{"id":3033,"date":"2022-04-08T00:57:44","date_gmt":"2022-04-08T06:57:44","guid":{"rendered":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/?p=3033"},"modified":"2022-04-08T15:28:57","modified_gmt":"2022-04-08T21:28:57","slug":"bnnetxtreme-an-enhanced-methodology-for-bangla-fake-news-detection-online","status":"publish","type":"post","link":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/2022\/04\/08\/bnnetxtreme-an-enhanced-methodology-for-bangla-fake-news-detection-online\/","title":{"rendered":"BNnetXtreme: An enhanced methodology for Bangla fake news detection online"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\"><strong>Introductio<\/strong>n<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Reading news online has become more common in Bangladesh, displacing the traditional technique of staying up to date with current events by reading printed copies of newspapers sent to one&#8217;s doorstep every morning. As a result of this fact, the number of online news portals has significantly increased as they adapt to the modern approach of maximizing profit, the potential of which has been highlighted rapidly. Even well-known and well-known newspaper companies in Bangladesh, on the other hand, utilize misleading and fraudulent headlines to attract traffic to their websites. In 2015, millions of Bangladeshis shared a news story on a popular online news portal alerting them that Abdur Razzak, their favorite actor, had died. Nonetheless, a small number of people may have picked up on the fact that the actor is dead in the latest film he was working on, rather than in real life [5]. People\u2019s panic lasted weeks, but the practice of publishing satire and fake news with an impressive methodology of making the news appear true in order to boost website tra\ufb00ic skyrocketed at times.&nbsp;Even though Bangladesh publishes over 1000 newspapers online every day, the inundation of false and satirical news has made finding real news challenging. The fake and satirical news portals are often found to be filled with malicious intentions\u2014having both increasing the number of visitors and stealing the visitor\u2019s personal data to sell to third-party organizations.<\/p>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img decoding=\"async\" width=\"640\" height=\"400\" data-src=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/the-diplomat_Joy.jpeg\" alt=\"\" class=\"wp-image-3034 lazyload\" data-srcset=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/the-diplomat_Joy.jpeg 640w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/the-diplomat_Joy-300x188.jpeg 300w\" data-sizes=\"(max-width: 640px) 100vw, 640px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 640px; --smush-placeholder-aspect-ratio: 640\/400;\" \/><figcaption>Bangladesh fights with fake news [source: Daily Star]<\/figcaption><\/figure><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Over the years, Natural Language Processing, a branch of Artificial Intelligence, has played an increasingly important role in comprehending written languages and delivering on-demand, useful solutions to respective problem domains, particularly in the detection of fake news. While using machine learning techniques to detect fake and satirical news in English is admirable, there has been minimal success in Bangla news. A recent study developed a Deep Neural Network architecture termed BNnet (Imran et al., 2020) to predict Bangla fake news demonstrating substantial performance, in line with the development necessary in Bangla news. However, there is still potential for improvement when it comes to detecting fake news using various deep learning architectures. We contribute to the following in this project:<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Propose a novel methodology for Bangla fake news detection&nbsp;<\/li><li>Demonstrate a promising and improved detection performance of Bangla fake news by providing a comparative performance analysis among the different classifiers used<\/li><\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">We used both embedding-based and transformer-based models to achieve our goal, with a strong emphasis on BERT Bangla [1]. We used a total of five evaluation metrics to assess the models: Accuracy, Precision, Recall, F1 Score, and Area Under the ROC Curve (AUC).<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Dataset we used<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Data was gathered from numerous Bangla news portals via web scraping. We started with a list of 43 Bangla news portal websites, 25 of which are legitimate, reputable, and verified news portals, and 18 of which are satirical and fake news portals. A set of sample Bangla news is provided below:<\/p>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-large\"><img decoding=\"async\" width=\"1024\" height=\"447\" data-src=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-1024x447.png\" alt=\"\" class=\"wp-image-3043 lazyload\" data-srcset=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-1024x447.png 1024w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-300x131.png 300w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-768x335.png 768w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-1536x670.png 1536w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-2048x893.png 2048w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/Screen-Shot-2022-04-08-at-1.04.22-AM-1568x684.png 1568w\" data-sizes=\"(max-width: 1024px) 100vw, 1024px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 1024px; --smush-placeholder-aspect-ratio: 1024\/447;\" \/><figcaption>Fig 1. Bangla Fake News Samples <\/figcaption><\/figure><\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Experimentation<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Our experiment is split into two parts: one uses embedding-based models such as word2vec [8], fastText [7], and GloVe [6], and the other uses BERT [9], a transformer-based model. Both of these steps have two sub-steps that must be completed for the experiment to be completed. The following figure 2 shows the proposed methodology of this experiment.