| Abstrakt: |
Sentiment or opinion largely relies on public commentary, where reflections are either positive or negative. Sentiment classification automates the process of determining the orientation of a subject based on text, which aims to classify documents by expressed views. This task faces significant challenges due to issues, like negation, ambiguity, and complex language structures. In this work, a new Squirrel Search Mayfly Algorithm_Hierarchical Deep Learning for Text (SSMA_HDLTex) is established for sentiment classification using aspect term extraction and optimized deep learning. Primarily, the document on Amazon review is taken as input and later it is applied to the process of tokenization. In this process, Bidirectional Encoder Representations from Transformers is employed to partition the sentence into tokens. Later, Aspect Term Extraction is effectuated. At last, sentiment classification is done by employing HDLTex which is trained by utilizing the presented SSMA method. The novel SSMA method is devised by integrating the Squirrel Search Algorithm as well as the Mayfly Algorithm. The proposed SSMA_HDLTex has attained maximal and precision, F-measure, and recall, of 0.936, 0.937, and 0.941correspondingly. This innovative approach significantly enhances the accuracy and reliability of sentiment classification tasks. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink