Home »  

Attribution-NonCommercial-ShareAlike 4.0 International

Except where otherwise noted, content on this site is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.

 

Amara Boateng 

Professor Jonathan McVey

ENGL 21007 : Writing for Engineering May 3, 2023

‘

Rhetorical Analysis OF An Engineering Lab Report

The lab report, entitled “Fake news detection within online social media using supervised artificial intelligence algorithms,” aims to address the growing concern of fake news on social media. It was written by Feyza Altunbey Ozbay and Bilal Alatas, both of whom are affiliated with Firat University’s Department of Software Engineering in Turkey.  The report uses rhetorical strategies to establish the significance of the problem and present a proposed solution. The tone is impartial, neutral and written in a formal, technical language with an emphasis on outlining research and its findings rather than passing judgment. Researchers and professionals in the domains of software engineering, data science, and artificial intelligence who are interested in utilizing AI algorithms to detect fake news are most likely the report’s target audiences. Policymakers and social media platform managers worried about the proliferation of false information on their platforms may find the report of interest as well.

The report begins with an abstract section by highlighting the impact of the internet and social media on social interactions. The quote, “Along with the development of the Internet, the emergence and widespread adoption of the social media concept have changed the way news is formed and published” emphasizes the transformative impact of social media on the journalism sector, suggesting that traditional techniques of verifying news may no longer be enough in the age of social media. This sets the stage for a discussion of the fake news problem on social media, which occurs due to the ease with which false information may be spread. It highlighted the impact of social media on the creation and dissemination of news providing context for the emergence of the fake news problem on social media. The next evidence, “the fake news problem, despite being introduced for the first time very recently, has become an important research topic due to the high content of social media,” is intended to establish the significance of the problem and the need for a solution. The author(s) highlight the relatively recent emergence of the fake news problem on social media and how this problem has become a significant research topic due to the large volume of content on social media. This suggests that fake news is not just a minor issue, but a major problem that requires serious attention. This evidence highlights the harmful effects of fake news and strengthens the argument for the proposed model. Followed by the quote, “In this paper, a two-step method for identifying fake news on social media has been proposed, focusing on fake news” is to introduce the proposed method for identifying fake news on social media. It’s intended to establish the main focus and contribution of the paper while highlighting the two-step method for identifying fake news on social media using text mining and artificial intelligence algorithms. This suggests that the proposed method is a valuable contribution to addressing the fake news problem on social media. The introduction of the report begins by stating, “The last technological developments and the spread of the Internet have caused an enormous impact on social interactions. Social media has become an increasingly popular way of obtaining information for people. Additionally, people share their personal activities, interests, and opinions on different social media platforms.” The author highlights the growing popularity of social media and how it has changed the way people obtain and share information. This sets the context for the rest of the article and establishes the importance of the topic. The quote “In this study, a detection model containing two different steps has been proposed to detect fake news in social media. The proposed model is an approach that combines methods of text analysis and supervised artificial intelligence algorithms.” presents the proposed model for detecting fake news on social media, which combines text analysis methods and supervised artificial intelligence algorithms. The author is proposing a model that combines text analysis and supervised artificial intelligence algorithms to detect fake news on social media, which could help address the negative effects of fake news and improve the reliability of social media news. The quote “Various approaches have been proposed to detect fake news, such machine learning” (Source: Section II, Paragraph 1) established the need for a new approach to fake news detection. The authors provided a comprehensive review of existing research to demonstrate the limitations of current methods and the need for a more effective creditable approach and convince the reader of the research significancy.  

