Ensembles to Detect Fake News – An Approach Based on Specialized Classifiers

• Patrick Antunes dos Santos IME
• Paulo Márcio Souza Freire IME
• Ronaldo Ribeiro Goldschmidt IME

Resumo

The growing spread of Fake News is a consequence of the popularization of digital media as tools that facilitate the propagation and consumption of information. Ensemble-based approaches to detect this harmful type of news have shown promising performance. Despite their ability to combine machine learning classifiers to achieve more robust results, so far, these approaches have been limited to traditional classifiers (i.e., classifiers that can be applied to problems other than Fake News detection, such as decision trees, K-NN, SVM, etc...). Hence, the present work proposes Ensembles that use, in addition to the traditional ones, classifiers specifically designed to detect Fake News. Preliminary experiments with two datasets showed evidence that the proposed Ensembles have the potential to overcome those that exclusively use traditional classifiers.

Palavras-chave: Fake News Detection, Machine Learning, Ensemble, Social Networks

Referências

Herley Shaori Al-Ash, Mutia Fadhila Putri, Petrus Mursanto, and Alhadi Bustamam. 2019. Ensemble Learning Approach on Indonesian Fake News Classification. ICICOS 2019 - 3rd International Conference on Informatics and Computational Sciences: Accelerating Informatics and Computational Research for Smarter Society in The Era of Industry 4.0, Proceedings (2019). https://doi.org/10.1109/ICICoS48119.2019.8982409

Ranojoy Barua, Rajdeep Maity, Dipankar Minj, Tarang Barua, and Ashish Kumar Layek. 2019. F-NAD: An Application for Fake News Article Detection using Machine Learning Techniques. 2019 IEEE Bombay Section Signature Conference, IBSSC 2019 2019Januar (2019), 0–5. https://doi.org/10.1109/IBSSC47189.2019.8973059

Nicolo Bonettini, Edoardo Daniele Cannas, Sara Mandelli, Luca Bondi, Paolo Bestagini, and Stefano Tubaro. 2021. Video Face Manipulation Detection Through Ensemble of CNNs. (2021), 5012–5019. https://doi.org/10.1109/icpr48806.2021.9412711

Mohamed K. Elhadad, Kin Fun Li, and Fayez Gebali. 2020. Detecting Misleading Information on COVID-19. IEEE Access 8 (2020), 165201–165215. https://doi.org/10.1109/access.2020.3022867 arxiv:D7

Paulo Freire and Ronaldo Goldschmidt. 2019. Uma introdução ao combate automático às fake news em redes sociais virtuais. In Tópicos de Gerenciamento de Dados e Informação. SBC, Fortaleza, CE, Brazil, 38–67. https://doi.org/10.5753/sbc.6251.1

Paulo Freire and Ronaldo Goldschmidt. 2022. Fake News Detection Based on Explicit and Implicit Signals of a Hybrid Crowd: Proposal, Impacts and Perspectives. In Anais Estendidos do XXVIII Simpósio Brasileiro de Sistemas Multimídia e Web (Curitiba). SBC, Porto Alegre, RS, Brasil, 27–30. https://doi.org/10.5753/webmedia_estendido.2022.224573.

Parvathy Ganesh, Lekshmi Priya, and R Nandakumar. 2021. Fake News Detection - A Comparative Study of Advanced Ensemble Approaches. (2021), 1003–1008. https://doi.org/10.1109/icoei51242.2021.9453061

Emmanuel Goldschmidt, Ronaldo e Passos. 2015. Data mining: Conceitos, técnias, algoritmos, orientações e aplicações. Gulf Professional Publishing

Yin Fu Huang and Po Hong Chen. 2020. Fake news detection using an ensemble learning model based on Self-Adaptive Harmony Search algorithms. Expert Systems with Applications 159 (2020), 113584. https://doi.org/10.1016/j.eswa.2020.113584 arxiv:D3

Rohit Kumar Kaliyar, Anurag Goswami, and Pratik Narang. 2019. Multiclass Fake News Detection using Ensemble Machine Learning. Proceedings of the 2019 IEEE 9th International Conference on Advanced Computing, IACC 2019 (2019), 103–107. https://doi.org/10.1109/IACC48062.2019.8971579

Sawinder Kaur, Parteek Kumar, and Ponnurangam Kumaraguru. 2020. Automating fake news detection system using multi-level voting model. Soft Computing 24, 12 (2020), 9049–9069. https://doi.org/10.1007/s00500-019-04436-y arxiv:D19

Mohammad Zubair Khan and Omar Hussain Alhazmi. 2020. Study and analysis of unreliable news based on content acquired using ensemble learning (prevalence of fake news on social media). International Journal of Systems Assurance Engineering and Management 11, s2 (2020), 145–153. https://doi.org/10.1007/s13198-020-01016-4 arxiv:D20

Sachin Kumar, Rohan Asthana, Shashwat Upadhyay, Nidhi Upreti, and Mohammad Akbar. 2020. Fake news detection using deep learning models: A novel approach. Transactions on Emerging Telecommunications Technologies 31, 2 (2020), 1–23. https://doi.org/10.1002/ett.3767 arxiv:D13

John Joy Kurian, Deborah Zenobia Rachael Menezes, Avinash Ronanki, Gaurang Sharma, Sandeep Krishna Prasad, Ashish Chouhan, and Ajinkya Prabhune. 2021. EnFVe: An Ensemble Fact Verification Pipeline. (2021), 80–89. https://doi.org/10.1109/wiiat50758.2020.00016

