Sentiment analysis using a deep ensemble learning model

Başarslan, Muhammet Sinan; Kayaalp, Fatih

doi:10.1007/s11042-023-17278-6

Cited by 3 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of 13,567 comments are amassed through this scraping process, forming the basis for subsequent analysis. To facilitate robust model training and evaluation, the dataset is judiciously divided into training (10,853 comments) and testing (2,714 comments) sets, maintaining an 80:20 ratio [33]. This partitioning is essential to validate the model's performance on unseen data, contributing to the overall generalizability of the sentiment analysis model.…”

Section: Data Collectionsmentioning

confidence: 99%

Improving sentiment analysis on PeduliLindungi comments: a comparative study with CNN-Word2Vec and integrated negation handling

Jayadianti,

Arianti,

Cahyana

et al. 2023

SITech

View full text Add to dashboard Cite

This study investigates sentiment analysis in Google Play reviews of the PeduliLindungi application, focusing on the integration of negation handling into text preprocessing and comparing the effectiveness of two prominent methods: CNN-Word2Vec CBOW and CNN-Word2Vec SkipGram. Through a meticulous methodology, negation handling is incorporated into the preprocessing phase to enhance sentiment analysis. The results demonstrate a noteworthy improvement in accuracy for both methods with the inclusion of negation handling, with CNN-Word2Vec SkipGram emerging as the superior performer, achieving an impressive 76.2% accuracy rate. Leveraging a dataset comprising 13,567 comments, this research introduces a novel approach by emphasizing the significance of negation handling in sentiment analysis. The study not only contributes valuable insights into the optimization of sentiment analysis processes but also provides practical considerations for refining methodologies, particularly in the context of mobile application reviews.

show abstract

Section: Data Collectionsmentioning

confidence: 99%