Rhetorical analysis is the process of examining how a speaker or writer uses language to communicate their ideas and persuade their audience. It involves analyzing the use of rhetorical devices such as imagery, figurative language, and tone, as well as the structure and organization of the text or speech.

Rhetorical Analysis Essay

            The article “Fake News Detection within Online Social Media using Supervised Artificial Intelligence Algorithms” was written by Feyza Altunbey Ozbay and Bilal Alatas, both affiliated with the Department of Computer Engineering at Istanbul Technical University in Turkey. Despite their different areas of focus, they both have extensive expertise in computer science, particularly in the fields of machine learning, data mining, natural language processing, and network analysis. As accomplished researchers, both authors have published numerous articles, and this publication is just one example of their work. The primary goal of the article is to address the issue of fake news and explore how artificial intelligence algorithms can be utilized to mitigate this problem. The article is written in an informative tone and is likely intended for software engineering professionals or employers at major media companies. Therefore, this article could be a valuable resource for software engineers, data scientists, or anyone interested in understanding how supervised machine learning algorithms can be used to combat the spread of fake news on social media.
                  This section is the abstract, which is the summary of the entire article consume into a paragraph. From the abstract we can already see the author is suggesting is a dangerous problem through using rhetorical strategies.  The use of words such as “dangerous,” “high content,” and “main challenge” contribute to the sense of concern surrounding the topic, while the proposed two-step method for identifying fake news provides a clear solution to the problem. The experimental evaluation of twenty-three intelligent classification methods provides evidence of the effectiveness of the proposed approach, which combines text analysis methods and supervised artificial intelligence algorithms. In summary, the author’s effective use of rhetorical strategies and supporting evidence emphasizes the need for addressing the issue of fake news in social media.

              The first section is the introduction, where the author begins by explaining the idea, they want to conduct an experiment on. The authors begin explaining the impact of development of social media on social interactions and the way people consume news. They point out the advantage of social media is easy to access but at the same time the authors also acknowledge things as fake news and misinformation is being spread and is being spread quickly. “The spread of low-quality news, namely fake news, have a negative effect on opinions of society and individual. Fake news is not only harmful to individuals and society, but also to businesses and governments.” They point out that fake news detection has become a significant research area and the authors propose a detection model that combines text analysis methods and supervised artificial intelligence algorithms to detect fake news in social media. The purpose of this section is to provide an overview of the problem and introduce the proposed solution that will be further detailed in the following sections.

              The second section is related works, this section provides an overview of various approaches proposed in the literature for detecting fake news. The purpose this section is to review various methods that have been proposed to detect fake news, including linguistic cue approaches, network analysis approaches, and machine learning techniques which can be seen on the chart above. The authors also mention different types of fake news, such as serious fabrication, large-scale hoaxes, and humorous fake news. They describe how some researchers have used satirical cues, conflicting viewpoints in social media, and emotional analysis to identify fake news. This section offers a comprehensive overview of the diverse range of approaches that have been developed to address the issue of detecting fake news, as well as the significant challenges faced by researchers in this field. By providing a detailed passage like this, the author demonstrates a high level of expertise in this area, thereby boosting the credibility of their writing.

                The third section is the models used by the authors and it presents a detailed explanation of the models that the authors have proposed to detect fake news in their experiment. The section outlines the three main steps of the proposed model: pre-processing, feature extraction, and supervised artificial intelligence algorithms. The authors begin by describing the pre-processing step, which involves filtering out redundant terms or characters, such as numbers and stop-words. This helps to ensure that the data set is clean and ready for analysis. Next, the authors explain the feature extraction step, which is used to reduce the dimension of the feature space. This is an important step because it helps to simplify the data set and make it more manageable for analysis. By reducing the dimension of the feature space, the authors can focus on the most important features that are most likely to be associated with fake news. Finally, the authors describe the supervised artificial intelligence algorithms that are used to analyze the fake news dataset. The authors have used twenty-three different algorithms in this study, all of which have been applied to the pre-processed and feature-extracted data set. Overall, the tone of this section is informative and straightforward, which helps to make the complex topic of fake news detection more accessible to a wider audience. The authors have provided an explanation of the twenty-three different algorithms that are used in their study, which demonstrates their expertise and knowledge of the subject matter. By doing so, they have added credibility to their research and have provided a valuable contribution to the field of fake news detection.

             The fourth section is the dataset, the purpose of this section is to present the experimental evaluations of intelligent classification algorithms for detecting fake news using three different datasets. The section provides details on the data sources, feature selection, and performance evaluation of 23 supervised artificial intelligence algorithms. The section reports the “accuracy”, “precision”, “recall”, and “F-measure” metrics of each algorithm on each dataset and compares their performance. This help to inform the audience about the performance of different algorithms for detecting fake news and to provide them with strong evidence about which algorithm performs better in each dataset. This not just allows the audience to make an informed decision when selecting an algorithm to use for detecting fake news but also increase the credibility of the article.

           In conclusion, the article “Fake News Detection within Online Social Media using Supervised Artificial Intelligence Algorithms” by Feyza Altunbey Ozbay and Bilal Alatas provides a overview of the issue of fake news and proposes a solution of using supervised artificial intelligence algorithms to detect fake news. The authors effectively used rhetorical strategies and provided evidence to emphasize the need for addressing this issue. The article also offers a thorough review of various approaches proposed in the literature for detecting fake news, and the authors’ proposed model is presented in a clear and informative manner. The dataset section provides strong evidence of the effectiveness of the proposed approach, which combines text analysis methods and supervised artificial intelligence algorithms. Overall, this article could be a valuable resource for software engineers, data scientists, or anyone interested in understanding how supervised machine learning algorithms can be used to combat the spread of fake news on social media.