A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification
Fake profile identification on social media platforms is essential for preserving a reliable online community. Previous studies have primarily used conventional classifiers for fake account identification on social networking sites, neglecting feature selection and class balancing to enhance perfor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taiwan Association of Engineering and Technology Innovation
2024-01-01
|
| Series: | Proceedings of Engineering and Technology Innovation |
| Subjects: | |
| Online Access: | https://ojs.imeti.org/index.php/PETI/article/view/13200 |
| _version_ | 1797337798913556480 |
|---|---|
| author | Swetha Chikkasabbenahalli Venkatesh Sibi Shaji Balasubramanian Meenakshi Sundaram |
| author_facet | Swetha Chikkasabbenahalli Venkatesh Sibi Shaji Balasubramanian Meenakshi Sundaram |
| author_sort | Swetha Chikkasabbenahalli Venkatesh |
| collection | DOAJ |
| description |
Fake profile identification on social media platforms is essential for preserving a reliable online community. Previous studies have primarily used conventional classifiers for fake account identification on social networking sites, neglecting feature selection and class balancing to enhance performance. This study introduces a novel multistage stacked ensemble classification model to enhance fake profile detection accuracy, especially in imbalanced datasets. The model comprises three phases: feature selection, base learning, and meta-learning for classification. The novelty of the work lies in utilizing chi-squared feature-class association-based feature selection, combining stacked ensemble and cost-sensitive learning. The research findings indicate that the proposed model significantly enhances fake profile detection efficiency. Employing cost-sensitive learning enhances accuracy on the Facebook, Instagram, and Twitter spam datasets with 95%, 98.20%, and 81% precision, outperforming conventional and advanced classifiers. It is demonstrated that the proposed model has the potential to enhance the security and reliability of online social networks, compared with existing models.
|
| first_indexed | 2024-03-08T09:19:48Z |
| format | Article |
| id | doaj.art-27fc8ca1f0aa4e29bd093683f05d9eb2 |
| institution | Directory Open Access Journal |
| issn | 2413-7146 2518-833X |
| language | English |
| last_indexed | 2024-03-08T09:19:48Z |
| publishDate | 2024-01-01 |
| publisher | Taiwan Association of Engineering and Technology Innovation |
| record_format | Article |
| series | Proceedings of Engineering and Technology Innovation |
| spelling | doaj.art-27fc8ca1f0aa4e29bd093683f05d9eb22024-01-31T12:57:47ZengTaiwan Association of Engineering and Technology InnovationProceedings of Engineering and Technology Innovation2413-71462518-833X2024-01-0110.46604/peti.2024.13200A Fake Profile Detection Model Using Multistage Stacked Ensemble ClassificationSwetha Chikkasabbenahalli Venkatesh0Sibi Shaji1Balasubramanian Meenakshi Sundaram2School of Computational Sciences & IT, Garden City University, Bangalore, IndiaSchool of Computational Sciences & IT, Garden City University, Bangalore, IndiaDepartment of Computer Science & Engineering, New Horizon College of Engineering, Bangalore, India Fake profile identification on social media platforms is essential for preserving a reliable online community. Previous studies have primarily used conventional classifiers for fake account identification on social networking sites, neglecting feature selection and class balancing to enhance performance. This study introduces a novel multistage stacked ensemble classification model to enhance fake profile detection accuracy, especially in imbalanced datasets. The model comprises three phases: feature selection, base learning, and meta-learning for classification. The novelty of the work lies in utilizing chi-squared feature-class association-based feature selection, combining stacked ensemble and cost-sensitive learning. The research findings indicate that the proposed model significantly enhances fake profile detection efficiency. Employing cost-sensitive learning enhances accuracy on the Facebook, Instagram, and Twitter spam datasets with 95%, 98.20%, and 81% precision, outperforming conventional and advanced classifiers. It is demonstrated that the proposed model has the potential to enhance the security and reliability of online social networks, compared with existing models. https://ojs.imeti.org/index.php/PETI/article/view/13200fake profileonline social networksstacked ensembleimbalanced datasetcost-sensitive learning |
| spellingShingle | Swetha Chikkasabbenahalli Venkatesh Sibi Shaji Balasubramanian Meenakshi Sundaram A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification Proceedings of Engineering and Technology Innovation fake profile online social networks stacked ensemble imbalanced dataset cost-sensitive learning |
| title | A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification |
| title_full | A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification |
| title_fullStr | A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification |
| title_full_unstemmed | A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification |
| title_short | A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification |
| title_sort | fake profile detection model using multistage stacked ensemble classification |
| topic | fake profile online social networks stacked ensemble imbalanced dataset cost-sensitive learning |
| url | https://ojs.imeti.org/index.php/PETI/article/view/13200 |
| work_keys_str_mv | AT swethachikkasabbenahallivenkatesh afakeprofiledetectionmodelusingmultistagestackedensembleclassification AT sibishaji afakeprofiledetectionmodelusingmultistagestackedensembleclassification AT balasubramanianmeenakshisundaram afakeprofiledetectionmodelusingmultistagestackedensembleclassification AT swethachikkasabbenahallivenkatesh fakeprofiledetectionmodelusingmultistagestackedensembleclassification AT sibishaji fakeprofiledetectionmodelusingmultistagestackedensembleclassification AT balasubramanianmeenakshisundaram fakeprofiledetectionmodelusingmultistagestackedensembleclassification |