Customized Visualization of Email Using Sentimental and Impact Analysis in R

  • V. RoopaEmail author
  • K. IndujaEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1046)


In our modern world of social interactions where the analysis of each content on social media is based on the impact of the sentiment it imposes on the forum. The proposed system is used to implement a more personalized and customized report of these impacts. Email is of main focus here where in out of all other social applications, responses to and from the email is the most traditional and ethical way to communicate online. Users share all information, through internet especially emails because of its fast transmission and is considered as the most professional medium. Hence the proposed model focus more on the subjective content of email processed on R libraries created for Natural language processing in a more customized way. Nowadays, crime rate in emails are increasing drastically. Spamming, phishing and email fraudulent are the ways of targeting common people. The sentimental analysis on the impact of the email received is analysed and visualized. The system also proposes a design for establishing a framework that detects the suspicious one by comparing the mail with keywords and also reveals the level of suspiciousness in the particular mail.


Sentiment analysis Text mining Analysis Analytic Spamming 


  1. 1.
    Peng, R.D.: Overview and history of R. Computing for Data Analysis Course, Johns Hopkins UniversityGoogle Scholar
  2. 2.
    Hershkop, S.: Behavior-based email analysis with application to spam detection. Columbia UniversityGoogle Scholar
  3. 3.
    Ma, J., Saul, L.K., Savage, S., Voelker, G.M.: Learning to detect malicious web sites from suspicious URLs. University of California, San DiegoGoogle Scholar
  4. 4.
    Chakraborty, G.: Applications of text analytics and sentiment mining. Oklahoma State UniversityGoogle Scholar
  5. 5.
    Zanasi, A.: Text mining tools. Modena and Reggio Emilia University, Italy. Appendix: Springer-Author DiscountGoogle Scholar
  6. 6.
    Medhat, W., Hassan, A., Korashy, H.: Sentiment analysis algorithms and applications: a survey. Ain Shams Eng. J. 5, 1093–1113 (2014)CrossRefGoogle Scholar
  7. 7.
    Ghosh, S., Roy, S., Bandyopadhyay, S.K.: A tutorial review on text mining algorithms. Int. J. Adv. Res. Comput. Commun. EngGoogle Scholar
  8. 8.
    Pendar, N.: Toward spotting the pedophile telling victim from predator in text chats. In: IEEE Internet Computing, pp. 235–241 (2007)Google Scholar
  9. 9.
    Stolfo, S.J., Hershkop, S.: Email mining toolkit supporting law enforcement forensic analyses. Columbia UniversityGoogle Scholar
  10. 10.
    Vadher, B.: EMail data mining: an approach to construct an organization position-wise structure while performing email analysis. Master’s Projects, Paper 63, San Jose State University (2010)Google Scholar
  11. 11.
    Zhao, Y.: Text mining with R – an analysis of Twitter dataGoogle Scholar
  12. 12.
    Haddia, E., Liua, X., Shib, Y.: The role of text pre-processing in sentiment analysis. IEEEGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Information TechnologySri Krishna College of TechnologyCoimbatoreIndia

Personalised recommendations