Improving the accuracy of cinema review topic modeling on Twitter with parallel latent Dirichlet allocation and latent Dirichlet allocation
Krishna K. Leela, R Surendran · 2025
The primary objective of research is to compare the Latent Dirichlet Allocation model and Parallel Latent Dirichlet Allocation to improve the accuracy and precision of movie reviews on Twitter. The first group Latent Dirichlet Allocation includes 21 sample inputs and the group Parallel Latent Dirichlet Allocation includes 21 samples, alpha value of 0.05 beta value of 0.2 and 80% G power is also being taken into consideration and total sample size N is 42. The accuracy of the Latent Dirichlet Allocation is 90% typically higher compared to the 89% accuracy of the Parallel Latent Dirichlet Allocation. The mean accuracy of the detection was found to be within +/- 2 standard Deviation, and a t-test using an independent sample showed that this result is statistically significant and got a significance value of P is 0.023(p<0.05). Performance of Latent Dirichlet Allocation is better than Parallel Latent Dirichlet Allocation by comparing their results. The accuracy of Latent Dirichlet Allocation is higher than the comparison algorithm Parallel Latent Dirichlet Allocation accuracy.