Professional Documents
Culture Documents
net/publication/281554739
CITATIONS READS
3 898
2 authors, including:
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Himani Mittal on 20 August 2019.
Recent advancements in the field of e-learning and virtual learning have changed the face of education. An important part
of learning process is assessment of student learning through examinations. The Examination process involves conduct of
examinations, evaluation of the answers and result declaration. This paper reviews various computer-based, computer-
assisted and web-based tools for evaluation of the Subjective, Objective and Practical Examinations. For subjective
examinations, statistical and mathematical tools available for evaluation of short-answer, long-answer and essay-length
answer questions are reviewed. The scope of evaluation done by these tools is limited to style and keyword presence. For
objective examinations, a number of automated tools for multiple-choice question evaluation are available. For practical
examinations, the scope of evaluation tools available is limited to computer science education. These tools are used for
evaluation of software programs in assignments or competitions. The paper also includes a discussion on the reviewed
work. The subjective tools use a bag-of-words approach. The objective tools focus on Multiple Choice Questions. The use of
practical tools can be extended to formal examinations also. Finally, it is concluded that though there are many tools
available for objective evaluation, but there is a need to develop tools for evaluating subjective and practical examinations
satisfactorily. The scope for further work to enhance the performance of evaluation tools is also included.
Keywords: Evaluation tools, Subjective Evaluation, Statistical Methods, Latent Semantic Analysis, Practical Assignments.
1. INTRODUCTION
Teaching and learning process is undergoing a transition. Virtual learning and E-learning platforms have changed
the face of classroom teaching. Examinations are an important part of learning process which require to be
computerized. In traditional examination system, the student submits the answers written on answer-book.
These answer-books are given to evaluator for grading. Grading is time consuming and depends on availability
of evaluator. Then the results are compiled. The use of computerized tools reduces the limitations of manual
process. The online examination terminals transfer the answers submitted by students, electronically to the
centralized database and thus avoiding the physical movement of answer books. The advantages of intelligent
software tools are manifold. They are fast and avoid human errors of omission and totaling mistakes. They
ensure uniformity of marking scheme because they have the same inference mechanism for checking all the
answers. Automation can ensure speedy result declaration.
The student’s performance is evaluated with the help of Objective, Practical and Subjective examinations
as per the need of the course. Subjective Examinations include short-answer, long-answer and essay-length
answer questions. The answers are evaluated on the basis of a number of parameters like correctness, presence
of keywords and style of writing. The scope of evaluation done by available tools is limited to presence of
keywords and style of writing. They use a bag-of-words approach and cannot evaluate factual correctness. The
objective examinations can be any of the following variety like multiple-choice questions (MCQ), multiple-
answer questions, fill-in-the-blanks, match-the-following and one-word answers. For evaluation of Objective
examination, a range of computerized evaluation tools are available that have good performance. However,
these tools primarily focus on MCQ questions. Practical Examinations for computer science education include
project work, assignments and programming experiments. The available tools focus only on the evaluation of
programming assignments and competitions.
The paper is organized as follows. The review of related work in Subjective, Objective and Practical
evaluation tools is given in section 2. The discussion on available reviewed work is included in section 3.
Conclusions and scope for future work is mentioned in section 4.
*Corresponding author: syamala@pu.ac.in; research.himani@gmail.com
112 M. Syamala Devi and Himani Mittal
In 2008, Li Bin, Lu Jun, Yao Jian-Min, Zhu Qiao-Ming [17], the K-Nearest Neighbor (KNN) algorithm for
text classification is applied. It makes use of training documents which have known categories and finds closest
neighbors of the new sample document among all. These neighbors enable to find the category of new document.
The experiments show accuracy above 76%. In 2010, Islam and Hoque [18] proposed a system that makes use
of Generalised latent semantic analysis (GLSA) technique for evaluation. In GLSA n-gram by document matrix
is created instead of a word by document matrix of LSA. It has 89% of accuracy which show that the system is
very closer to human grader. In 2010, Cutrone and Chang [19] in their research paper proposed a short answer
evaluation method using Natural language processing (NLP) techniques. It reduces the standard answer and
student answer into its canonical form and compares them. It uses NLP techniques like parsing, stemming,
stop-word removal, morpho-syntactic-variation handling, etc. The system in its current format is capable of
processing answers containing a single sentence that is free of grammar and spelling mistakes.
there paper published in 2006 [35] the architecture of an Automatic Program Evaluation System. This system
can handle only C programs. Their approach is to perform White Box test, instead of, Black box or Grey box
testing.
