Term Paper: Cyber Crime Malicious Activities

Pages: 7 (2334 words)  ·  Style: APA  ·  Bibliography Sources: 5  ·  Level: College Junior  ·  Topic: Teaching  ·  Buy This Paper

SAMPLE EXCERPT:

[. . .] The basic idea here is that various authors have various compositions of text that are characterized by the word usage's probability distribution. To be more precise, in the population of text belonging to an author the identification of new text can be thought of as a classification problem or a statistical hypothesis. In order to make the authorship analysis easier, much of the earlier work made use of the statistical methods. In order to perform the lexical data analysis researches used to make use of associated distributions (Iqbal et al., 2010).

Machine learning techniques' use became very extensive in the authorship analysis with the arrival of the powerful computers. In order to conduct a test on the Federalist Papers a Bayesian model was conducted by some researchers. Two different Bayesian models were compared by some researchers for the purpose of classification of text. Although there are structural limitations in the naive Bayesian models with regards to the classification of text, there were a few relatively powerful methods that were applied in the authorship analysis and text categorization, from among these the neutral network is the most neutral one (Iqbal et al., 2010).

There was a researcher who made use of the standard feed forward artificial neural network which is also known as multi-layer perception. This was used in order to attribute the authorship to the disputed Federalist Papers. There were 3 hidden layers in the network used by them and it had two layers of output. The results received were similar to the results that were received by the previous work done on the particular topic. Radial basis function (RBF), is another kind of neutral network which was used by some researchers. REF was applied by them in order to investigate the extent to which Shakespeare collaborated with John Fletcher, his contemporary, on the different plays (Iqbal et al., 2010).

Another technique was presented by a researcher for the attribution of authorship. The main idea here was to make use of the probabilities of the following letters like features. To handle this problem a Support Vector Machine (SVM) was introduced. In order to identify the writing of seven authors from 2,652 newspaper articles which were written by many authors, experiments were done. Around 60-80% of the times the targeted authors were detected by the method. There is a new area of this study in which it is the content of the message that the identification of electronic message authors is based upon. SVM was used by a researcher as a learning algorithm in order to categorize 150 email documents from a three authors. An accuracy of 80% on average was achieved in this experiment (Abbassi and Chen, 2009).

Generally speaking there were higher accuracies that were achieved when the machine learning methods were made use of as compared to the statistical methods. The underlying distribution of personal word usage can be modeled by them with a big set of features.

Conclusion

There are a few general conclusions that we can draw from the literature review. It is because of many of the previous studies done with the hopes of resolving the authorship identification problem that new applications and techniques have come into being. Style markers were mostly used as features. There was an extensive use of the statistical approaches. In this paper there have mainly been 3 problems that have been identified regarding the cybercrime and its investigations. According to the first problem there are difficulties in identifying the author as that would require the suspects writing sample so that it could be checked against the samples available to the investigator. This problem can be solved by getting writing samples from the email or blog archives of the suspects and matching them to the investigation samples. The second problem is regarding the lack of data or samples to match them against the work done by the suspects, this problem can be solved by asking the suspects to give live samples of their writings to match against what little evidence is present. The third problem is regarding the lack of information about the criminal such as, if it is male or female, young or old etc. This problem can be solved by making use of some of the external sources such as blog, and social sites to see something written by someone that is relevant to the samples that the investigator has and to observe the writing style.

References

Abbasi, A. And Chen, H. (2009). A comparison of tools for detecting fake websites, IEEE Computer, 42 (10), pp. 78 -- 86

Abbasi, A., Zhang, Z., Zimbra, D., Chen, H. And Nunamaker, J.F. Jr. (2010). Detecting fake websites: the contribution of statistical learning theory, MIS Quarterly, 34 (3), pp. 435 -- 461.

Fouss, F. Achbany, Y. And Saerens, M. (2010). A probabilistic reputation model based on transaction ratings. Information Sciences, 180 (11), pp. 2095 -- 2123.

Hu, Q., An, S.… [END OF PREVIEW]

Four Different Ordering Options:

?
Which Option Should I Choose?

1.  Buy the full, 7-page paper:  $26.88

or

2.  Buy & remove for 30 days:  $38.47

or

3.  Access all 175,000+ papers:  $41.97/mo

(Already a member?  Click to download the paper!)

or

4.  Let us write a NEW paper for you!

Ask Us to Write a New Paper
Most popular!

Cybercrime What's in a Name? Term Paper


Cyber Crime Purpose & Audience Organization Literature Review Chapter


Information Technology (IT) Risk Management Cyber Crime Research Paper


How Does the Australian Criminal Justice System Respond to White Collar and Corporate Crime? Essay


Computer Hacker Term Paper


View 28 other related papers  >>

Cite This Term Paper:

APA Format

Cyber Crime Malicious Activities.  (2014, February 3).  Retrieved April 21, 2019, from https://www.essaytown.com/subjects/paper/cyber-crime-malicious-activities-like/4668160

MLA Format

"Cyber Crime Malicious Activities."  3 February 2014.  Web.  21 April 2019. <https://www.essaytown.com/subjects/paper/cyber-crime-malicious-activities-like/4668160>.

Chicago Format

"Cyber Crime Malicious Activities."  Essaytown.com.  February 3, 2014.  Accessed April 21, 2019.
https://www.essaytown.com/subjects/paper/cyber-crime-malicious-activities-like/4668160.