Related work:Many application system are been createdand many research have been done to detect suspicious words messages, chat,profile, email spam, URL malicious web content also to detect phishing attacksin social media. The social approach to detect spam or malicious on Facebook,Twitter, Myspace was based on information found in social media by identifyingor detecting malicious URL link, email with spam content, suspicious words fromimage and video text.

There’s few application that detect suspicious words embeddedin images or video with help of image processing, image retrieval techniques.Previous study monitoring messages sent through social networking sites and instantmessages. The designed framework that prevent, predicts, provide evidence of cyber-attacksprofile when suspicious messages sent between users, but fail to detectsuspicious messages in short form and coded words form sent via IM and SNM inreal time. They also fail to detect suspicious words in all kind of long andshort words form and coded words embedded in image contents.Mohd Mahmood Ali, Khaja Moizuddin Mohdand Lakshmi Rajamani are researchers that found out SMD framework to detectsuspicious word from messages stored in database after users made communicationvia social media{Ali2014}.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

This paper was not focus on coded words and shortform chat messages. It was to prevent, predict and provide evidence ofsuspicious words and tracing the profile of individual or group committingcrime and report to E-crime department. However the approaches used such as datamining, ontology structure divided the websites texts semantically with theassistance of Word Net database into different attributes of threats categoriesfor example: murder, kidnap and sexual{Ali2014}. But ontology wasn’t refreshedfrequently with new code words that are discovered utilizing data mining approach. Rajamani, Lakshmi Ali, Mohammed MahmoodRasheed, Mohammed Abdul presented a system designed with a thought of textsecure framework that recognizes suspicious messages which prompts unlawfulmovements by criminals.

A framework was not concentrated on securing messagesby utilizing encryption approaches and furthermore does not focus on short formmessages. This paper gives different thoughts regarding stemming calculationand priority algorithm{Rajamani2013}.Murugesan, Devi, Deepthi, Lavanya andAnnie Princy.

They proposed the system monitoring suspicious discussionsautomatically on online forum, they used text analysis to detect suspiciouspost in online forums. They focus on automated classification to identify moreimportant suspicious discussion{Murugesan2016}. Thivya Shilpa. Gv proposed a frameworkwhich provide security, predicts, detect coded words and short form ofsuspicious words with the help of association rule mining techniques and ontologyconcept that provide security for the stored chat messages by using encryptiontechnique. But this paper doesn’t detect suspicious word attached in imagecontents {Thivya2015}.

Salim Almi Omar Beqqali, a researcherdiscovered automatic system for detecting suspicious profile in social mediathrough identifying suspicious performance and concern of users. The techniquespresented is mainly based on the calculation of similarity distance todifferentiate suspicious posts using text analysis. The limitations foundexecuting time, development automated classifications and using techniques.John Resig Ankur Teredesai 11 in theirpaper explore framework for IM and various data mining issues and how theyrelate to Instant Messaging and current Counter-Terrorism efforts. And thispaper does not tend to fully detect suspicious messages, not even detection oftopics and social network analysis.Those above articles explains approachesand limitations of capture suspicious word. Currently, clients are usingdifferent tricks of sending short form or coded words which is not so easy to recogniseby crime departments or admin. Our proposed algorithms is to detect suspiciousword in short form or coded words attached in images that are sent by users {Vijayarajan2016}.