SQLify (2007) [36] is to assist students learn SQL. It facilitated writing test queries against databases,
receive immediate feedback which is more informative than what can be offered by DBMS. In 2010, Zhang
and Haifeng Ke [37] also proposed a design for SQL Paperless Examination System. In 2008, Farrow and King
[38] used an online programming examination to assess undergraduates who had learned Java for two terms. It
uses BLUEJ and JUnit software. In 2010, Bronius Skupas [39] wrote a paper on feedback improvement in
automatic program evaluation systems. He says that some programming errors should not influence the final
score heavily. Black box testing alone cannot ensure this. A typical approach is to use semi-automatic systems
for programming exam evaluation. It proposes two grading steps. The first step is responsible for student program
output format checking. The second step relates to output correctness. In 2011, Fernández Alemán [40] proposed
an automated assessment tool for programming courses. It extends the functionality of Mooshak by adding a
external static marker.
In Zhenming, Liang and Guohua, 2003 [41] and Zhang, Zhuang, Zhenming and Guohua, 2006 [42], tool
was developed to measure operating skills of the students and their proficiency in using software like Ms-
Word, Ms-Excel, Ms-Powerpoint and internet familiarity.
An overview of features required by practical evaluation tools is given in [43]. For Evaluation of GUI-
based student programs English [44] proposed a tool called JEWL for Java GUI programs.
programming examinations is discussed in [38]. The operating skills are evaluated in [41, 42]. Programming
languages evaluated by these tools are C, C++, Fortran, Pascal and Java (All tools do not evaluate all languages).
The technique used in all the tools for evaluation is black box testing. [39, 45] emphasize the use of white-box
testing in evaluation tools.
The practical evaluation tools are built using different technologies. Assyst is a collection of Linux shell
scipts. Boss is developed using Java. Mooshak is implemented using Tcl/Tk. [41,42] are designed using DCOM.
4.1. Conclusions
Using computer technology to conduct and evaluate examinations will benefit both students and the universities,
by saving time, effort, ensuring minimal error and universal accessibility of the system. For the Objective type
of examinations, many Universities and institutes use computerized tools for the evaluation. However, there is
enough scope for research in the evaluation of Practical and Subjective examinations as the existing computerized
tools do not focus on correctness of answers.
References
[1] Macdonald, N. H., Frase, L. T., Gingrich, P. S., Keenan, S. A., (1982), The Writer’s Workbench: Computer Aids for Text
Analysis, IEEE Transactions on Communications, 30(1), 105-110.
[2] Page, E. B., (1994), Computer Grading of Student Prose, Using Modern Concepts and Software, The Journal of
Experimental Education, 62(2), 127-142.
[3] Shermis, M. D., Mzumara, H. R., Olson, J., Harrington, S., (2001), On-line Grading of Student Essays: PEG goes on the
World Wide Web, Assessment & Evaluation in Higher Education, 26(3), 247-259.
[4] Burstein, J., Kukich, K., Wolff, S., Chi Lu, Chodorow, M., Braden-Harder, L., and Harris, M. D., (1998), Automated
Scoring Using A Hybrid Feature Identification Technique, Proceedings of the Annual Meeting of the Association of
Computational Linguistics and International Conference on Computational Linguistics, 1, 206-210. Doi: 10.315/
980451.980879.
[5] Attali, Y., Burstein, J., (2006), Automated Essay Scoring With E-rater? V.2.0, The Journal of Technology, Learning and
Assessment, 4(3), e-journal.
[6] Burstein, J., Marcu, D., (2000), Towards Using Text Summarization for Essay-Based Feedback, in Le 7e Conference
Traitement Automatique des Langues Naturelles TALN’2000.
116 M. Syamala Devi and Himani Mittal
[7] Sukkarieh, J. Z., Blackmore, J., (2009), c-rater: Automatic Content Scoring for Short Constructed Responses, Proceedings
of the Twenty-Second International FLAIRS Conference, AAAI Press, pp. 290-295.
[8] Sukkarieh, J. Z., (2011), “Using a MaxEnt Classifier for the Automatic Content Scoring of Free-Text Responses”, American
Institute of Physics Conference Proceedings, 1305(1), 41.
[9] Foltz, P. W., Laham, D., & Landauer, T. K. (1999), Automated Essay Scoring: Applications to Educational Technology. In
B. Collis and R. Oliver (Eds.), Proceedings of EDMedia’99, Charlottesville, VA: Association of Computing in Education,
(pp. 939-944).
[10] Hofmann, T., (1999), Probabilistic Latent Semantic Indexing Proceedings of the 22nd International Conference on Research
and Development in Information Retrieval (SIGIR’99).
[11] Callear, D., Jerrams-Smith, J., Soh, V., (2001), Bridging Gaps in Computerised Assessment of Texts, Proceedings of the
IEEE International Conference on Advanced Learning Techniques (ICALT’01), IEEE, 139-149.
[12] Rudner, L. M., Liang, T., (2002), Automated Essay Scoring Using Bayes’ Theorem, The Journal of Technology, Learning,
and Assessment, 1(2), e-journal.
[13] Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003), Latent Dirichlet Allocation. Journal of Machine Learning Research, 3(5),
993-1022.
[14] Rose, C. P., Roque, A., Bhembe, D., VanLehn, K., (2003), A Hybrid Approach to Content Analysis for Automatic Essay
Grading, Proceedings of the 2003 Conference of the North American Chapter of Association of Computational Linguistics
on Human Language Technology, 2, 88-90. Doi: 10.3115/1073483.1073513.
[15] Perez, D., Gliozzo, A., Strapparava, C., Alfonseca, E., Rodrýguez, P., Magnini, B., (2005), Automatic Assessment of
Students’ Free-text Answers Underpinned by the Combination of a BLEU-inspired Algorithm and Latent Semantic Analysis,
in Proceedings of 18th International Florida Artificial Intelligence Research Society Conference, Flairs, AAAI Press.
[16] Kakkonen, T., Myller, N., Sutinen, E., Timonen, J., (2008), Comparison of Dimension Reduction Methods for Automated
Essay Grading, Educational Technology & Society, 11(3), 275-288.
[17] Li Bin, Lu Jun, Yao Jian-Min, Zhu Qiao-Ming, (2008), Automated Essay Scoring Using the KNN Algorithm, International
Conference on Computer Science and Software Engineering, IEEE, Vol. 1, pp 735-738. DOI 10.1109/CSSE.2008.623
[18] Islam M. , Hoque A.S.M.L., (2010), Automated Essay Scoring Using Generalized Latent Semantic Analysis, Proceedings
of 13th International Conference on Computer and Information Technology, pp. 358-363.
[19] Cutrone, L., Chang, M., (2010), Automarking: Automatic Assessment of Open Questions, 10th IEEE International
Conference on Advanced Learning Technologies, IEEE, 143-147.
[20] Tinoco, L. C., Fox, E., Ehrich, R., Fuks, H., (1996), QUIZIT: An Interactive Quiz System for WWW-based Instruction, 7 th
Proceedings of the Symposium of Educational Technology.
[21] Tinoco, L. C., Fox, E. A., Barnette, N. D., (1997), Online Evaluation in WWW-based Courseware, Proceedings of the 28 th
SIGCSE technical Symposium on Computer Science Education, 29(1), 194-198. Doi:101145/268085.268156.
[22] Gardner, L., (2001), Computer Supported Learning. A Large-Scale, Web-based Learning and Assessment System to Support
Flexible Education, Proceedings of the 34th Hawaii International Conference on System Sciences, Vol 1.
[23] http://www.webassign.net/
[24] Xingbao Li, Yunming Wu, (2007), Design and Development of Online Examination and Evaluation System based on B/
S Structure, Proceedings of International Conference on Wireless Communications, Networking and Mobile Computing,
IEEE, 6223-6225.
[25] Li Jun, (2009), Design of Online Examination System Based on Web Service and COM, The 1st International Conference
on Information Science and Engineering, pp. 3276-3279.
