A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers
During the last decades, the volume of multimedia content posted in social networks has grown exponentially and such information is immediately propagated and consumed by a significant number of users. In this scenario, the disruption of fake news providers and bot accounts for spreading propaganda...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9385071/ |
| _version_ | 1818730132528955392 |
|---|---|
| author | David Martin-Gutierrez Gustavo Hernandez-Penaloza Alberto Belmonte Hernandez Alicia Lozano-Diez Federico Alvarez |
| author_facet | David Martin-Gutierrez Gustavo Hernandez-Penaloza Alberto Belmonte Hernandez Alicia Lozano-Diez Federico Alvarez |
| author_sort | David Martin-Gutierrez |
| collection | DOAJ |
| description | During the last decades, the volume of multimedia content posted in social networks has grown exponentially and such information is immediately propagated and consumed by a significant number of users. In this scenario, the disruption of fake news providers and bot accounts for spreading propaganda information as well as sensitive content throughout the network has fostered applied research to automatically measure the reliability of social networks accounts via Artificial Intelligence (AI). In this paper, we present a multilingual approach for addressing the bot identification task in Twitter via Deep learning (DL) approaches to support end-users when checking the credibility of a certain Twitter account. To do so, several experiments were conducted using state-of-the-art Multilingual Language Models to generate an encoding of the text-based features of the user account that are later on concatenated with the rest of the metadata to build a potential input vector on top of a Dense Network denoted as <italic>Bot-DenseNet</italic>. Consequently, this paper assesses the language constraint from previous studies where the encoding of the user account only considered either the metadata information or the metadata information together with some basic semantic text features. Moreover, the <italic>Bot-DenseNet</italic> produces a low-dimensional representation of the user account which can be used for any application within the Information Retrieval (IR) framework. |
| first_indexed | 2024-12-17T22:56:55Z |
| format | Article |
| id | doaj.art-1ebb755a99db4bc6a0a8cbf21d5f538b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T22:56:55Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1ebb755a99db4bc6a0a8cbf21d5f538b2022-12-21T21:29:31ZengIEEEIEEE Access2169-35362021-01-019545915460110.1109/ACCESS.2021.30686599385071A Deep Learning Approach for Robust Detection of Bots in Twitter Using TransformersDavid Martin-Gutierrez0https://orcid.org/0000-0002-8824-8304Gustavo Hernandez-Penaloza1https://orcid.org/0000-0003-2177-6185Alberto Belmonte Hernandez2https://orcid.org/0000-0002-4009-2662Alicia Lozano-Diez3https://orcid.org/0000-0002-5918-8568Federico Alvarez4https://orcid.org/0000-0001-7400-9591Visual Telecommunication Applications Group, Signals, Systems and Radio Communications (SSR) Department, Universidad Politécnica de Madrid, Madrid, SpainVisual Telecommunication Applications Group, Signals, Systems and Radio Communications (SSR) Department, Universidad Politécnica de Madrid, Madrid, SpainVisual Telecommunication Applications Group, Signals, Systems and Radio Communications (SSR) Department, Universidad Politécnica de Madrid, Madrid, SpainAUDIAS–Audio Data Intelligence and Speech, Universidad Autónoma de Madrid, Madrid, SpainVisual Telecommunication Applications Group, Signals, Systems and Radio Communications (SSR) Department, Universidad Politécnica de Madrid, Madrid, SpainDuring the last decades, the volume of multimedia content posted in social networks has grown exponentially and such information is immediately propagated and consumed by a significant number of users. In this scenario, the disruption of fake news providers and bot accounts for spreading propaganda information as well as sensitive content throughout the network has fostered applied research to automatically measure the reliability of social networks accounts via Artificial Intelligence (AI). In this paper, we present a multilingual approach for addressing the bot identification task in Twitter via Deep learning (DL) approaches to support end-users when checking the credibility of a certain Twitter account. To do so, several experiments were conducted using state-of-the-art Multilingual Language Models to generate an encoding of the text-based features of the user account that are later on concatenated with the rest of the metadata to build a potential input vector on top of a Dense Network denoted as <italic>Bot-DenseNet</italic>. Consequently, this paper assesses the language constraint from previous studies where the encoding of the user account only considered either the metadata information or the metadata information together with some basic semantic text features. Moreover, the <italic>Bot-DenseNet</italic> produces a low-dimensional representation of the user account which can be used for any application within the Information Retrieval (IR) framework.https://ieeexplore.ieee.org/document/9385071/Artificial intelligencebot detectordeep learningfeature representationlanguage modelsmisinformation detection |
| spellingShingle | David Martin-Gutierrez Gustavo Hernandez-Penaloza Alberto Belmonte Hernandez Alicia Lozano-Diez Federico Alvarez A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers IEEE Access Artificial intelligence bot detector deep learning feature representation language models misinformation detection |
| title | A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers |
| title_full | A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers |
| title_fullStr | A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers |
| title_full_unstemmed | A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers |
| title_short | A Deep Learning Approach for Robust Detection of Bots in Twitter Using Transformers |
| title_sort | deep learning approach for robust detection of bots in twitter using transformers |
| topic | Artificial intelligence bot detector deep learning feature representation language models misinformation detection |
| url | https://ieeexplore.ieee.org/document/9385071/ |
| work_keys_str_mv | AT davidmartingutierrez adeeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT gustavohernandezpenaloza adeeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT albertobelmontehernandez adeeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT alicialozanodiez adeeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT federicoalvarez adeeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT davidmartingutierrez deeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT gustavohernandezpenaloza deeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT albertobelmontehernandez deeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT alicialozanodiez deeplearningapproachforrobustdetectionofbotsintwitterusingtransformers AT federicoalvarez deeplearningapproachforrobustdetectionofbotsintwitterusingtransformers |