Aspect Based Multi-Labeling Using SVM Based Ensembler

ABSTRACT

Sentiment analysis is one of the most prominent sub-areas of research in Natural Language
Processing (NLP), where it is important to consider implicit or explicit emotions conveyed by review
material. Researchers also recognized that the generic feelings derived from the textual material are
insufficient, so the sentiment analysis aspect based was coined to extract the emotions from textual data.
Multi-labeling based on aspects data can resolve the issue of extracting emotion aspect based. In this work,
a novel approach namely: Evolutionary Ensembler (EEn) is proposed to effectively boost the accuracy
and diversity of multi-label learners. Unlike traditional multi-label training methods, EEn emphasizes the
accuracy and diversity of multi-label-based models. We have used seven datasets (medical, hotel, movies,
automobiles, proteins, birds, emotions, news). At first, we applied a pre-processing step to gain the refined
and clean data. Second, we have applied the Vader tool with Bag of Words (BoW) for the feature extraction.
Third, the word2vec method is applied to draw an association between words. Moreover, the SVM model
(tuned with GA) is trained and tested on the refined data. The accuracy of the aspect-based multi-labeling
using the SVM-GA on medical, hotel, movies, automobiles, proteins, birds, emotions, news are 93.13%,
94.32%, 94.0%, 95.10%, 90.20%, 93.22%, 90.0%, and 94.0%, respectively. Our proposed model with
different dimensions of multi-label datasets shows that EEn is vastly superior to other popular techniques.
Experimental outcomes validate the success of the implemented approach among existing benchmark
techniques.