Spam Detection on Twitter Using Traditional Classifiers

Abstract

Social networking sites have become very popular in recent years. Users use them to find new friends, updates their existing friends with their latest thoughts and activities. Among these sites, Twitter is the fastest growing site. Its popularity also attracts many spammers to infiltrate legitimate users' accounts with a large amount of spam messages. In this paper, we discuss some userbased and content-based features that are different between spammers and legitimate users. Then, we use these features to facilitate spam detection. Using the API methods provided by Twitter, we crawled active Twitter users, their followers/following information and their most recent 100 tweets. Then, we analyzed the collected dataset and evaluated our detection scheme based on the suggested user and content-based features. Our results show that among the four classifiers we evaluated, the Random Forest classifier produces the best results. Our results based on the 100 most recent tweets also show that spam detection based on our suggested features can achieve 95.7% precision and 95.7% Fmeasure using the Random Forest classifier.

A Framework for Evaluating Anti Spammer Systems for Twitter

“…Performance is evaluated based on precision (the percentage of correct positive prediction), recall (the percentage of positive instances that were predicted as positive), and accuracy (overall percentage of correct prediction). [7] demonstrates a method of extracting the user and contextbased features from the dataset before running this through Meda et al's Random Forest classifier [25]. The output was evaluated based on precision and f-measure, the harmonic mean of precision and recall.…”

“…In Twitter, the #hashtag is used to describe a term, event, or emotion. If multiple tweets occur with the same #hashtag, it will become a trending topic [7]. Spammers often include a trending #hashtag with their tweets (though with unrelated content) in order to lure in legitimate users [17].…”

“…These features are used in different combinations with varying success. [7] uses the number following and number followed features, and achieve 95.7% precision, whereas [14] uses number following, number followed, and reputation, but only achieves 91% precision. Both [12] and [2] use the followers-tofollowings ratio.…”

“…When the user selects the name of an existing anti spammer system, WEST automatically selects the set of features used by that system. WEST also allows for new features to be added by the user and presently there are 17 systems [1,2,4,[6][7][8][9][10][11][12][13][14][15][16][17][18][19] and 173 features. Each of those features can be grouped into four types: profile, activities, relations, and tweet contents.…”

Improved Micro-Blog Classification for Detecting Abusive Arabic Twitter Accounts

“…In [17], McCord et al used four different machine learning algorithms to identify spammer and non-spammer accounts on Twitter. The features were based on the user information and the content information.…”