Analysis of fine tuning the hyper parameters in RoBERTa model using genetic algorithm for text classification

Sobhanam, Hridya; Prakash, Jay

doi:10.1007/s41870-023-01395-4

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article3

Other2

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 5 publications

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Convolutional neural networks and histogram-oriented gradients: a hybrid approach for automatic mango disease detection and classification

Admass,

Munaye,

Bogale

2023

Int. j. inf. tecnol.

View full text Add to dashboard Cite

Convolutional neural networks and histogram-oriented gradients: a hybrid approach for automatic mango disease detection and classification

Admass,

Munaye,

Bogale

2023

Int. j. inf. tecnol.

View full text Add to dashboard Cite

Analyzing sentiments towards E-Levy policy implementation in Ghana using twitter data

Appiahene,

Afrifa,

Akwah

et al. 2024

Int. j. inf. tecnol.

View full text Add to dashboard Cite

A newly proposed or implemented government policy often encounters challenges. Ghanaian citizens have always look down negatively upon their government’s policies, hence those are rarely appreciated. This paper ponders over the Ghanaian government’s proposal of electronic levy on mobile money transactions which was announced in the 2022 budget on November 17, 2021. We have scrutinized this governmental policy through the ordinary citizen's perspective using lexicon-based sentiment analysis on Twitter data. Lexicons are collections of words that express specific emotions, and deals with interpreting emotions like happiness, frustration, anger, and sadness. Twitter, serving as a means for people to share their views, provides enormous user generated content, beneficial for research purposes. We collected e-levy specific Twitter data in five phases, namely; policy introduction, popularity, discussion, feeble, and debate phases. The policy introduction phase recorded the least volume of data containing 1400 tweets, among which our sentiment analyzer classifies 8.93% as positive, 89.29% as neutral, and 1.78% as negative. The debate phase recorded the highest amount of data containing 18.423 tweets, among which 24.43% tweets are classified as positive, 59.29% as neutral, and 16.28% as negative. An analysis on the entire data containing 38,771 tweets reports 25.50% positive, 59.02% neutral, and 15.48% negative tweets. Our study determines that people are not largely unhappy established by the stable positive sentiment percentage, however, there is a high neutral score in all the phases.

show abstract

Improving nonprofit engagement on social media: Using big data, machine-learning, and sentiment analysis to evaluate leading nonprofits’ message strategies on Twitter/X

Dardis,

Buckley,

Mitra

et al. 2024

Int. j. inf. tecnol.

View full text Add to dashboard Cite

Analysis of fine tuning the hyper parameters in RoBERTa model using genetic algorithm for text classification

Cited by 5 publications

References 23 publications

Convolutional neural networks and histogram-oriented gradients: a hybrid approach for automatic mango disease detection and classification

Convolutional neural networks and histogram-oriented gradients: a hybrid approach for automatic mango disease detection and classification

Analyzing sentiments towards E-Levy policy implementation in Ghana using twitter data

Improving nonprofit engagement on social media: Using big data, machine-learning, and sentiment analysis to evaluate leading nonprofits’ message strategies on Twitter/X

Contact Info

Product

Resources

About