Sentiment analysis: Bayesian Ensemble Learning

Abstract

The huge amount of textual data on the Web has grown in the last few years rapidly creating unique contents of massive dimension. In a decision making context, one of the most relevant tasks is polarity classification of a text source, which is usually performed through supervised learning methods. Most of the existing approaches select the best classification model leading to over-confident decisions that do not take into account the inherent uncertainty of the natural language. In this paper, we pursue the paradigm of ensemble learning to reduce the noise sensitivity related to language ambiguity and therefore to provide a more accurate prediction of polarity. The proposed ensemble method is based on Bayesian Model Averaging, where both uncertainty and reliability of each single model are taken into account. We address the classifier selection problem by proposing a greedy approach that evaluates the contribution of each model with respect to the ensemble. Experimental results on gold standard datasets show that the proposed approach outperforms both traditional classification and ensemble methods.

Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması

“…Bayes tabanlı ensemble yöntemini diğer ensemble yöntemleri ile kıyaslamak için NB, ME, DVM ve Koşullu Rasgele Alanlar sınıflama algoritmalarını kullanarak altı farklı veri seti ile analiz yapmışlardır. Bu analizin sonucunda Bayes tabanlı yöntemin başarı oranını artırdığı ve zaman kazandırdığı görülmüştür [13]. Da Silva vd.…”

An Ensemble Model using a BabelNet Enriched Document Space for Twitter Sentiment Classification

“…They showed that random subspace has the better comperative results. Fersini et al [20] proposed a novel ensemble method based on Bayesian Model Averaging for sentiment analysis of user reviews. They showed their model outperformed the other approaches such as bagging.…”

Sentiment Analysis in Spanish for Improvement of Products and Services: A Deep Learning Approach

“…The performance of the machine learning technique depends on the effectiveness of the selected method for feature extraction. Among the most used methods are bag of words [13], TF-IDF [14], -grams (unigrams, bigrams, and trigrams) [11,15], features based on POS tagging [16], and features based on dependency rules [17].…”