<\/p>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img decoding=\"async\" width=\"610\" height=\"616\" data-src=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/image-4.png\" alt=\"\" class=\"wp-image-3035 lazyload\" data-srcset=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/image-4.png 610w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/image-4-297x300.png 297w, https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-content\/uploads\/sites\/115\/2022\/04\/image-4-150x150.png 150w\" data-sizes=\"(max-width: 610px) 100vw, 610px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 610px; --smush-placeholder-aspect-ratio: 610\/616;\" \/><figcaption>Fig 2. Proposed Methodology for Bangla Fake News Detection<\/figcaption><\/figure><\/div>\n\n\n\n<p class=\"has-text-align-left wp-block-paragraph\">At first, we have collected and extracted the data from various authentic and fake news portal of Bangladesh. Next, we have preprocessed data using Denoising, Normalization, and Stemming techniques to be able to use the data for training the machine learning models. Keeping the training and testing ratio as 80:20, we further then applied both pre-trained embedding algorithms and pre-trained BERT algorithms to detect the Bangla fake news. After implementing the system, we finally perform an analysis of the performance.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Results<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Our results demonstrate that transformer based (BERT models) performs better than embedding based algorithms in detection of Bangla fake news. As we have used both Multilingual based BERT and Bangla based BERT, we have found that the Bangla based BERT performs better than multilingual BERT. The multilingual based BERT model provides an accuracy score of 87% for Bangla fake news detection. However, the Bangla BERT based model produces an accuracy score of 91% while the Area Under Curve (AUC) score of 98%. Lastly, based on all the analysis, evaluation metrics, and performance, it can be said that the newly proposed BNnetXtreme demonstrated a significantly improved performance in detecting Bangla fake news, and the BERT Bangla base classifier is found to be the best.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Conclusion<\/h3>\n\n\n\n<p class=\"has-normal-font-size wp-block-paragraph\">The citizens of Bangladesh witness fake and misleading news as they browse the internet every day. Recently, numerous incidents took place that made people victims of identity theft, losing money due to investing in fake endorsed businesses, becoming participants of communal violence, etc. Thus, fake news in the context of Bangladesh is significantly important to take into consideration for advanced research and investigation to give users a safe space in online news portals that might potentially be misleading, fake, or malicious. Furthermore, to provide the policymakers of Bangladesh to control and monitor the online space in line with mitigating the public risk and influence led by fake and misleading news. In this project, we have thus studied and experimented with a proposed methodology that can detect Bangla fake news in order to contribute to the community that is fighting fake news every day.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">References<\/h3>\n\n\n\n<p class=\"has-small-font-size wp-block-paragraph\">[1] Sagor Sarker, 2020, BanglaBERT: Bengali Mask Language Model for Bengali Language Understanding, URL {https:\/\/github.com\/sagorbrur\/bangla-bert}, accessed on Feb 10, 2021.<\/p>\n\n\n\n<p class=\"has-small-font-size wp-block-paragraph\">[2] Hossain, E., Kaysar, N., Joy, J. U., Md, A. Z., Rahman, M., &amp; Rahman, W. (2022). A Study Towards Bangla Fake News Detection Using Machine Learning and Deep Learning. In&nbsp;<em>Sentimental Analysis and Deep Learning<\/em>&nbsp;(pp. 79-95). Springer, Singapore.<\/p>\n\n\n\n<p class=\"has-small-font-size wp-block-paragraph\">[3] George, M. Z. H., Hossain, N., Bhuiyan, M. R., Masum, A. K. M., &amp; Abujar, S. (2021, July). Bangla Fake News Detection Based On Multichannel Combined CNN-LSTM. In&nbsp;<em>2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)<\/em>&nbsp;(pp. 1-5). IEEE.<\/p>\n\n\n\n<p class=\"has-small-font-size wp-block-paragraph\">[4] Adib, Q. A. R., Mehedi, M. H. K., Sakib, M. S., Patwary, K. K., Hossain, M. S., &amp; Rasel, A. A. (2021, October). A Deep Hybrid Learning Approach to Detect Bangla Fake News. In&nbsp;2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)&nbsp;(pp. 442-447). IEEE.<\/p>\n\n\n\n<p class=\"has-small-font-size wp-block-paragraph\">[5] Al Imran, A., Wahid, Z., &amp; Ahmed, T. (2020, December). BNnet: A Deep Neural Network for the Identification of Satire and Fake Bangla News. In the International Conference on Computational Data and Social Networks (pp. 464-475). Springer, Cham.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">[6] Pennington, J., Socher, R., &amp; Manning, C. D. (2014, October). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532-1543).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">[7] Joulin, A., Grave, E., Bojanowski, P., Douze, M., J\u00e9gou, H., &amp; Mikolov, T. (2016). Fasttext. zip: Compressing text classification models. arXiv preprint arXiv:1612.03651.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">[8] Church, Kenneth Ward. &#8220;Word2Vec.&#8221; Natural Language Engineering 23.1 (2017): 155-162.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">[9] Devlin, J., Chang, M. W., Lee, K., &amp; Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Introduction Reading news online has become more common in Bangladesh, displacing the traditional technique of staying up to date with current events by reading printed copies of newspapers sent to one&#8217;s doorstep every morning. As a result of this fact, the number of online news portals has significantly increased as they adapt to the modern &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/2022\/04\/08\/bnnetxtreme-an-enhanced-methodology-for-bangla-fake-news-detection-online\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;BNnetXtreme: An enhanced methodology for Bangla fake news detection online&#8221;<\/span><\/a><\/p>\n","protected":false},"author":438,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[15],"tags":[],"class_list":["post-3033","post","type-post","status-publish","format-standard","hentry","category-cpsc-329-602-w22","entry"],"featured_image_src":null,"featured_image_src_square":null,"author_info":{"display_name":"Zaman Wahid","author_link":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/author\/zaman-wahid\/"},"_links":{"self":[{"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/posts\/3033","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/users\/438"}],"replies":[{"embeddable":true,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/comments?post=3033"}],"version-history":[{"count":7,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/posts\/3033\/revisions"}],"predecessor-version":[{"id":3049,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/posts\/3033\/revisions\/3049"}],"wp:attachment":[{"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/media?parent=3033"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/categories?post=3033"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wpsites.ucalgary.ca\/isec-601-f21\/wp-json\/wp\/v2\/tags?post=3033"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}