Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models

Röchert, Daniel; Neubaum, German; Stieglitz, Stefan

doi:10.1007/978-3-030-61841-4_8

Cited by 4 publications

(2 citation statements)

References 22 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then the classification efficiency was assessed using the following metrics: Precision, Recall, and F1-score. A new and more advanced approach to text classification using one CNN and two LSTM layers was described in [ 27 ].…”

Section: Related Workmentioning

confidence: 99%

On the development of an information system for monitoring user opinion and its role for the public

et al. 2022

View full text Add to dashboard Cite

Social media services and analytics platforms are rapidly growing. A large number of various events happen mostly every day, and the role of social media monitoring tools is also increasing. Social networks are widely used for managing and promoting brands and different services. Thus, most popular social analytics platforms aim for business purposes while monitoring various social, economic, and political problems remains underrepresented and not covered by thorough research. Moreover, most of them focus on resource-rich languages such as the English language, whereas texts and comments in other low-resource languages, such as the Russian and Kazakh languages in social media, are not represented well enough. So, this work is devoted to developing and applying the information system called the OMSystem for analyzing users’ opinions on news portals, blogs, and social networks in Kazakhstan. The system uses sentiment dictionaries of the Russian and Kazakh languages and machine learning algorithms to determine the sentiment of social media texts. The whole structure and functionalities of the system are also presented. The experimental part is devoted to building machine learning models for sentiment analysis on the Russian and Kazakh datasets. Then the performance of the models is evaluated with accuracy, precision, recall, and F1-score metrics. The models with the highest scores are selected for implementation in the OMSystem. Then the OMSystem’s social analytics module is used to thoroughly analyze the healthcare, political and social aspects of the most relevant topics connected with the vaccination against the coronavirus disease. The analysis allowed us to discover the public social mood in the cities of Almaty and Nur-Sultan and other large regional cities of Kazakhstan. The system’s study included two extensive periods: 10-01-2021 to 30-05-2021 and 01-07-2021 to 12-08-2021. In the obtained results, people’s moods and attitudes to the Government’s policies and actions were studied by such social network indicators as the level of topic discussion activity in society, the level of interest in the topic in society, and the mood level of society. These indicators calculated by the OMSystem allowed careful identification of alarming factors of the public (negative attitude to the government regulations, vaccination policies, trust in vaccination, etc.) and assessment of the social mood.

show abstract

Section: Related Workmentioning

confidence: 99%

On the development of an information system for monitoring user opinion and its role for the public

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, this has also accelerated the propagation of misleading information. Misinformation about health has been detected on different social media sites, such as Twitter [2][3][4][5], Facebook [6][7][8][9], YouTube [10][11][12][13], Pinterest [14,15], and Weibo [16,17]. Waszak et al [18] found that 40% of the most frequently shared links on social media contained medical information related to the most common diseases and causes of death were classified as fake news.…”

Section: Introductionmentioning

confidence: 99%

Visualizing the Interpretation of a Criteria-Driven System That Automatically Evaluates the Quality of Health News: Exploratory Study of 2 Approaches

Liu¹,

Alsghaier²,

Tong³

et al. 2022

JMIR AI

View full text Add to dashboard Cite

Background Machine learning techniques have been shown to be efficient in identifying health misinformation, but the results may not be trusted unless they can be justified in a way that is understandable. Objective This study aimed to provide a new criteria-based system to assess and justify health news quality. Using a subset of an existing set of criteria, this study compared the feasibility of 2 alternative methods for adding interpretability. Both methods used classification and highlighting to visualize sentence-level evidence. Methods A total of 3 out of 10 well-established criteria were chosen for experimentation, namely whether the health news discussed the costs of the intervention (the cost criterion), explained or quantified the harms of the intervention (the harm criterion), and identified the conflicts of interest (the conflict criterion). The first step of the experiment was to automate the evaluation of the 3 criteria by developing a sentence-level classifier. We tested Logistic Regression, Naive Bayes, Support Vector Machine, and Random Forest algorithms. Next, we compared the 2 visualization approaches. For the first approach, we calculated word feature weights, which explained how classification models distill keywords that contribute to the prediction; then, using the local interpretable model-agnostic explanation framework, we selected keywords associated with the classified criterion at the document level; and finally, the system selected and highlighted sentences with keywords. For the second approach, we extracted sentences that provided evidence to support the evaluation result from 100 health news articles; based on these results, we trained a typology classification model at the sentence level; and then, the system highlighted a positive sentence instance for the result justification. The number of sentences to highlight was determined by a preset threshold empirically determined using the average accuracy. Results The automatic evaluation of health news on the cost, harm, and conflict criteria achieved average area under the curve scores of 0.88, 0.76, and 0.73, respectively, after 50 repetitions of 10-fold cross-validation. We found that both approaches could successfully visualize the interpretation of the system but that the performance of the 2 approaches varied by criterion and highlighting the accuracy decreased as the number of highlighted sentences increased. When the threshold accuracy was ≥75%, this resulted in a visualization with a variable length ranging from 1 to 6 sentences. Conclusions We provided 2 approaches to interpret criteria-based health news evaluation models tested on 3 criteria. This method incorporated rule-based and statistical machine learning approaches. The results suggested that one might visually interpret an automatic criterion-based health news quality evaluation successfully using either approach; however, larger differences may arise when multiple quality-related criteria are considered. This study can increase public trust in computerized health information evaluation.

show abstract

A Proposal to Find Fake News and Detecting Political Bias of News Articles

Pandya

Jaiswal

Rautaray

et al. 2022

Advances in Data and Information Sciences

View full text Add to dashboard Cite

Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models

Cited by 4 publications

References 22 publications

On the development of an information system for monitoring user opinion and its role for the public

On the development of an information system for monitoring user opinion and its role for the public

Visualizing the Interpretation of a Criteria-Driven System That Automatically Evaluates the Quality of Health News: Exploratory Study of 2 Approaches

A Proposal to Find Fake News and Detecting Political Bias of News Articles

Contact Info

Product

Resources

About