Topic-aware neural attention network for malicious social media spam detection
Social media platforms, such as Facebook and X (formally known as Twitter), have become indispensable tools in today's society because they facilitate social discussion and information sharing. This feature makes social networks more attractive for spammers who intentionally spread fake message...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824012389 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524892322758656 |
|---|---|
| author | Maged Nasser Faisal Saeed Aminu Da’u Abdulaziz Alblwi Mohammed Al-Sarem |
| author_facet | Maged Nasser Faisal Saeed Aminu Da’u Abdulaziz Alblwi Mohammed Al-Sarem |
| author_sort | Maged Nasser |
| collection | DOAJ |
| description | Social media platforms, such as Facebook and X (formally known as Twitter), have become indispensable tools in today's society because they facilitate social discussion and information sharing. This feature makes social networks more attractive for spammers who intentionally spread fake messages, post malicious links and spread rumours. Recently, several machine learning methods have been introduced for social network malicious spam classification. However, most existing methods generally rely on handcrafted features and traditional embedding models, which are relatively less effective. Therefore, inspired by the success of the neural attention network, we propose an interactive neural attention-based method for malicious spam detection by integrating long short-term memory (LSTM), topic modelling, and the BERT technique. In the proposed approach, first, we employed the LSTM encoder, which was integrated with the Twitter latent Dirichlet allocation (LDA) model via an interactive attention mechanism to jointly learn local content and global topic representations. Second, to further learn the contextualized features of texts, the model was further integrated with the BERT technique. Last, the Softmax function was then applied at the output layer for the final spam classification. A series of experiments were conducted utilizing two real-world datasets to evaluate the model. Using dataset 1, the proposed model outperformed the baseline techniques, with average improvements in recall, precision, and F1 and accuracies of 17.54 %, 6.19 %, 11.91 %, and 12.27 %, respectively. In addition, the proposed model performed well for the second dataset and obtained average gains of 11.81 %, 4.38 %, 8.12, and 7.42 in terms of recall, precision, F1, and accuracy, respectively. |
| format | Article |
| id | doaj-art-5a7ae3bf0aa24c90844d6d1836fbca23 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-5a7ae3bf0aa24c90844d6d1836fbca232025-01-18T05:03:41ZengElsevierAlexandria Engineering Journal1110-01682025-01-01111540554Topic-aware neural attention network for malicious social media spam detectionMaged Nasser0Faisal Saeed1Aminu Da’u2Abdulaziz Alblwi3Mohammed Al-Sarem4Computer & Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaCollege of Computing and Digital Technology, Birmingham City University, Birmingham B4 7XG, UK; Corresponding author.Department of Computer Science, Hassan Usman Katsina Polytechnic, Katsina State, NigeriaDepartment of Computer Science, Applied College, Taibah University, Saudi ArabiaCollege of Computer Science and Engineering, Taibah University, Medina, Saudi ArabiaSocial media platforms, such as Facebook and X (formally known as Twitter), have become indispensable tools in today's society because they facilitate social discussion and information sharing. This feature makes social networks more attractive for spammers who intentionally spread fake messages, post malicious links and spread rumours. Recently, several machine learning methods have been introduced for social network malicious spam classification. However, most existing methods generally rely on handcrafted features and traditional embedding models, which are relatively less effective. Therefore, inspired by the success of the neural attention network, we propose an interactive neural attention-based method for malicious spam detection by integrating long short-term memory (LSTM), topic modelling, and the BERT technique. In the proposed approach, first, we employed the LSTM encoder, which was integrated with the Twitter latent Dirichlet allocation (LDA) model via an interactive attention mechanism to jointly learn local content and global topic representations. Second, to further learn the contextualized features of texts, the model was further integrated with the BERT technique. Last, the Softmax function was then applied at the output layer for the final spam classification. A series of experiments were conducted utilizing two real-world datasets to evaluate the model. Using dataset 1, the proposed model outperformed the baseline techniques, with average improvements in recall, precision, and F1 and accuracies of 17.54 %, 6.19 %, 11.91 %, and 12.27 %, respectively. In addition, the proposed model performed well for the second dataset and obtained average gains of 11.81 %, 4.38 %, 8.12, and 7.42 in terms of recall, precision, F1, and accuracy, respectively.http://www.sciencedirect.com/science/article/pii/S1110016824012389Spam detectionTopic modellingAttention neural networkMalicious detectionBidirectional encoder representations from transformers (BERT)Online social network |
| spellingShingle | Maged Nasser Faisal Saeed Aminu Da’u Abdulaziz Alblwi Mohammed Al-Sarem Topic-aware neural attention network for malicious social media spam detection Alexandria Engineering Journal Spam detection Topic modelling Attention neural network Malicious detection Bidirectional encoder representations from transformers (BERT) Online social network |
| title | Topic-aware neural attention network for malicious social media spam detection |
| title_full | Topic-aware neural attention network for malicious social media spam detection |
| title_fullStr | Topic-aware neural attention network for malicious social media spam detection |
| title_full_unstemmed | Topic-aware neural attention network for malicious social media spam detection |
| title_short | Topic-aware neural attention network for malicious social media spam detection |
| title_sort | topic aware neural attention network for malicious social media spam detection |
| topic | Spam detection Topic modelling Attention neural network Malicious detection Bidirectional encoder representations from transformers (BERT) Online social network |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824012389 |
| work_keys_str_mv | AT magednasser topicawareneuralattentionnetworkformalicioussocialmediaspamdetection AT faisalsaeed topicawareneuralattentionnetworkformalicioussocialmediaspamdetection AT aminudau topicawareneuralattentionnetworkformalicioussocialmediaspamdetection AT abdulazizalblwi topicawareneuralattentionnetworkformalicioussocialmediaspamdetection AT mohammedalsarem topicawareneuralattentionnetworkformalicioussocialmediaspamdetection |