Heterogeneous feature analysis on twitter data set for identification of spam messages

الملخص EN

Spam is an undesirable content that present on online social networking sites, while spammers are the users who post this content on social networking sites.

Unwanted messages posted on Twitter may have several goals and the spam tweets can interfere with statistics presented by Twitter mining tools and squander users’ attention..

Since Twitter has achieved a lot of attractiveness through-out the world, the interest towards it by the spammers and malevolent users is also increases.

To overcome the spam problems many researchers proposed ideas using machine learning algorithms for the identification of spam messages.

Not only the selection of classifiers but also the variegated feature analysis is essential for the identification of irrelevant messages in social networks.

The proposed model performs a heterogeneous feature analysis on the twitter data streams for classifying the unsolicited messages using binary and continuous feature extraction with sentiment analysis on social network datasets.

The features created are assessed using significant stratagems and the finest features are selected.

A classifier model is built using these feature vectors to predict and identify the spam messages in Twitter.

The experimental results clearly show that the proposed Sentiment Analysis based Binary and Continuous Feature Extraction model with Random Forest (SA-BC-RF) approach classifies the spam messages from the social networks with an accuracy of 90.72% when compared with the other state-of-the-art methods.