[26] Moe Moe Aye and Mie Mie Thet Thwin, (2008), “Mobile Agent Based Online Examination System”, Proceedings of
International Conference on Electrical/electronics, Computer, Telecommunication and Information Technology Association,
1, 193-196.
[27] Gawali, R. D., Meshram, B. B., (2009), “Agent-Based Autonomous Examination Systems”, International Conference on
Intelligent Agent and Multi-agent Systems, IEEE, pp 1-7.
[28] Jackson, D., Usher, M., (1997), “Grading Student Programs using ASSYST”, In Proceedings of the 28 th SIGCSE Technical
Symposium, pp. 335-339. dx.doi.org/doi:10.1145/268084.268210.
Review of Computerized Evaluation tools in Education 117
[29] Daly C., (1999), RoboProf and an Introductory Computer Programming Course, Proceedings of the 4 th Annual SIGCSE/
SIGCUE on Innovation and Technology in Computer Science Education June 27 -30, 1999, Krakow Poland, Pages 155-
158. DOI : 10.1145/384267.305904.
[30] http://www.boss.org.uk/
[31] Leal, J.P., Silva, F., (2003), Mooshak: AWeb-based Multi-site Programming Contest System, Journal of Software- Practice
and Experience, John Wiley and Sons, 33(6), 567-581.DOI:10.1002/spe.522.
[32] García-Mateos, G., Fernández-Alemán, J., L., (2009), A Course on Algorithms and Data Structures Using On-line Judging,
Proceedings of the 14th annual ACM SIGCSE Conference on Innovation and Technology in Computer Science Education
41(3), 45-49. Doi: 10.1145/1505496.1562897.
[33] Montoya-Dato, F. J., Fernández-Alemán, J. L., and García-Mateos, G., (2009), “An Experience on Ada Programming
using On-line Judging,” in Proc. 14th International Conference on Relaible Software Technologies, pp. 75-89.Doi: 10.1007/
978-3-642-01924-16.
[34] Douce et al., (2005), A Technical Perspective on ASAP - Automated System for Assessment of Programming. in Proceedings
of the 9th Computer Assisted Assessment Conference.
[35] Mandal, A. K., Mandal, C., Reade, C. M. P., (2006), Architecture of an Automatic Program Evaluation System, In CSIE
Proceedings.
[36] Raadt. M., Dekeyser, S., Tien Yu Lee, (2007), A Student Employing Peer Review and Enhanced Computer Assisted
Assessment of Querying Skills, Informatics in Education, 2007, 6(1), 163-178.
[37] Gaoyan Zhang, Haifeng Ke, (2010), SQL Paperless Examination System Design, 2010 Second International Conference
on Computer Modeling and Simulation, IEEE, 3, 475-478. DOI 10.1109/ICCMS.2010.468.
[38] Farrow, M., King, P. J. B., (2008), Experiences with Online Programming Examinations, IEEE Transactions on Educatio,
51(2).
[39] Skupas, B., (2010), Feedback Improvement in Automatic Program Evaluation Systems, Informatics in Education, 9(2),
229-237.
[40] Fernández Alemán, J. L., (2011), Automated Assessment in a Programming Tools Course, IEEE Transactions on Education,
54(4), 576-581.
[41] Yuan Zhenming, Zhang Liang, Zhan Guohua, (2003), “A Novel Web-Based Online Exmination System For Computer
Science Education”, IEEE, Proceedings of International Conference on Frontiers in Education.
[42] Liang Zhang, Yue-ting Zhuang, Zhen-ming Yuan, Guo-hua Zhan, (2006), “A Web-based Examination and Evaluation
System for Computer Education”, IEEE, Proceedings of the Sixth International Conference on Advanced Learning
Technologies.
[43] Hollingsworth, J. (1960), Automatic Graders for Programming Classes. Commun. ACM 3, 10, 528-529. DOI: 10.1145/
367415.367422.
[44] ENGLISH, J. (2004), Automated Assessment of GUI Programs using JEWL. Proceedings of the 9th Annual SIGCSE
Conference on Innovation and Technology in Computer Science Education. 131-141.
[45] FORISEK, M., (2006), On the Suitability of Programming Tasks for Automated Evaluation, Informatics in Education,
2006, 5(1), 63-76 63.