Machine Learning for the Detection of Spam in Twitter Networks

Wang, Alex Hai

doi:10.1007/978-3-642-25206-8_21

Cited by 14 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Menggunakan algoritme Random Forest dengan presisi sebesar 95.7% dan F-measure sebesar 95.7%. Prototipe deteksi akun spam pada Twitter dibangun oleh Wang (2012). Studi ini menunjukkan bahwa bayesian classifier menunjukkan kinerja yang baik dibandingkan classifier lainnya dalam mendeteksi akun spam pada Twitter.…”

Section: Pendahuluanunclassified

Deteksi Spam pada Twitter Menggunakan Algoritme Naïve Bayes

Wahyuningtyas

Sitanggang

Khotimah

2020

J Ilmu Komput Agri-Inf

View full text Add to dashboard Cite

Di era berkembangnya penggunaan Internet, Twitter merupakan salah satu layanan jejaring sosial yang sering digunakan sebagai alat komunikasi yang saling menghubungkan antar pengguna. Selain itu Twitter juga dimanfaatkan sebagai media untuk promosi, kampanye politik, dan sarana protes. Twitter dihadapkan pada berbagai masalah seperti gangguan privasi pengguna dan spam pada Twitter. Dengan adanya masalah spam, perlu dilakukan klasifikasi untuk tweet spam dan bukan spam. Penelitian ini bertujuan untuk mendeteksi tweet spam dan bukan spam. Hal tersebut dapat dilakukan dengan klasifikasi, terdapat berbagai macam metode klasifikasi, salah satu metode dalam data mining untuk mengklasifikasikan spam dan bukan spam adalah Naïve Bayes. Naïve Bayes banyak digunakan karena kesederhanaan algoritme dan mudah untuk diimplementasikan. Penelitian ini mengumpulkan data spam dari Twitter dengan mengidentifikasi terlebih dahulu akun yang diduga sebagai spammer. Penelitian ini menggunakan 70% data latih dan 30% data uji dengan metode klasifikasi Naïve Bayes. Data Twitter yang diperoleh merupakan data teks yang masih banyak mengandung kata-kata yang tidak baku, sehingga dibutuhkan tahap praproses, tahap yang dilakukan adalah tokenizing, filtering, normalisasi kata, stemming. Akurasi hasil klasifikasi tweet spam dan bukan spam adalah 95.57%. Kata Kunci: klasifikasi spam, Naïve Bayes, text mining, Twitter.

show abstract

Section: Pendahuluanunclassified

Deteksi Spam pada Twitter Menggunakan Algoritme Naïve Bayes

Wahyuningtyas

Sitanggang

Khotimah

2020

J Ilmu Komput Agri-Inf

View full text Add to dashboard Cite

show abstract

“…Their results showed that the Random Forest algorithm has the best performance. Wang [21] indicated that Naive Bayesian has better classification results than the Neural Network, Decision Tree, SVM and k-NN on the dataset he collected.…”

Section: A Spammer Detection Approachesmentioning

confidence: 99%

A Spammer Identification Method for Class Imbalanced Weibo Datasets

2019

View full text Add to dashboard Cite

Nowadays, Weibo has become a significant and popular information sharing platform in China. Meanwhile, spammer identification has been a big challenge for it. To mitigate the damage caused by spammers, classification algorithms from machine learning have been applied to distinguish spammers and non-spammers. However, most of the previous studies overlook the class imbalance problem of real-world data. In this paper, by analyzing the characteristics of spammers in Weibo, we select microblog content similarity, the average number of links, and the other 12 features to construct a comprehensive feature vector never seen before. Considering the existence of imbalance problems in spammer identification, an ensemble learning method is used to combine multiple base classifiers for improving the learning performance. During the training stage of base learners, fuzzy-logic-based oversampling and cost-sensitive support vector machine are considered to tackle imbalanced data at both data and algorithmic levels. The experimental results demonstrate that compared with the existing state-of-the-art methods, the recall rate of our proposed approach increases by 6.5% and reaches the precision value of 87.53% when used to deal with real-world Weibo datasets we collected.

show abstract

“…They implemented a logistic regression classifier and crawl URLs as they are submitted to web services to determine whether the URLs direct to spam. Much preliminary work (Benevenuto et al, 2010;Lee et al, 2010;Stringhini et al, 2010;Wang, 2010;Wang, 2012) relies on account features including the number of followers and friends, text similarities between tweets, URL ratios, and account creation dates, although most of these features can be easily manipulated by spammers. That is why works have emerged recently that try to extract features that are most difficult to simulate.…”

Section: Previous Workmentioning

confidence: 99%

Detecting malicious tweets in trending topics using a statistical analysis of language

Martínez-Romo

Araujo

2013

Expert Systems with Applications

164

View full text Add to dashboard Cite

a b s t r a c tTwitter spam detection is a recent area of research in which most previous works had focused on the identification of malicious user accounts and honeypot-based approaches. However, in this paper we present a methodology based on two new aspects: the detection of spam tweets in isolation and without previous information of the user; and the application of a statistical analysis of language to detect spam in trending topics. Trending topics capture the emerging Internet trends and topics of discussion that are in everybody's lips. This growing microblogging phenomenon therefore allows spammers to disseminate malicious tweets quickly and massively. In this paper we present the first work that tries to detect spam tweets in real time using language as the primary tool. We first collected and labeled a large dataset with 34 K trending topics and 20 million tweets. Then, we have proposed a reduced set of features hardly manipulated by spammers. In addition, we have developed a machine learning system with some orthogonal features that can be combined with other sets of features with the aim of analyzing emergent characteristics of spam in social networks. We have also conducted an extensive evaluation process that has allowed us to show how our system is able to obtain an F-measure at the same level as the best state-ofthe-art systems based on the detection of spam accounts. Thus, our system can be applied to Twitter spam detection in trending topics in real time due mainly to the analysis of tweets instead of user accounts.

show abstract

Machine Learning for the Detection of Spam in Twitter Networks

Cited by 14 publications

References 7 publications

Deteksi Spam pada Twitter Menggunakan Algoritme Naïve Bayes

Deteksi Spam pada Twitter Menggunakan Algoritme Naïve Bayes

A Spammer Identification Method for Class Imbalanced Weibo Datasets

Detecting malicious tweets in trending topics using a statistical analysis of language

Contact Info

Product

Resources

About