A Tweet Sentiment Classification Approach Using a Hybrid Stacked Ensemble Technique

With the extensive availability of social media platforms, Twitter has become a significant tool for the acquisition of peoples’ views, opinions, attitudes, and emotions towards certain entities. Within this frame of reference, sentiment analysis of tweets has become one of the most fascinating research areas in the field of natural language processing. A variety of techniques have been devised for sentiment analysis, but there is still room for improvement where the accuracy and efficacy of the system are concerned. This study proposes a novel approach that exploits the advantages of the lexical dictionary, machine learning, and deep learning classifiers. We classified the tweets based on the sentiments extracted by TextBlob using a stacked ensemble of three long short-term memory (LSTM) as base classifiers and logistic regression (LR) as a meta classifier. The proposed model proved to be effective and time-saving since it does not require feature extraction, as LSTM extracts features without any human intervention. We also compared our proposed approach with conventional machine learning models such as logistic regression, AdaBoost, and random forest. We also included state-of-the-art deep learning models in comparison with the proposed model. Experiments were conducted on the sentiment140 dataset and were evaluated in terms of accuracy, precision, recall, and F1 Score. Empirical results showed that our proposed approach manifested state-of-the-art results by achieving an accuracy score of 99%.

[1]  Gyu Sang Choi,et al.  Extensive hotel reviews classification using long short term memory , 2020, Journal of Ambient Intelligence and Humanized Computing.

[2]  Jing Cai,et al.  A Weighted Voting Classifier Based on Differential Evolution , 2014 .

[3]  Xuejun Zhang,et al.  Deep Convolution Neural Networks for Twitter Sentiment Analysis , 2018, IEEE Access.

[4]  Estevam R. Hruschka,et al.  Tweet sentiment analysis with classifier ensembles , 2014, Decis. Support Syst..

[5]  Aytug Onan,et al.  A multiobjective weighted voting ensemble classifier based on differential evolution algorithm for text sentiment classification , 2016, Expert Syst. Appl..

[6]  Paolo Nesi,et al.  Predicting TV programme audience by using twitter based metrics , 2017, Multimedia Tools and Applications.

[7]  Felipe Ferreira Bocca,et al.  The effect of tuning, feature engineering, and feature selection in data mining applied to rainfed sugarcane yield modelling , 2016, Comput. Electron. Agric..

[8]  Xavier Giró-i-Nieto,et al.  From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction , 2016, Image Vis. Comput..

[9]  Jiebo Luo,et al.  A picture tells a thousand words - About you! User interest profiling from user generated visual content , 2015, Signal Process..

[10]  Haiyi Zhang,et al.  Text Mining of Twitter Data Using a Latent Dirichlet Allocation Topic Model and Sentiment Analysis , 2018 .

[11]  Doaa Mohey El Din Mohamed Hussein,et al.  A survey on sentiment analysis challenges , 2016, Journal of King Saud University - Engineering Sciences.

[12]  Gyu Sang Choi,et al.  Sentiment analysis of tweets using a unified convolutional neural network‐long short‐term memory network model , 2020, Comput. Intell..

[13]  Gyu Sang Choi,et al.  Tweets Classification on the Base of Sentiments for US Airline Companies , 2019, Entropy.

[14]  Ankit,et al.  An Ensemble Classification System for Twitter Sentiment Analysis , 2018 .

[15]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[16]  Jamil Hussain,et al.  Tweets Classification and Sentiment Analysis for Personalized Tweets Recommendation , 2020, Complex..

[17]  Erik Cambria,et al.  Affective Computing and Sentiment Analysis , 2016, IEEE Intelligent Systems.

[18]  Andreas F. Ehmann,et al.  Lyric Text Mining in Music Mood Classification , 2009, ISMIR.

[19]  Krzysztof Marasek,et al.  Deep Belief Neural Networks and Bidirectional Long-Short Term Memory Hybrid for Speech Recognition , 2015 .

[20]  Federico Divina,et al.  Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting , 2018 .

[21]  Samir Kumar Bandyopadhyay,et al.  Sentiment Analysis-An Objective View , 2016 .

[22]  Mathieu Cliche,et al.  BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs , 2017, *SEMEVAL.

[23]  Antonio Gabriel López-Herrera,et al.  Deep learning and multilingual sentiment analysis on social media data: An overview , 2021, Appl. Soft Comput..

[24]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[25]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.

[26]  Zhixue Sun,et al.  Well production forecasting based on ARIMA-LSTM model considering manual operations , 2021, Energy.

[27]  Fernando de la Prieta,et al.  Sentiment Analysis Based on Deep Learning: A Comparative Study , 2020, Electronics.

[28]  Andria Arisal,et al.  A multi domains short message sentiment classification using hybrid neural network architecture , 2021 .

[29]  Bei Yu,et al.  An evaluation of text classification methods for literary study , 2008, Lit. Linguistic Comput..