Assessment of Source, Medium, and Intercommunication for Assessing the Credibility of Content

Gayakwad, Milind; Patil, Suhas H.

doi:10.1109/smartgencon51891.2021.9645746

Cited by 2 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Still, the common observation is about the accuracy which is better in the combined approaches rather than relying on a single algorithm or a single approach (Purba et al, 2021). Dataset collection also differs as the approach changes (Blondeel & Bb, 2015), for example, the dataset for analyzing the credibility of the posts on social media is different than the credibility assessment of a normal article published on a website (Gayakwad & Patil, 2021). The modeling of the approach changes according to the dataset, the loosely coupled approach is difficult because a lot of preprocessing is needed before proceeding with the training and testing of data .…”

Section: Elsinoëampelina Elsinoaceae Incertaesedismentioning

confidence: 99%

See 1 more Smart Citation

Credibility Evaluation of User-generated Content using Novel Multinomial Classification Technique

Gayakwad¹,

Patil²,

Joshi³

et al. 2022

IJRITCC

View full text Add to dashboard Cite

Awareness about the features of the internet, easy access to data using mobile, and affordable data facilities have caused a lot of traffic on the internet. Digitization came with a lot of opportunities and challenges as well. One of the important advantages of digitization is paperless transactions, and transparency in payment, while data privacy, fake news, and cyber-attacks are the evolving challenges. The extensive use of social media networks and e-commerce websites has caused a lot of user-generated information, misinformation, and disinformation on the Internet. The quality of information depends upon various stages (of information) like generation of information, medium of propagation, and consumption of information. Content being user-generated, information needs a quality assessment before consumption. The loss of information is also necessary to be examined by applying the machine learning approach as the volume of content is extremely huge. This research work focuses on novel multinomial classification (based on multinoulli distribution) techniques to determine the quality of the information in the given content. To evaluate the information content a single algorithm with some processing is not sufficient and various approaches are necessary to evaluate the quality of content. We propose a novel approach to calculate the bias, for which the Machine Learning model will be fitted appropriately to classify the content correctly. As an empirical study, rotten tomatoes’ movie review data set is used to apply the classification techniques. The accuracy of the system is evaluated using the ROC curve, confusion matrix, and MAP.

show abstract

Section: Elsinoëampelina Elsinoaceae Incertaesedismentioning

confidence: 99%

“…October 2022 Revised: 20 November 2022 Accepted: 25 December 2022 ___________________________________________________________________________________________________________________ disinformation(Gayakwad & Patil, 2021). Correct and quality information is missing in all these forms of information.…”

mentioning

confidence: 99%

Credibility Evaluation of User-generated Content using Novel Multinomial Classification Technique

Gayakwad¹,

Patil²,

Joshi³

et al. 2022

IJRITCC

View full text Add to dashboard Cite

show abstract

Credibility Analysis of User-Designed Content Using Machine Learning Techniques

Gayakwad

Patil

Kadam

et al. 2022

ASI

View full text Add to dashboard Cite

Content is a user-designed form of information, for example, observation, perception, or review. This type of information is more relevant to users, as they can relate it to their experience. The research problem is to identify the credibility and the percentage of credibility as well. Assessment of such content is important to convey the right understanding of the information. Different techniques are used for content analysis, such as voting the content, Machine Learning Techniques, and manual assessment to evaluate the content and the quality of information. In this research article, content analysis is performed by collecting the Movie Review dataset from Kaggle. Features are extracted and the most relevant features are shortlisted for experimentation. The effect of these features is analyzed by using base regression algorithms, such as Linear Regression, Lasso Regression, Ridge Regression, and Decision Tree. The contribution of the research is designing a heterogeneous ensemble regression algorithm for content credibility score assessment, which combines the above baseline methods. Moreover, these factors are also toned down to obtain the values closer to Gradient Descent minimum. Different forms of Error Loss, such as Mean Absolute Error, Mean Squared Error, LogCosh, Huber, and Jacobian, and the performance is optimized by introducing the balancing bias. The accuracy of the algorithm is compared with induvial regression algorithms and ensemble regression separately; this accuracy is 96.29%.

show abstract

Assessment of Source, Medium, and Intercommunication for Assessing the Credibility of Content

Cited by 2 publications

References 24 publications

Credibility Evaluation of User-generated Content using Novel Multinomial Classification Technique

Credibility Evaluation of User-generated Content using Novel Multinomial Classification Technique

Credibility Analysis of User-Designed Content Using Machine Learning Techniques

Contact Info

Product

Resources

About