Songqian Li, Kun Ma, Xuewei Niu, Yufeng Wang, Ke Ji, Ziqiang Yu, and Zhenxiang Chen. 2019. Stacking-based ensemble learning on low dimensional features for fake news detection. Proceedings - 21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019 (2019), 2730–2735. https://doi.org/10.1109/HPCC/SmartCity/DSS.2019.00383. arxiv:D2

Ana Carolina Lorena, João Gama, and Katti Faceli. 2011. Inteligência Artificial: uma abordagem de aprendizado de máquina. Grupo Gen - LTC

Atik Mahabub. 2020. A robust technique of fake news detection using Ensemble Voting Classifier and comparison with other classifiers. SN Applied Sciences 2 (2020), 1–9. Issue 4. https://doi.org/10.1007/s42452-020-2326-y

Igor Maffei Libonati Maia, Marcelo Pereira de Souza, Flávio Roberto Matias da Silva, Paulo Márcio Souza Freire, and Ronaldo Ribeiro Goldschmidt. 2021. A Sentiment-Based Multimodal Method to Detect Fake News. In Proceedings of the Brazilian Symposium on Multimedia and the Web (Belo Horizonte, Minas Gerais, Brazil) (WebMedia ’21). Association for Computing Machinery, New York, NY, USA, 213–216. https://doi.org/10.1145/3470482.3479467

Priyanka Meel, Puneet Chawla, Sahil Jain, and Utkarsh Rai. 2020. Web Text Content Credibility Analysis using Max Voting and Stacking Ensemble Classifiers. Proceedings - 2020 Advanced Computing and Communication Technologies for High Performance Applications, ACCTHPA 2020 (2020), 157–161. https://doi.org/10.1109/ACCTHPA49271.2020.9213234 arxiv:D21

Palagati Bhanu Prakash, Mandi Pavan Kumar, Ganjikunta VenkataManaswini, and K. M. Mehata. 2019. Fake data analysis and detection using ensembled hybrid algorithm. Proceedings of the 3rd International Conference on Computing Methodologies and Communication, ICCMC 2019Iccmc (2019), 890–897. https://doi.org/10.1109/ICCMC.2019.8819741 arxiv:D6

Harita Reddy, Namratha Raj, Manali Gala, and Annappa Basava. 2020. Text-mining-based Fake News Detection Using Ensemble Methods. International Journal of Automation and Computing 17, 2 (2020), 210–221. https://doi.org/10.1007/s11633-019-1216-5 arxiv:D16

Saarthak Sangamnerkar, R. Srinivasan, M. R. Christhuraj, and Rajeev Sukumaran. 2020. An ensemble technique to detect fabricated news article using machine learning and natural language processing techniques. 2020 International Conference for Emerging Technology, INCET 2020June (2020). https://doi.org/10.1109/INCET49848.2020.9154053 arxiv:D8

Kai Shu, Amy Sliva, Suhang Wang, Jiliang Tang, and Huan Liu. 2017. Fake News Detection on Social Media: A Data Mining Perspective. SIGKDD Explor. Newsl. 19, 1 (Sept. 2017), 22–36. https://doi.org/10.1145/3137597.3137600

W Z R W Shv, R I Xvhuv, Qdpho Dqg, Xvlqj Vnohduq, L Q Wkrq, and Phdvxuhv Vxfk. 2021. $ QDO VLV RI (QVHPEOH / HDUQLQJ 0RGHOV IRU, GHQWLI LQJ 6SDP RYHU 6RFLDO 1HWZRUNV XVLQJ. (2021), 713–718

Paulo Márcio Souza Freire, Flávio Roberto Matias da Silva, and Ronaldo Ribeiro Goldschmidt. 2021. Fake news detection based on explicit and implicit signals of a hybrid crowd: An approach inspired in meta-learning. Expert Systems with Applications 183 (2021), 115414. https://doi.org/10.1016/j.eswa.2021.115414

Ting Su, Craig Macdonald, and Iadh Ounis. 2019. Ensembles of recurrent networks for classifying the relationship of fake news titles. SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information RetrievalJune (2019), 893–896. https://doi.org/10.1145/3331184.3331305 arxiv:D1

Gustavo Testoni, Marcelo Souza, Paulo Márcio Freire, and Ronaldo Goldschimidt. 2021. Um Método Linguístico que combina Polaridade, Emoção e Aspectos Gramaticais para Detecção de Fake News em Inglês. In Anais do X Brazilian Workshop on Social Network Analysis and Mining (Evento Online). SBC, Porto Alegre, RS, Brasil, 151–162. https://doi.org/10.5753/brasnam.2021.16133

Soroush Vosoughi, Deb Roy, and Sinan Aral. 2018. The spread of true and false news online. Science 359, 6380 (2018), 1146–1151. https://doi.org/10.1126/science.aap9559 arXiv: [link]

Patrick Wang, Rafael Angarita, and Ilaria Renna. 2018. Is This the Era of Misinformation Yet: Combining Social Bots and Fake News to Deceive the Masses. In Companion Proceedings of the The Web Con 2018 (Lyon, France) (WWW ’18). International World Wide Web Con Steering Committee, Republic and Canton of Geneva, Switzerland, 1557–1561. https://doi.org/10.1145/3184558.3191610