Fame for sale: Efficient detection of fake Twitter followers

In the paper

“The conclusions of their investigation have shown that the metric used to evaluate the performance of the different classifiers changes the optimal distribution of the classes for the training set.”

What the sources say

• Supported

  The Conclusion (Section 10; page unavailable) says the best training-class distribution tends to be near the natural distribution when accuracy is the performance measure, but near a balanced distribution when AUC is used. This directly supports the claim that the evaluation metric affects the optimal training-class distribution. (LLM, conf=0.93)

  cites [34] [34] G. M. Weiss, F. Provost, Learning when training data are costly: the effect of class distribution on tree induction, Journal of Artificial Intelligence Research 19 (2003) 315-354. - source

In the paper

“Moreover, the optimal distribution has an oversampling of the minority class (there are also cases when the best classifier is obtained with an oversampling up to 90% of the minority class samples).”

What the sources say

• Partly supported

  Section 6.3 (page unavailable) reports that, for AUC, 11 of the 12 data sets whose optimal range excludes the natural distribution have more minority-class examples in that range. This supports the claim that increasing the minority-class share can be optimal. The cited 90% example is not established as the best classifier overall: the paper says it performs better at high true-positive rates in one example, while a balanced distribution has the highest AUC for that data set. (LLM, conf=0.85)

  cites [34] [34] G. M. Weiss, F. Provost, Learning when training data are costly: the effect of class distribution on tree induction, Journal of Artificial Intelligence Research 19 (2003) 315-354. - sourceExperimental — accuracy not yet measured

In the paper

“The authors exploit several characteristics that can be gathered crawling an account's details, both from its profile and timeline. For each investigated account, such characteristics are exploited in a Random Forest algorithm [23, 43], that outputs if the account is a spambot or not.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [23] [23] M. Hall, I. Witten, E. Frank, Data Mining: Practical Machine Learning Tools and Techniques, 3rd Edition, Morgan Kaufmann, 2011. -
• ?Could not verify

  The WEKA Workbench section describes software for applying classification algorithms, but it does not describe crawling account profiles or timelines to detect spambots. Searches for Random Forest and spambot account features found no passage in our copy establishing the specific method attributed to this source. (LLM, conf=0.76)

  cites [43] [43] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, I. H. Witten, The WEKA data mining software: an update, ACM SIGKDD explorations newsletter 11 (1) (2009) 10-18. - sourceExperimental — accuracy not yet measured

In the paper

“Sensitivity analysis, instead, aims at assessing the relative importance of the different features used to build a classification model [48].”

What the sources say

• Partly supported

  The Introduction (page unavailable) says global sensitivity analysis quantifies the relative importance of model input variables in determining an output. That supports the general purpose described, but the paper does not specifically address features used to build a classification model. (LLM, conf=0.86)

  cites [48] [48] A. Saltelli, Making best use of model evaluations to compute sensitivity indices, Computer Physics Communications 145 (2) (2002) 280-297. sourceExperimental — accuracy not yet measured

In the paper

“Our results show that most of the rules proposed by Media provide unsatisfactory performance in revealing fake followers, while features proposed in the past by Academia for spam detection provide good results.”

• Also stated in: § Contributions · p. 3 · plain

  “algorithms based on classification rules do not succeed in detecting the fake followers in our baseline dataset.”

In the paper

“The final result is a novel Class A classifier, general enough to thwart overfitting, lightweight thanks to the usage of the less costly features, and still able to correctly classify more than 95% of the accounts of the original training set.”

• Also stated in: § Contributions · p. 3 · plain

  “lightweight classifiers that make use of the less costly features, while still being able to correctly classify more than 95% of the accounts of our training dataset.”

In the paper

“Summarizing, independently from the typology of the account, the rules are almost always satisfied, leading to a severe flaw when dealing with fake followers detection.”

In the paper

“Indeed, the large majority of the accounts are recognized as humans, resulting in a high precision, accuracy around 0.5 and very low recall.”

In the paper

“The trained classifiers obtained their best results on a balanced distribution of humans and fake followers.”

In the paper

“As shown, only three rules obtained a value higher than 0.6, namely: (1) the threshold of at least 30 followers, (2) the threshold of at least 50 tweets, and (3) the use of a userID in at least one tweet.”

