A Scoping Review of the Relationship of Big Data Analytics with Context-Based Fake News Detection on Digital Media in Data Age

Shahzad, Khurram; Khan, Shakeel Ahmad; Ahmad, Shakil; Iqbal, Abid

doi:10.3390/su142114365

Cited by 19 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prophet is well-known for handling seasonal and trend components, while TBATS is proficient in handling cyclic patterns and nonlinearities in the data. By combining these techniques, the hybrid model was able to take various factors that affect malaria prevalence, resulting in more precise and reliable forecasts into account [ 11 , 12 , 17 , 18 ].…”

Section: Discussionmentioning

confidence: 99%

Dynamics of Malaria Incidence in Khyber Pakhtunkhwa, Pakistan: Unveiling Rapid Growth Patterns and Forecasting Future Trends

Khan,

Qureshi,

Bae

et al. 2024

J Epidemiol Glob Health

View full text Add to dashboard Cite

Background Malaria remains a formidable worldwide health challenge, with approximately half of the global population at high risk of catching the infection. This research study aimed to address the pressing public health issue of malaria’s escalating prevalence in Khyber Pakhtunkhwa (KP) province, Pakistan, and endeavors to estimate the trend for the future growth of the infection. Methods The data were collected from the IDSRS of KP, covering a period of 5 years from 2018 to 2022. We proposed a hybrid model that integrated Prophet and TBATS methods, allowing us to efficiently capture the complications of the malaria data and improve forecasting accuracy. To ensure an inclusive assessment, we compared the prediction performance of the proposed hybrid model with other widely used time series models, such as ARIMA, ETS, and ANN. The models were developed through R-statistical software (version 4.2.2). Results For the prediction of malaria incidence, the suggested hybrid model (Prophet and TBATS) surpassed commonly used time series approaches (ARIMA, ETS, and ANN). Hybrid model assessment metrics portrayed higher accuracy and reliability with lower MAE (8913.9), RMSE (3850.2), and MAPE (0.301) values. According to our forecasts, malaria infections were predicted to spread around 99,301 by December 2023. Conclusions We found the hybrid model (Prophet and TBATS) outperformed common time series approaches for forecasting malaria. By December 2023, KP’s malaria incidence is expected to be around 99,301, making future incidence forecasts important. Policymakers will be able to use these findings to curb disease and implement efficient policies for malaria control.

show abstract

Section: Discussionmentioning

confidence: 99%

Dynamics of Malaria Incidence in Khyber Pakhtunkhwa, Pakistan: Unveiling Rapid Growth Patterns and Forecasting Future Trends

Khan,

Qureshi,

Bae

et al. 2024

J Epidemiol Glob Health

View full text Add to dashboard Cite

show abstract

“…Standard Deviation: Measure of variation within values for any given occurrence in a dataset. As can be depicted in equation (2).…”

Section: 1b Data Processingmentioning

confidence: 99%

“…as mentioned in the research article published by Shaqra University (Kingdom of Saudi Arabia) [1]. Many of these emerge as a result of massive unstructured data in the fields of Big Data Analytics and how they lead to Fake News scenarios that can present polarizing views [2].…”

Section: Introductionmentioning

confidence: 99%

Profile Verification and Secured Social Engineering with Machine Learning Models

Gupta

Sujatha

Elango

et al. 2023

Preprint

View full text Add to dashboard Cite

Digital media as a platform is one of highest interactive yet sensitive arenas of information technology. With the rise of Online Social Networks, the idea of authentic identity is often seen on the brink of attack with the impact of cases of Social Engineering and other forms of Cyber Threats. The research here mainly aims at developing a Profile Verification Model with existing datasets from platforms such as Instagram. This includes understanding the behavioural aspects of interactions with masked identity elements such as bots and fake accounts Using the concepts of Supervised Machine Learning, its objective is to use existing algorithms such as Random Forest Classifier, K-Nearest Neighbour Classifier, and Linear SVM, using data pre-processing techniques to transform valid input training and testing formats. Finally, drawing comparative results using mathematical operations for accuracy and testing and depict the same through data visualization tools.

show abstract

“…In addition to its uses for communication and entertainment, the Internet is an important tool for finding information. The amount of digital information available is continually growing, with more being added daily [15][16][17][18][19][20]. The Internet has become an essential resource for accessing a vast amount of information on a wide range of topics.…”

Section: Literature Reviewmentioning

confidence: 99%

Towards Fake News Detection: A Multivocal Literature Review of Credibility Factors in Online News Stories and Analysis Using Analytical Hierarchical Process

Abrar,

Khan,

Khan

et al. 2023

Electronics

View full text Add to dashboard Cite

Information and communication technologies have grown globally in the past two decades, expanding the reach of news networks. However, the credibility of the information is now in question. Credibility refers to a person’s belief in the truth of a subject, and online readers consider various factors to determine whether a source is trustworthy. Credibility significantly impacts public behaviour, and less credible news spreads faster due to people’s interest in emotions like fear and disgust. This can have negative consequences for individuals and economies. To determine the credibility factors in digital news stories, a Multivocal Literature Review (MLR) was conducted to identify relevant studies in both white and grey literature. A total of 161 primary studies were identified from published (white) literature and 61 were identified from unpublished (grey) literature. As a result, 14 credibility factors were identified, including “number of views”, “reporter reputations”, “source information”, and “impartiality”. These factors were then analysed using statistical tests and the Analytic Hierarchy Process (AHP) for decision-making to determine their criticality and importance in different domains.

show abstract

A Scoping Review of the Relationship of Big Data Analytics with Context-Based Fake News Detection on Digital Media in Data Age

Cited by 19 publications

References 38 publications

Dynamics of Malaria Incidence in Khyber Pakhtunkhwa, Pakistan: Unveiling Rapid Growth Patterns and Forecasting Future Trends

Dynamics of Malaria Incidence in Khyber Pakhtunkhwa, Pakistan: Unveiling Rapid Growth Patterns and Forecasting Future Trends

Profile Verification and Secured Social Engineering with Machine Learning Models

Towards Fake News Detection: A Multivocal Literature Review of Credibility Factors in Online News Stories and Analysis Using Analytical Hierarchical Process

Contact Info

Product

Resources

About