A Survey of Spam Detection Methods on Twitter

Kabakuş, Abdullah Talha; Kara, Resul

doi:10.14569/ijacsa.2017.080305

Cited by 11 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section we only gave the some account based features. For further and deeply information about other types of features, [1] and [16] We performed account classification with using an ANN. We used four different activation functions and compared the efficiencies of different combinations of these activation functions.…”

Section: Materials and Methods (Materyal Ve Yöntemler)mentioning

confidence: 99%

“…By the same way, the tweets of and account or its relations an provide information about its authenticity or its fraud. For this reason, fake account detection are categorized as follows: Detecting with using account based features, detecting with using tweet based features, and detecting with relationship between users [1].…”

Section: Introduction (Gi̇ri̇ş)mentioning

confidence: 99%

“…For this purpose, we applied an ANN classifier to this problem and we evaluated performances of different activation functions. Also, we only used account based features because of their lightweight nature and that they allow to real-time detection [1], [15].…”

Section: Introduction (Gi̇ri̇ş)mentioning

confidence: 99%

See 2 more Smart Citations

Detecting Fake Twitter Accounts with using Artificial Neural Networks

Şimşek

Yilmaz

Kahriman

et al. 2018

AIS

View full text Add to dashboard Cite

Online Social Networks (OSNs) are great environments for sharing ideas, following news, advertising products etc., and they have been widely using by people. Although these advantages of OSNs, it is difficult to understand whether an account in OSNs really belongs to a person or organization. Through created fake accounts, unwanted content can spread over the social network. Therefore, the identification of fake accounts is an important problem. In this study, we applied Artificial Neural Network (ANN) classifier to this problem and we evaluated performances of different activation functions. According to the experimental results, use of artificial neural networks in detecting fake accounts yielded successful results. The use of various activation functions in different layers on the ANN significantly affects the results. In the literature, other classification methods have been widely used for detecting fake accounts and spammers on OSNs. To the best of our knowledge, there is no detailed study that classifies fake accounts using ANNs with different activation functions.

show abstract

Section: Materials and Methods (Materyal Ve Yöntemler)mentioning

confidence: 99%

Section: Introduction (Gi̇ri̇ş)mentioning

confidence: 99%

See 1 more Smart Citation

Detecting Fake Twitter Accounts with using Artificial Neural Networks

Şimşek

Yilmaz

Kahriman

et al. 2018

AIS

View full text Add to dashboard Cite

show abstract

“…The challenge in spam detection is that spammers often use dynamic words that are difficult to detect. Moreover, extracting important features for spam detection can be computationally expensive [26,27]; hence, we did not consider the cost in this study. Chu et al [8,9] applied machine-learning models and discovered that human accounts tended to interact with other human accounts via their tweets, retweets, mentions, hashtags, and direct messaging more often than bots.…”

Section: Literature Reviewmentioning

confidence: 99%

Feature selection using Benford’s law to support detection of malicious social media bots

Mbona

Eloff

2022

Information Sciences

View full text Add to dashboard Cite

“…In the literature, many methods are proposed for detecting spam accounts in the Twitter social network. The anomaly detection method (ADM), link analysis method (LAM), comparison and contracting method (CCM), deceptive information detection approach (DIDA), following and follower comparison analysis (FFCA), ensemble learning analysis (ELA), account creation time-based analysis (ACTA), using spammer detection tools (USDT), honeypot-based twitter spam detection (HTSD), short message analysis (SMA), trend-topic analysis (TTA), tweet-based spam detection (TSD), graph-based spam detection (GSD), and hybrid spam detection (HSD) are among these methods, which are commonly used approaches to detect spam ( Talha & Kara, 2017 ; Çıtlak, Dörterler & Doğru, 2019 ; Güngör, Ayhan Erdem & Doğru, 2020 ; Rupapara et al, 2021 ; Bouadjenek et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities

Atacak

Çıtlak

Doğru

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Background Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That’s why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Methods Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutions in spam detection, as in many application areas. For this purpose, a data set was created by collecting data on the twitter platform for spam detection. In the study, fuzzy logic-based classification approaches are suggested for spam detection. In the first stage of the proposed method, a data set with extracted attributes was obtained by applying normalization and crowdsourcing approaches to the raw data obtained from Twitter. In the next stage, as a process of the data preprocessing step, six attributes in the binary form in the data set were subjected to a rating-based transformation and combined with the other real-valued attribute to create a database to be used in spam detection. Classification process inputs were obtained by applying the fisher-score method, one of the commonly used filter-based methods, to the data set obtained in the second stage. In the last stage, the data were classified based on FL based approaches according to the obtained inputs. As FL approaches, four different Mamdani and Sugeno fuzzy inference systems based on interval type-1 and Interval Type-2 were used. Finally, in the classification phase, four different machine learning (ML) approaches including support vector machine (SVM), Bayesian point machine (BPM), logistic regression (LR) and average perceptron (Avr Prc) methods were used to test the effectiveness of these approaches in detecting spam. Results Experimental results were obtained by applying different FL and ML based approaches on the data set created in the study. As a result of the experiments, the Interval Type-2 Mamdani fuzzy inference system (IT2M-FIS) provided the highest performance with an accuracy of 0.955, a recall of 0.967, an F-score 0.962 and an area under the curve (AUC) of 0.971. However, it has been observed that FL-based spam models have a higher performance than ML-based spam models in terms of metrics including accuracy, recall, F-score and AUC values.

show abstract

A Survey of Spam Detection Methods on Twitter

Cited by 11 publications

References 53 publications

Detecting Fake Twitter Accounts with using Artificial Neural Networks

Detecting Fake Twitter Accounts with using Artificial Neural Networks

Feature selection using Benford’s law to support detection of malicious social media bots

Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities

Contact Info

Product

Resources

About