In the paper

“in our dataset, fake followers accounts almost never tweet from API (instead, they use Twitter.com to tweet), whereas human accounts have posted at least once from outside the website.”

In the paper

“Although obtaining very good results in detecting the real human accounts, the algorithm achieves a poor fake follower account detection.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“As an example, all rules by Van Den Beld have accuracy and precision close to 0.5 or a very low recall.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [11] [11] Stateofsearch.com, How to recognize Twitterbots: 7 signals to look out for., http://goo.gl/YZbVf, Last checked 23/07/15 (August 2012). -

In the paper

“If we consider as useful the rules and features that have an information gain value higher than 0.5, we observe that, even if many rules exhibit a very low I gain , their 'feature' version becomes much more interesting: for example, rules 18, 20, 21 and 22 have an evident increase in their information gain when used as features.”

In the paper

“Coincidentally, we have that the best performing rules also show the highest Pcc values, namely their satisfaction is more strongly related to the belonging class.”

In the paper

“We contacted their customer service, but we were answered that 'how the respective criteria are measured is rather an internal information'.”

In the paper

“As expected by the definition of MCC , such rules also exhibit a combination of high accuracy, precision, and recall.”

In the paper

“The exception is rule 6, '0 tweets': as a rule, it has an information gain value of 0.02, but when considered as a feature (i.e., number of tweets) it obtains 0.621.”

In the paper

“Also, we observe that 'tweet from API' has an MCC of -0.779, meaning that it is strictly related to the class of the account, but by an inverse factor:”

In the paper

“This poor performance is also expressed by a F-Measure close to 0.1 and by the low MCC value.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“Observing the results in Table 11, we can identify several promising features: 'number of tweets' (already noticed in Section 4), 'ratio between friends and followersˆ2', 'bidirectional links ratio' and 'API ratio'.”

In the paper

“This test set therefore comprises a broad range of accounts created during the nine years since Twitter's advent.”

In the paper

“Observing the tree structure of our J48 classifier, instead, low values for this feature characterize fake followers, compared with higher values that indicate human accounts in our baseline dataset.”

In the paper

“The reduced error pruning with 50 folds produces a classifier that has MCC dropping from 0.966 to 0.866.”

In the paper

“For example, the tree that does not use that feature, pruned with subtree raising confidence of 0.25, requires 101 nodes, whereas the tree that uses it requires only 33 nodes.”

In the paper

“Then, all the classifiers of the previous sections are classifiers of Class B , with the exception of the classifier with the feature set of Yang et al. [2], that belongs to Class C .”

What the sources say

• ?Not checked — no full text of the sourcecites Yang et al. [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“The decision tree obtained with the feature set of Stringhini et al. [8] has 22 leaves, 43 nodes, and a height of 7, whereas the best feature is the friends/(followersˆ2) ratio that places at the root.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“More than 72% of the fake followers in our training dataset have a URL ratio lower than 0.05, oppositely to 14% of human accounts.”

In the paper

“Indeed, in this experiment SVM scores only slightly worse than RF, D and J48, and better than AB.”

In the paper

“All the rules and features considered in this study fall into one of the three aforementioned categories, as reported in Table 14.”

In the paper

“The decision tree with the feature set of Yang et al. [2] has 17 leaves, 33 nodes and a height of 8, with the bi-directional link ratio as the root.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“Furthermore, we clearly observe that the pruned version of Stringhini et al. [8] reduces its recall of 0.017, while the one of Yang et al. [2] only drops of 0.004”

What the sources say

• ?Not checked — no full text of the sourcecites Stringhini et al. [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not checked — no full text of the sourcecites Yang et al. [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“For this reason, we trained and evaluated the proposed Class A classifiers, which achieve overall good performances, while only exploiting cost-efficient features.”

In the paper

“Overall, the results of this experiment show that, even reducing the features, it is possible to have a detection rate higher than 0.95 (as in the last lines of Table 13, for [8] and [2], respectively).”

What the sources say

• ?Not checked — no full text of the sourcecites Stringhini et al. [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not checked — no full text of the sourcecites Yang et al. [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“A further interesting observation is that both the classifiers employ a set of features that includes both features proposed by the grey literature for fake detection, which we introduced in Section 4, and by Academia for spam and bot detection, as detailed in Section 5.”

