Step section is used to monitor user’s activities and

Step 2: Admin login

The system will start reading the
messages and attached document such as images by user’s string. It happened
when users send messages and input suspicious word in images the system admin
will automatically start monitoring the messages and images that contain
suspicious word in short form or coded word in stored database. This section is
used to monitor user’s activities and check for suspicious word modification by
adding a new code word. Admin has username and password that can login and
check all sharing details of users and information when the system flags it to
be suspicious word. Also scanning all messages and post images to identifying
suspicious word short form or code word available, perform task of encoding and
decoding plain text hidden in images with help of cryptography algorithm.

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


order now

Encrypt and decrypt the image/text.

The proposed methods using cryptography
algorithm triple DES, (3 data encryption standard) this algorithm is for
encryption or decrypting the information that are sent to users. We detect the
suspicious messages / images sent from users who are already registered on
social media. Although new users sign up themselves on the site to send short
messages and attached documents of those who already registered and view the
messages and sending request from registered users, but if they do not
registers they cannot be able to login{Rani2015}.

Triple DES algorithm used by admin to
encrypt the messages or file attached, such images are sent to users or sent
some block suspicious words in short form or code words not to be access by
users. There are two procedures we used for encoding and decoding messages
shared among users are {Rani2015}:

·        
The process of encoding
the plaintext into cipher text / image is called Encryption.

·        
The process of decoding
ciphers text to plaintext / image is called Decryption

Short form and code word detected

We used suspicious words dictionary to
detect the suspicious words of all kind in any form which are not actually used
in the normal messages of communication. Admin part has a different database that
keep up with short form of suspicious words. For example, users detail information
are: names, email, location names but for short form of suspicious word, for
example, kl (kill), att (attack), bom (bomb) and cash ($). Using WorldNet
ontology techniques for extracting information from unstructured data and data
mining approach {Ali2013}.

Code word

Contrasting a few messages impacted
inside same group can be recognized as code words. In the event that same word
was utilized by various individuals in discussion inside a gathering alongside
known suspicious words in database, then these words are considered as code
words and furthermore added to suspicious rundown to recognize suspicious words
in future {Thivya2015}.

New suspicious word updated

New suspicious words that are not as of
now in database are established with the assistance of code words discovery technique
and will be included back in ontology. In this manner attitude utilized here is
completely refreshed without even a second’s pause. This ontology refresh helps
in finding suspicious words in dynamic way and it releases time in recognizing
suspicious words in future {Thivya2015}.

Pre-processing

The filtering of messages and files is pre-processing
in text mining approaches started by checking suspicious word in the dataset by
removing unnecessary word, check errors spelling if messages are correct. This
stage includes text corpus consists large set of structured text messages in
social media. Text corpus consists stop word, stemming and remove word in
computing by Natural Language Processing Algorithms.

Machine Learning, NLP: Text
Classification

Text Classification assigns at least one
or more classes to a document as specified by their contents. Classes are
chosen from a formerly established taxonomy categorization (a hierarchy system
of classifications or classes). Document classification is an issue in library
science for checking Text corpus database and extracting data of a few
structured information, example of this documentations might be classified by
their subjects or as indicated by different attribute’s, (for example, compose
document, date, year, sender and recipient details, time and so on. There are
several approaches of text classifications, which are as follows: