Exploring the influence of CAPTCHA types to the users response time by statistical analysis
- 231 Downloads
CAPTCHA stands for Completely Automated Public Turing Test to Tell Computers and Humans Apart. It is a test program that solves a given task for preventing the attacks made by automatic programs. If the response to CAPTCHA is correct, then the program classifies the user as a human. This paper introduces a new analysis of the impact of different CAPTCHAs to the Internet user’s response time. It overcomes the limitations of the previous approaches in the state-of-the-art. In this sense, different types of CAPTCHAs are presented and described. Furthermore, an experiment is conducted, which is based on two populations of Internet users for text and image-based CAPTCHA types, differentiated by demographic features, such as age, gender, education level and Internet experience. Each user is required to solve the different types of CAPTCHA, and the response time to solve the CAPTCHAs is registered. The obtained results are statistically processed by Mann-Whitney U and Pearson’s correlation coefficient tests. They analyze 7 different hypotheses which evaluate the response time in dependence of gender, age, education level and Internet experience, for the different CAPTCHA types. It represents an invaluable study in the literature to predict the best use of a given CAPTCHA for specific types of Internet users.
KeywordsCAPTCHA Web Response time Usability Statistical analysis Internet user
The authors are fully grateful to Sanja Petrovska for collecting the data, and to anonymous users for providing their data. This study was partially funded by the Grant of the Ministry of Education, Science and Technological Development of the Republic of Serbia, as a part of the project TR33037 within the framework of the Technological development program.
Compliance with Ethical Standards
Conflict of interests
Author Darko Brodić declares that he has no conflict of interest. Author Alessia Amelio declares that she has no conflict of interest. Author Radmila Janković declares that she has no conflict of interest.
This article does not contain any dangerous study with human participants or animals performed by any of the authors.
This study was partially funded by the Grant of the Ministry of Education, Science and Technological Development of the Republic of Serbia, as a part of the project TR33037 within the framework of the Technological development program. The receiver of the funding is Dr. Darko Brodić.
- 1.Baecher P, Fischlin M, Gordon L, Langenberg R, Lutzow M, Schroder D (2010) CAPTCHAS: the good, the bad, and the ugly. In Proc. of GI-Sicherheit, lecture notes in informatics, vol 170, pp 353–365Google Scholar
- 2.Baird HS, Riopka T (2005) Scattertype: a reading CAPTCHA resistant to segmentation attack. In: Proc. document recognition and retrieval XII, SPIE-IS&T electronic imaging, vol 5676. SPIE, pp 197–207Google Scholar
- 5.Brodić D, Amelio A (2016) Analysis of the human-computer interaction on the example of image-based CAPTCHA by association rule mining. In: Proc. of 5th international workshop on symbiotic interaction, lecture notes in computer science, vol 9961. Springer, pp 38–51Google Scholar
- 6.Brodić D, Amelio A, Draganov IR (2016) Response time analysis of text-based CAPTCHA by association rules. In: Proc. of 17th international conference on artificial intelligence: methodology, systems, applications AIMSA, lecture notes in computer science, vol 9883. Springer, pp 78–88Google Scholar
- 7.CAPTCHA. http://www.captcha.net
- 8.Chellapilla K, Larson K, Simard P, Czerwinski M (2005) Designing human friendly human interaction proofs (HIPs). In: Proc. of SIGCHI conf. on human factors in computing systems, pp 711–720Google Scholar