In the paper

“The results in Table 13 show an evident decrease in accuracy , precision and recall for the less pruned trees (subtree raising 0.25 and reduced error 3 folds), as well as for both F-Measure and AUC , and an even noticeable decrease of the MCC measure.”

What the sources say

• ?Not checked — no full text of the sourcecites Yang et al. [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“It is worth noting that the Class A classifier with BN outperforms the Class C competitor, noticeably obtaining an increase in all the metrics, but the AUC .”

In the paper

“Such simpler trees generally use subsets of the feature set, still maintaining very good performance on our BAS dataset.”

In the paper

“Concerning the complexity of the two decision trees obtained with the J48 algorithm, they are comparable, since both of them are composed by 31 nodes and 16 leaves and they have a height of 7.”

In the paper

“Timeline-based ( Class B ) features have been shown to be less time-demanding, while still effective”

In the paper

“In the two validation experiments, AB and BN noticeably switch their performances: the Adaptive Boosting algorithm raises its accuracy of 0.1 and its precision of around 0.08, outperforming the Bayesian Network-based one.”

In the paper

“Notably, none of the features is clearly dominant: all the 19 Class A features give a significant contribution to the detection of fake Twitter followers.”

In the paper

“The SVM classifier, instead, proves to be extremely effective, being the second best classifier when validated against random sampled accounts, and still performing very well against sampled Obama followers.”

In the paper

“With this final outcome, we were able to achieve detection rates comparable with the best of breed classifiers, whereas these latter necessitate overhead-demanding features.”

In the paper

“Indeed, while in Tables 12 and 16 almost all the considered classifiers achieved comparable performances, here we can see some major differences.”

In the paper

“AB and BN obtain lower results for both accuracy and precision, but still a noticeably high recall”

In the paper

“However, relationships-based ( Class C ) features are more demanding in terms of data to be downloaded and, consequently, they require a significant analysis time, making them unsuitable for analyses on massive amounts of followers.”

In the paper

“Observing the validation against the random sampled accounts, we can see that the five Class A classifiers obtain an accuracy above 0.9, a precision close to (when not much higher than) 0.9 and a recall above 0.94”

In the paper

“The RF, D, and J48 classifiers obtain results that are comparable for the two test sets, with an accuracy greater than 0.9 and a precision close to 0.87, with a reduction of only 0.025 on average.”

In the paper

“We can finally observe that the AUC metric is always very high and that does not consistently reflect the real performances obtained by the five classifiers, as the F-measure and the MCC actually do.”

In the paper

“Also the RF classifier looses 0.4 of accuracy and a considerable 0.1 in precision”

In the paper

“The results in [12], however, lack a validation phase.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“Similarly, if the practice of buying fake followers is adopted by malicious accounts, as spammers, it can act as a way to post more authoritative messages and launch more effective advertising campaigns [6].”

What the sources say

• ?Not checked — no full text of the sourcecites [6] [6] C. Castillo, M. Mendoza, B. Poblete, Information credibility on Twitter, in: Proceedings of the 20th international conference on World Wide Web, ACM, 2011, pp. 675-684. - source

In the paper

“To the best of our knowledge, however, despite fake followers constitute a widespread phenomenon with both economical and social impacts, in the literature the topic has not been deeply investigated yet.”

In the paper

“However, such rules are usually paired neither with analytic algorithms to aggregate them, nor with validation mechanisms.”

In the paper

“However, the criteria used for the analysis are not publicly disclosed and just partially deductible from information available on their web sites.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [13] [13] Statuspeople.com, Status People Fakers, http://goo.gl/0Jpky, Last checked 23/07/15. -
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [14] [14] SocialBakers, Fake follower check, http://goo.gl/chWn0, Last checked 23/07/15. -
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [15] [15] Twitteraudit, How many of your followers are real?, www.twitteraudit.com, Last checked 23/07/15. -

In the paper

“While the company website provides eight criteria to evaluate the fakeness degree of the followers of a certain account, it omits details on how to combine such criteria to classify the accounts.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [14] [14] SocialBakers, Fake follower check, http://goo.gl/chWn0, Last checked 23/07/15. -

In the paper

“Actually, this happens because Pcc evaluates the linear dependency between two variables that assume very similar values, namely the output of the rule and the class, while the Pcc* considers variables with more heterogeneous values.”

