Light Gradient Boosting Machine for General Sentiment Classification on Short Texts: A Comparative Evaluation

Fatimah Alzamzami,Mohamad Hoda,Abdulmotaleb El Saddik

doi:10.1109/access.2020.2997330

Abstract

Recently, the focus on sentiment analysis has been domain dependent even though the expressions used by the public are unsophisticatedly familiar regardless of the topics or domains. Online social media (OSNs) has been a daily venue for informal conversational contents from various domains ranging from sports and cooking to politics and human rights. Generating specific resources for every domain independently requires high cost and extensive efforts. In response, we propose to build a general multi-class sentiment classifier using our Domain-Free Sentiment Multimedia Dataset (DFSMD). Based on the proven capabilities of Light Gradient Boosting Machine (LGBM) in dealing with high dimensional and imbalance data, we have trained an LGBM model to recognize one of three sentiments of tweets: positive, negative, or neutral. We have conducted extensive comparisons and evaluations for six other standard sentiment classification algorithms and different sets of features including OSNs-specific ones. Our results have shown that LGBM model is the winner among the other six algorithms. It has been also shown that our dataset contains distinguishing characteristics in the three classes. Moreover, hashtag words are shown to be significantly important in capturing the sentiments of tweets. In addition, our findings have revealed the effectiveness of our approach in adapting general-domain sentiment to domain-specific sentiment analysis.

Highlights

As has become evident, online social media (OSNs) platforms have proliferated in recent years and immense amount of data from different domains is being publicly published online
(2) Investigate how our proposed features would perform on our Domain-Free Sentiment Multimedia Dataset (DFSMD). (3) Investigate the correlation between positive, negative, and neutral terms extracted from our DFSMD dataset
Four classifiers were used in training a binary sentiment model in the work [22] and the results showed that Support Vector Machine (SVM) was the winner among naïve -bayes (NB), maximum entropy (ME), and stochastic gradient descent (SGD)

Summary

Introduction

Online social media (OSNs) platforms have proliferated in recent years and immense amount of data from different domains is being publicly published online. Machine intelligence is inevitably necessary to automate the monitoring of online stream of conversations and talks that express various opinions regardless of the aspects involved; let it be preferences, agreements, refutations or even neutrality over a discussed topic. These opinion-rich conversations fall under the umbrella of sentiment analysis, The associate editor coordinating the review of this manuscript and approving it for publication was Alberto Cano. With the input limit restriction, we have observed the emergence of online cultural language that includes slangs, short forms, emojis, etc This has resulted in contents with a mix of spoken and online language.

Objectives

Methods

Results