- 10.Cumming G (2012) Understanding the new statistics: effect sizes confidence intervals and meta-analysis. Routledge, New YorkGoogle Scholar
- 11.DICE CAPTCHA. http://dice-captcha.com/
- 12.Dhamija R, Tygar J (2005) Phish and HIPs: human interactive proofs to detect phishing attacks. In: Proc. of Human interactive proofs: second international workshop (HIP), pp 127–141Google Scholar
- 13.Exact and asymptotic p-value. Available online. https://analyse-it.com/docs/user-guide/101/exactasymptoticpvalues
- 15.First Workshop on Human Interactive Proofs (2002). http://www2.parc.com/istl/groups/did/HIP2002
- 16.Friedman Test in SPSS Statistics. Available online. https://statistics.laerd.com/spss-tutorials/friedman-test-using-spss-statistics.php
- 20.IBM SPSS software. http://www.ibm.com/analytics/us/en/technology/spss/
- 21.Kalsoom S, Ziauddin S, Abbasi AR (2012) An image-based CAPTCHA scheme exploiting human appearance characteristics. KSII Trans Internet Inf Syst 6(2):734–749Google Scholar
- 24.Kim J, Yang J, Wohn K (2014) AgeCAPTCHA: an image-based CAPTCHA that annotates images of human faces with their age groups. KSII Trans Int Inf Syst 8 (3):1071–1092Google Scholar
- 25.Kruskal-Wallis H Test using SPSS Statistics. Available online. https://statistics.laerd.com/spss-tutorials/kruskal-wallis-h-test-using-spss-statistics.php
- 28.Lillibridge MD, Abadi M, Bharat K, Broder A (2001) Method for selectively restricting access to computer systems. US Patent 6,195,698. http://www.google.com/patents/US6195698
- 29.Liu Y, Cui J, Zhao H, Zha H (2012) Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking. In: Proc. of the 21st international conference on pattern recognition, pp 898–901Google Scholar
- 30.Liu Y, Nie L, Han L, Zhang L, Rosenblum DS (2015) Action2activity: recognizing complex activities from sensor data. In: Proc. of the 24th international conference on artificial intelligence. AAAI Press, pp 1617–1623Google Scholar
- 31.Liu Y, Zhang L, Nie L, Yan Y, Rosenblum DS (2016) Fortune teller: predicting your career path. In: Proc. of the Thirtieth AAAI conference on artificial intelligence. AAAI Press, pp 201–207Google Scholar
- 33.Liu L, Cheng L, Liu Y, Jia Y, Rosenblum DS (2016) Recognizing complex activities by a probabilistic interval-based model. In: Proc. of the Thirtieth AAAI conference on artificial intelligence. AAAI Press, pp 1266–1272Google Scholar
- 34.Liu Y, Zhang X, Cui J, Wu C, Aghajan H, Zha H (2010) Visual analysis of child-adult interactive behaviors in video sequences. In: Proc 16th International conference on virtual systems and multimedia, pp 26–33Google Scholar
- 35.Liu Y, Liang Y, Liu S, Rosenblum DS, Zheng Y (2016) Predicting urban water quality with ubiquitous data. CoRR abs/1610.09462
- 36.Liu Y, Zheng Y, Liang Y, Liu S, Rosenblum DS (2016) Urban water quality prediction based on multi-task multi-view learning. In: Proc. of IJCAI. IJCAI/AAAI Press, pp 2576–2581Google Scholar
- 39.Mann-Whitney U Test using SPSS Statistics Laerd Statistics. https://statistics.laerd.com/spss-tutorials/mann-whitney-u-test-using-spss-statistics.php
- 41.Preotiuc-Pietro D, Liu Y, Hopkins D, Ungar L (2017) Beyond binary labels: political ideology prediction of Twitter users. In: Annual meeting of the association for computational linguisticsGoogle Scholar
- 42.Research Methods I: SPSS for Windows part 3, Nonparametric tests. Available online. http://www.discoveringstatistics.com/docs/nonparametric.pdf
- 44.Rusu A, Govindaraju V (2005) Visual CAPTCHA with handwritten image analysis. In: Proc. of HIP, lecture notes in computer science, vol 3517. Springer, pp 42–52Google Scholar
- 45.The Mann-Whitney U-test – Analysis of 2-Between-Group Data with a Quantitative Response Variable. Available online. http://psych.unl.edu/psycrs/handcomp/hcmann.PDF