In the paper

“Thus, we can derive that the rule is based on a right assumption (for example, the use of hashtags), but the rule definition is too simple to be effective: the algorithm proposed by [12] is simply too naive for the complex task of fake accounts detection in Twitter.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“We acknowledge that our fake followers dataset is just illustrative, and not exhaustive, of all the possible existing sets of fake followers.”

In the paper

“Moreover, there are situations where some predictive models perform better than others, even having a lower accuracy [38].”

What the sources say

• Not checked yetcites [38] [38] D. M. W. Powers, Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation, International Journal of Machine Learning Technologies 2 (1) (2011) 37-63. -

In the paper

“In [12] it is detailed an algorithm to evaluate an account based on some of its public features. The cited algorithm has enough details to be reproducible: it assigns human/active and bot/inactive scores and classifies an account considering the gap between the sum of the two scores.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“This is because a single rule - or feature - alone may not perform well in classifying fake and human accounts, but it may improve the detection if used in combination with other ones.”

In the paper

“We consider as 'certified humans' all the 469 accounts out of the 574 followers that successfully completed the CAPTCHA.”

In the paper

“However, MAUs can be assimilated neither to a random sample of Twitter accounts nor to the followers of a given account.”

In the paper

“Furthermore, MCC is considered the unbiased version of the F-Measure , since it uses all the four elements of the confusion matrix [38].”

What the sources say

• Not checked yetcites [38] [38] D. M. W. Powers, Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation, International Journal of Machine Learning Technologies 2 (1) (2011) 37-63. -

In the paper

“This last set has been sampled (with confidence level 95% and confidence interval 2.5), leading to a final set of 1488 accounts, that have been subject to a manual verification to determine the nature of their profiles and tweets.”

In the paper

“The FakeFollowerCheck tool analyzes the followers of an account and considers them likely fake when the criteria listed in Table 4 are satisfied.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [14] [14] SocialBakers, Fake follower check, http://goo.gl/chWn0, Last checked 23/07/15. -

In the paper

“Both of them propose a list of features to be extracted from manually classified datasets of accounts.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“This means that the only way to check a user's follow/unfollow behavior (rule 7) is to continuously monitor full friends and followers complete lists. The same applies with respect to the measurement of the delay experienced when a user follows (and replies to) other users (rule 6).”

In the paper

“Only accounts labeled as humans by both the sociologists have been included in the E13 dataset.”

In the paper

“Camisani-Calzolari [12] carried out a series of tests over samples of Twitter followers of Romney and Obama, for the last US presidential elections, as well as for popular Italian politicians.”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [12] [12] Camisani-Calzolari M. (digitalevaluations), Analysis of Twitter followers of the US Presidential Election candidates: Barack Obama and Mitt Romney (August 2012). -

In the paper

“In 2013, the Twitter staff conjectured that the number of 'false or spam accounts should represent less than 5% of our MAUs' (where MAUs refer to monthly active users) [35].”

What the sources say

• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [35] [35] Twitter Inc., Twitter's IPO filing, http://www.sec.gov/Archives/edgar/data/1418091/000119312513390321/d564001ds1.htm, Last checked 23/07/15 (Oct 2013). -

In the paper

“Such feature sets are then used to train and test machine learning classifiers in order to distinguish between humans and spammers.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“We have decided to include AB in our work, since it is considered one of the most effective machine learning algorithms for classification tasks [39].”

What the sources say

• Not checked yetcites [39] [39] J. Friedman, T. Hastie, R. Tibshirani, The elements of statistical learning, Vol. 1, Springer Series in Statistics, 2001. -

In the paper

“Without the original training set, we were unable to reproduce the same classifier, but we picked the five features and used them to train a set of classifiers with our BAS dataset.”

In the paper

“The study presented in [8] focuses on spambot detection.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“9. following rate : this metric reflects the speed at which an accounts follows other accounts. Spammers usually feature high values of this rate.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“The authors of [2] observed that Twitter spammers often modify their behavior in order to evade existing spam detection techniques.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“In 'glassbox' models, such as Decision Trees and Regression Models, the inner structure of the models can be understood by humans, also providing insights on how the classifiers identify fake accounts [39].”

