Venue & metadata

• Journal/Proceedings: Proceedings of the International Joint Conference on Neural Networks
• Volume: 2021-July
• Note: Cited by: 17
• Author keywords: Authorship Attribution; Cooperative Computing; Federated Learning; Natural Language Processing; Text classification

Abstract

Authorship Attribution (AA) is currently applied in several applications, among which fraud detection and anti-plagiarism checks: this task can leverage stylometry and Natural Language Processing techniques. In this work, we explored some strategies to enhance the performance of an AA task for the automatic detection of false and misleading information (e.g., fake news). We set up a text classification model for AA based on stylometry exploiting recurrent deep neural networks and implemented two learning tasks trained on the same collection of fake and real news, comparing their performances: one is based on Federated Learning architecture, the other on a centralized architecture. The goal was to discriminate potential fake information from true ones when the fake news comes from heterogeneous sources, with different styles. Preliminary experiments show that a distributed approach significantly improves recall with respect to the centralized model. As expected, precision was lower in the distributed model. This aspect, coupled with the statistical heterogeneity of data, represents some open issues that will be further investigated in future work. © 2021 IEEE.

Keywords

Classification (of information) GS Deep neural networks GS Network architecture GS Recurrent neural networks GS Text processing GS Authorship attribution GS Cooperative computing GS Federated learning GS Fraud detection GS Heterogeneous sources GS Learning approach GS Misleading informations GS Performance GS Stylometry GS Text classification GS Natural language processing systems GS

Links & artifacts

DOI Publisher Copy BibTeX Download .bib

{"key"=>"Marulli2021", "type"=>"Conference paper", "bibtex"=>"@conference{Marulli2021,\n  author = {Marulli, Fiammetta and Balzanella, Antonio and Campanile, Lelio and Iacono, Mauro and Mastroianni, Michele},\n  title = {Exploring a Federated Learning Approach to Enhance Authorship Attribution of Misleading Information from Heterogeneous Sources},\n  year = {2021},\n  journal = {Proceedings of the International Joint Conference on Neural Networks},\n  volume = {2021-July},\n  doi = {10.1109/IJCNN52387.2021.9534377},\n  type = {Conference paper}\n}\n", "author"=>"Marulli, Fiammetta and Balzanella, Antonio and Campanile, Lelio and Iacono, Mauro and Mastroianni, Michele", "author_array"=>[{"first"=>"Fiammetta", "last"=>"Marulli", "prefix"=>"", "suffix"=>""}, {"first"=>"Antonio", "last"=>"Balzanella", "prefix"=>"", "suffix"=>""}, {"first"=>"Lelio", "last"=>"Campanile", "prefix"=>"", "suffix"=>""}, {"first"=>"Mauro", "last"=>"Iacono", "prefix"=>"", "suffix"=>""}, {"first"=>"Michele", "last"=>"Mastroianni", "prefix"=>"", "suffix"=>""}], "author_0_first"=>"Fiammetta", "author_0_last"=>"Marulli", "author_0_prefix"=>"", "author_0_suffix"=>"", "author_1_first"=>"Antonio", "author_1_last"=>"Balzanella", "author_1_prefix"=>"", "author_1_suffix"=>"", "author_2_first"=>"Lelio", "author_2_last"=>"Campanile", "author_2_prefix"=>"", "author_2_suffix"=>"", "author_3_first"=>"Mauro", "author_3_last"=>"Iacono", "author_3_prefix"=>"", "author_3_suffix"=>"", "author_4_first"=>"Michele", "author_4_last"=>"Mastroianni", "author_4_prefix"=>"", "author_4_suffix"=>"", "title"=>"Exploring a Federated Learning Approach to Enhance Authorship Attribution of Misleading Information from Heterogeneous Sources", "year"=>"2021", "journal"=>"Proceedings of the International Joint Conference on Neural Networks", "volume"=>"2021-July", "doi"=>"10.1109/IJCNN52387.2021.9534377", "url"=>"https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116453728&doi=10.1109%2fIJCNN52387.2021.9534377&partnerID=40&md5=1a66f680877de40ba6525a359903672e", "abstract"=>"Authorship Attribution (AA) is currently applied in several applications, among which fraud detection and anti-plagiarism checks: this task can leverage stylometry and Natural Language Processing techniques. In this work, we explored some strategies to enhance the performance of an AA task for the automatic detection of false and misleading information (e.g., fake news). We set up a text classification model for AA based on stylometry exploiting recurrent deep neural networks and implemented two learning tasks trained on the same collection of fake and real news, comparing their performances: one is based on Federated Learning architecture, the other on a centralized architecture. The goal was to discriminate potential fake information from true ones when the fake news comes from heterogeneous sources, with different styles. Preliminary experiments show that a distributed approach significantly improves recall with respect to the centralized model. As expected, precision was lower in the distributed model. This aspect, coupled with the statistical heterogeneity of data, represents some open issues that will be further investigated in future work. © 2021 IEEE.", "author_keywords"=>"Authorship Attribution; Cooperative Computing; Federated Learning; Natural Language Processing; Text classification", "keywords"=>"Classification (of information); Deep neural networks; Network architecture; Recurrent neural networks; Text processing; Authorship attribution; Cooperative computing; Federated learning; Fraud detection; Heterogeneous sources; Learning approach; Misleading informations; Performance; Stylometry; Text classification; Natural language processing systems", "publication_stage"=>"Final", "source"=>"Scopus", "note"=>"Cited by: 17"}
    

Suggested citation

Marulli, F., Balzanella, A., Campanile, L., Iacono, M., & Mastroianni, M. (2021). Exploring a Federated Learning Approach to Enhance Authorship Attribution of Misleading Information from Heterogeneous Sources [Conference paper]. Proceedings of the International Joint Conference on Neural Networks, 2021-July. https://doi.org/10.1109/IJCNN52387.2021.9534377