2017 International Conference on Computer Science and Engineering (UBMK) 2017
DOI: 10.1109/ubmk.2017.8093420
|View full text |Cite
|
Sign up to set email alerts
|

Twitter fake account detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
39
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 78 publications
(40 citation statements)
references
References 6 publications
1
39
0
Order By: Relevance
“…To develop a fake account detection system, a new offline NB model from Sparks MLlib was trained and tested using TwFakeUsr data set. The accuracy and F-measure values were obtained 89.16% and 88.65%, respectively, which were similar to results in the work of Erşahin et al 12 The real-time performance of the system was also tested during the selection of 2000 tweets. The system classified 38 accounts as fake and filtered out the corresponding bogus tweets.…”
Section: Impact Of Real-time Fake Account Detection Systemsupporting
confidence: 85%
See 3 more Smart Citations
“…To develop a fake account detection system, a new offline NB model from Sparks MLlib was trained and tested using TwFakeUsr data set. The accuracy and F-measure values were obtained 89.16% and 88.65%, respectively, which were similar to results in the work of Erşahin et al 12 The real-time performance of the system was also tested during the selection of 2000 tweets. The system classified 38 accounts as fake and filtered out the corresponding bogus tweets.…”
Section: Impact Of Real-time Fake Account Detection Systemsupporting
confidence: 85%
“…A Spark cluster generally is composed of a cluster manager (master) and worker nodes. On the other side, NB model can be easily parallelized as it requires only one pass over data set . In order to evaluate the cluster effect of Spark, experiments were performed using four different clustering configurations, ie, (i) one master node, (ii) one master node + one worker node servers, (iii) one master node + two worker node servers, and (iv) one master node + four worker node servers.…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…The [25] show the way to detect the profiles in twitter if they fake profile or normal one by using technology called (Entropy Minimization Discretization (EMD)) on numerical features and analyzed the results of the Naïve Bayes algorithm).…”
Section: Methods Used For Fake Profile Detectionmentioning
confidence: 99%