What the sources say

• Not checked yetcites [39] [39] J. Friedman, T. Hastie, R. Tibshirani, The elements of statistical learning, Vol. 1, Springer Series in Statistics, 2001. -

In the paper

“Even if the proposed features have been originally designed for spam detection, here, for the first time, we consider them to spot another category of Twitter accounts, i.e., the fake followers.”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source
• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“2. spambots have sent less than 20 tweets;”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“3. the content of spambots' tweets exhibits the so-called message similarity ;”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“Instead, here we evaluate how those features, which proved to be quite robust against evasion techniques adopted by spammers, perform in detecting fake Twitter followers.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“Then, we have used a 10-fold cross validation [23] to estimate the performances of each obtained classifier.”

What the sources say

• Not checked yetcites [23] [23] M. Hall, I. Witten, E. Frank, Data Mining: Practical Machine Learning Tools and Techniques, 3rd Edition, Morgan Kaufmann, 2011. -

In the paper

“Beyond the features directly available from the account profile lookup, the authors propose some graph-, automation-, and timing-based features.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“4. spambots have a high tweets containing URLs ratio ( URL ratio );”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“1. age of the account (this feature also appears in [28]): the more an account is aged, the more it could be considered a good one;”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source
• ?Not checked — no full text of the sourcecites [28] [28] K. Lee, J. Caverlee, S. Webb, Uncovering social spammers: social honeypots + machine learning, in: SIGIR Conference on Research and Development in Information Retrieval, ACM, 2010, pp. 435-442. - source

In the paper

“total tweets 5. spambots have a high friends ( followersˆ2 ) ratio value (i.e., lower ratio values mean legitimate users).”

What the sources say

• ?Not checked — no full text of the sourcecites [8] [8] G. Stringhini, C. Kruegel, G. Vigna, Detecting spammers on social networks, in: 26th Annual Computer Security Applications Conference, ACSAC '10, ACM, 2010, pp. 1-9. - source

In the paper

“Thus, they suggested to consider some new features, making evasion more difficult for spammers.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“However, as claimed by the same authors, they are less robust with regards to evasion techniques and thus we decided not to include them in our evaluation.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“In other words, to get the total time, one should not consider the sum of the time needed for each of the three cost classes, but just the most costly one.”

In the paper

“The total time required to collect all data depends on the category that requires more time, i.e., the relationship one.”

In the paper

“A similar behavior has been observed for the average neighbor's tweets feature, that has been found to be lower for spammers in [2], but higher for our fake followers.”

What the sources say

• ?Not checked — no full text of the sourcecites [2] [2] C. Yang, R. Harkreader, G. Gu, Empirical evaluation and new design for fighting evolving Twitter spammers, Information Forensics and Security, IEEE Transactions on 8 (8) (2013) 1280-1293. - source

In the paper

“These initial observations highlight a behavioral difference between a spam account and a fake follower. In particular, fake followers appear to be more passive compared to spammers and they do not make use of automated mechanisms for posting their tweets, as spammers usually do.”

In the paper

“a classifier that uses a certain feature set belongs to the class of the more expensive feature.”

In the paper

“By capturing the nature of the social ties between an account and its neighbors, this feature is intrinsically harder to beat than those based on simpler characteristics, like, e.g., other information in the account's profile.”

In the paper

“This represents an unbiased sample of all the currently available (i.e., not closed, banned or suspended) Twitter accounts.”

In the paper

“we can consider the use of the most expensive Class B or even Class C features to have stronger evidences about the more suspicious followers.”

In the paper

“From the results shown in Table 13, we conclude that the bidirectional link ratio is an important feature for fake follower detection: even if not essential, it is extremely effective for the detection process.”

In the paper

“This experiment resembles the practical application scenario of the proposed classifier, since it investigates a sample of a single account's followers, in this case a major politician.”

In the paper

“Information fusion is a technique aimed at leveraging the predictive power of several different models in order to achieve a combined prediction accuracy which is better than the predictions of the single models [47].”

What the sources say

• ?Not checked — no full text of the sourcecites [47] [47] C. W. Chase Jr, Composite forecasting: combining forecasts for improved accuracy, Journal of Business Forecasting Methods & Systems 19 (2) (2000) 2. -

In the paper

“Automatically labeling the sampled accounts as humans would result in an error of at most 5%, still allowing an overall correct validation of our classifiers.”

In the paper

“meaning that only few fake followers are left behind, but a considerably higher number of human accounts are classified as fake followers”