<![CDATA[This study examines how transformer-based models, such as BERT and DistilBERT, can be used for sentiment analysis of IMDb movie reviews. The goal of the experiment was to find a balance between accuracy and computational efficiency, evaluating how well both models performed with different training parameters. BERT was able to reach a peak accuracy of 91.39% in three epochs, taking a total of 54 minutes to train. On the other hand, DistilBERT achieved a similar accuracy of 91.80% in only 38 minutes and 25 seconds. Although there was a slight variance in accuracy, DistilBERT proved to be a much more efficient option for training, thus becoming a feasible substitute for environments with limited resources. The findings were contrasted against R. Talibzade's (2023) research, which obtained a 98% accuracy rate using BERT but needed 12 hours of training, illustrating the balance between accuracy and training duration. Potential upcoming tasks involve refining further, testing with bigger datasets, investigating alternative transformer models, and utilizing more resource-efficient training methods to improve performance without sacrificing efficiency.]]>
Copyrights © 2024
