Automated Fake News Detection by LSTM Enabled with Optimal Feature Selection

Automated Fake News Detection by LSTM Enabled with Optimal Feature Selection S. Hannah Nithya Department of Computer Science and Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai, Tamil Nadu, India Arun Sahayadhas Department of Computer Science and Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai, Tamil Nadu, India

Fake news plays a major role by broadcasting misinformation, which influences people’s knowledge or perceptions and distorts their decision-making and awareness. Online forums and social media have stimulated the broadcast of fake news by embedding it with truthful information. Thus, fake news has evolved into the main challenge of better impact in the information-driven community for intense fakesters. The detection of fake news articles that is generally found by considering the quality of the information in their news feeds under uncertain authenticity calls for automated tools. However, designing such tools is a major problem because of the multiple faces of fakesters. This paper offers a new text-analytics-driven method for detecting fake news to reduce the risks impacted by the consumption of fake news. The methodology for improved fake news detection focusses on four phases: (a) pre-processing, (b) feature extraction, (c) optimal feature selection and (d) classification. The pre-processing of the text data will be initially done by stop word removal, blank space removal and stemming. Further, the feature extraction is performed by term frequency-inverse document frequency, and grammatical analysis is done using mean, Q25, Q50, Q75, Max, Min and standard deviation. Then, the optimal feature selection is developed, which minimises the number of input variables. It is intended to reduce the number of input variables to improve the model’s performance by minimising the computational cost of modelling. An improved meta-heuristic algorithm called successive position-based barnacles mating optimisation is used for optimal feature selection and classification. As the main contribution, the influence of deep learning is employed, which employs optimised long short-term memory. Finally, the result shows the superiority in terms of different significant measures by the proposed model over other methods for fake news detection experimentally done on a publicly available benchmark dataset.
05 28 2022 09 2022 2250036 10.1142/S0219649222500368 10.1142/S0219649222500368 https://www.worldscientific.com/doi/10.1142/S0219649222500368 https://www.worldscientific.com/doi/pdf/10.1142/S0219649222500368 10.1109/ACCESS.2019.2959234 10.1257/jep.31.2.211 10.1016/j.procs.2020.01.072 10.1109/MC.2017.104 10.1007/s11633-018-1124-0 10.1109/LSP.2020.3008087 10.1016/j.eswa.2020.113503 10.1007/s11633-015-0912-z 10.1162/neco.1997.9.8.1735 10.1016/j.eswa.2020.113584 10.1109/SAMI50585.2021.9378650 10.1016/j.chb.2017.11.034 10.1109/TMM.2016.2617078 10.1007/s11227-020-03294-y 10.1016/j.cogsys.2019.12.005 Neural Computing and Applications Kaliyar RK 1 33 2 2021 10.1007/s11042-020-10183-2 10.1109/ACCESS.2019.2907327 Cybernetics and Information Technologies Kumar CA 5 9 1 2009 10.1016/j.advengsoft.2016.01.008 10.1016/j.jjimei.2020.100007 10.1016/j.jastp.2019.105062 10.1016/j.physa.2019.123174 10.1016/j.asoc.2021.107393 10.1007/s11633-019-1216-5 10.1016/j.asoc.2020.106983 10.1007/s10588-018-09280-3 10.1145/3137597.3137600 Proceedings of the Iberian Languages Evaluation Forum Spalenza MA 2021 10.1049/iet-bmt.2017.0160 10.1016/j.comcom.2020.03.031 10.1016/j.engappai.2019.103330 10.1109/TKDE.2009.175 10.1126/science.aap9559 10.1007/s00500-016-2474-6 10.1007/s13278-019-0580-z 10.1016/j.eswa.2020.114090 10.1109/TNNLS.2014.2382123 IEEE Transactions on Neural Networks and Learning Systems Wu P 2609 31 7 2020 10.26599/TST.2018.9010139 10.1016/j.ejor.2019.06.022