There are X, Y, Z, V sub tests in a 90-question test. Test X has 45, test Y has 19, test Z has 14 and test V has 12 questions. A student’s score in this exam is calculated as follows:
-
Each correct answer adds 2 points in test X, 1.5 points in test Y, 1 point in test Z and 0.5 point in test V.
-
No point is reduced for incorrect or omitted questions.
According to data: A student who answers all of the questions in test V correctly, has 6 times more correct answers in test Y than in test X.
Now that this student has 38 correct answers in total and his score in the exam is 44, what is the number of correct answers he has in test Z?
-
A)
3
-
B)
4
-
C)
5
-
D)
6
-
E)
7
1.2 Question-2
The Fig. A.1 shows the number of questions in 4 sub tests and the points given for each correct answer. No point is reduced for incorrect or omitted questions.
According to data: A student who answers all of the questions in test V correctly, has 3 times more correct answers in test Y than in test X.
Now that this student has 30 correct answers in total and his score in the exam is 132, what is the number of correct answers he has in test Z?
-
A)
2
-
B)
4
-
C)
6
-
D)
8
-
E)
10
1.3 Question-3
The Table A.1 gives the planting areas of crops planted in a 1,200-decare land and the distribution of 600 tons of harvested crops in percentage.
According to this, how many tons greater is the harvested corn than the harvested sunflower?
-
A)
90
-
B)
96
-
C)
102
-
D)
104
-
E)
108
1.4 Question-4
The Fig. A.2 gives the planting areas of crops planted in a 1,200-decare land and the distribution of 600 tons of harvested crops in percentage.
According to this, how many tons greater is the harvested corn than the harvested sunflower?
-
A)
15
-
B)
30
-
C)
45
-
D)
60
-
E)
75
1.5 Question-5
The Table A.2 shows some activities performed by a sportsman and the amount of calories he burned after an hour of performing these activities.
Now that this sportsman burns 1,130 calories by performing 1Â h of activity A, 5Â h of activity B; what are activities A and B?
-
A)
Walking—Tennis
-
B)
Walking—Gymnastics
-
C)
Gymnastics—Tennis
-
D)
Tennis—Gymnastics
-
E)
Tennis—Biking
1.6 Question-6
The Fig. A.3 shows the amounts of a country’s imports and exports from 1999 to 2004. How many percent is this country’s exports in 2004 constitute of its total exports for six years?
-
A)
25
-
B)
28.5
-
C)
30.5
-
D)
35
-
E)
50
1.7 Question-7
See the Fig. A.4 and respond: How many unit squares is the above polygonal zone’s area?
-
A)
6
-
B)
6.5
-
C)
7
-
D)
7.5
-
E)
8
1.8 Question-8
As for Fig. A.5, Mert wants to obtain parts in Fig. A.5II by slicing the square in Fig. A.5I.
How many parts can he obtain at most?
-
A)
4
-
B)
5
-
C)
6
-
D)
7
-
E)
8
1.9 Question-9
Regarding Fig. A.6, it is wanted to obtain parts in Fig. A.6II by slicing the square in Fig. A.6I.
How many parts can be obtained at most?
-
A)
4
-
B)
5
-
C)
6
-
D)
7
-
E)
8
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Bayazit, A., Askar, P., Cosgun, E. (2014). Predicting Learner Answers Correctness Through Eye Movements with Random Forest. In: Peña-Ayala, A. (eds) Educational Data Mining. Studies in Computational Intelligence, vol 524. Springer, Cham. https://doi.org/10.1007/978-3-319-02738-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-02738-8_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02737-1
Online ISBN: 978-3-319-02738-8
eBook Packages: EngineeringEngineering (R0)