“Our proposed approach consists of a two-step process that combines text mining methods with supervised artificial intelligence (AI) algorithms.”(Source: Section III, Paragraph 1) meaning introducing their proposed solution is their priority with detailed explanations in order to establish the superiority of their approach. “The previously mentioned supervised artificial intelligence algorithms have been applied to the BuzzFeed Political News data set to predict whether the news is real or fake. TF is used to extract the feature from the data set. Table 5 shows the performance comparison for the different supervised artificial intelligence algorithms on the BuzzFeed Political News data set. Graphical representation of algorithm performances with respect to the accuracy, precision, recall, and F-measure metrics has been demonstrated in Fig. 4”. ( Section IV )  The purpose of using these evidence is to explain the methodology used by the authors to analyze the BuzzFeed Political News dataset, which involves the application of supervised artificial intelligence algorithms and the use of term frequency (TF) to extract features from the data set. Through analyzation of the quote is did show that the authors employed a rigorous and scientific approach in their analysis of the dataset. The use of supervised artificial intelligence algorithms and TF for feature extraction is a common practice in natural language processing and machine learning. The performance comparison table and graphical representation of algorithm performances provide a clear and detailed assessment of the effectiveness of each algorithm in detecting fake news. It did advance the author’s purpose and argument by establishing the credibility of their analysis and providing a foundation for their discussion of the results. The use of established methodologies adds weight to the authors’ conclusions and makes their findings more trustworthy. The quote “According to the obtained results, the best mean values in terms of accuracy, precision, and F-measure have been obtained from the Decision Tree algorithm. The best mean recall value as 1000 has been achieved by ZeroR, CVPS, and WIHW algorithms. (Section Vi) ” present the results of the authors’ analysis and to highlight the best performing algorithms in terms of accuracy, precision, recall, and F-measure, which shows that the Decision Tree algorithm performed the best overall, based on mean values of all evaluation metrics across all three datasets. The fact that the ZeroR, CVPS, and WIHW algorithms achieved the best mean recall value is notable, as recall is an important metric in detecting fake news. The result and discussions made has strengthened the authors’ argument by providing concrete evidence to support their conclusions. By highlighting the best performing algorithms, the authors are able to provide specific recommendations for future research and for the development of effective tools for detecting fake news.   The quote “In recent years, it has become difficult for users to access accurate and reliable information because of the increased amount of information on social media” (Section v). highlighted the problem of fake news and its impact on the accessibility of accurate and reliable information for social media users. The increasing amount of information on social media has made it more challenging for users to distinguish between real and fake news, leading to a potential decrease in trust and reliability of information sources. This has implications for individuals, organizations, and society as a whole.  The authors statement has establish the need for research on detecting fake news in social media. By highlighting the problem, the authors are demonstrating the relevance and importance of their research, as well as the potential impact it could have in addressing the issue. At the second part of the conclusion the author restated that “This combined model has been tested on three different real-world data set and evaluated according to accuracy, recall, precision, and F-measure values”(Section V). This statement illustrates and emphasizes that the proposed model has been tested and evaluated on real-world data sets using multiple metrics to determine its effectiveness in detecting fake news. By testing and evaluating the model using multiple metrics on real-world data sets, the authors have ensured that their proposed model is applicable in practical situations and provides a comprehensive evaluation of its performance. It has established  the validity and reliability of the proposed model by showing its effectiveness in detecting fake news using multiple evaluation metrics on real-world data sets, the authors have provided strong evidence of the usefulness of their proposed model for addressing the problem of fake news. The final quote “In future works, the current work may be improved by exploring new algorithms, hybridizing the current algorithms, integrating intelligent optimization algorithms for better results. Ensemble methods and different feature extraction methods may also be integrated for improving the performances of the models.” highlighted potential avenues for further research and improvement of the proposed model. The authors suggest several approaches that could be used to improve upon the proposed model, including exploring new algorithms, integrating intelligent optimization algorithms, and using ensemble methods and different feature extraction methods. And it has proved the authors’ commitment to further improving and refining their proposed model, as well as to encourage other researchers to explore new approaches and methods for detecting fake news in social media. By suggesting potential avenues for future research, the authors are advancing the field and contributing to the ongoing efforts to address the problem of fake news.           

  In conclusion, the lab report “Fake news detection within online social media using supervised artificial intelligence algorithms” uses rhetorical devices to convey the significance and importance of the topic. The author(s) use evidence to emphasize the negative effects of fake news, the impact of social media on the creation and dissemination of news, and the proposed method for identifying fake news on social media. This report provides valuable insight into the issue of fake news and proposes a solution using artificial intelligence algorithms.