Research Article
A Comparative Study to Detect Emotions from Tweets Analyzing Machine Learning and Deep Learning Techniques
|
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
|
| Volume 12 - Issue 30 |
| Published: June 2020 |
| Authors: Sanzana Karim Lora, Nazmus Sakib, Shahana Alam Antora, Nusrat Jahan |
10.5120/ijais2020451862
|
Sanzana Karim Lora, Nazmus Sakib, Shahana Alam Antora, Nusrat Jahan . A Comparative Study to Detect Emotions from Tweets Analyzing Machine Learning and Deep Learning Techniques. International Journal of Applied Information Systems. 12, 30 (June 2020), 6-12. DOI=10.5120/ijais2020451862
@article{ 10.5120/ijais2020451862,
author = { Sanzana Karim Lora,Nazmus Sakib,Shahana Alam Antora,Nusrat Jahan },
title = { A Comparative Study to Detect Emotions from Tweets Analyzing Machine Learning and Deep Learning Techniques },
journal = { International Journal of Applied Information Systems },
year = { 2020 },
volume = { 12 },
number = { 30 },
pages = { 6-12 },
doi = { 10.5120/ijais2020451862 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2020
%A Sanzana Karim Lora
%A Nazmus Sakib
%A Shahana Alam Antora
%A Nusrat Jahan
%T A Comparative Study to Detect Emotions from Tweets Analyzing Machine Learning and Deep Learning Techniques%T
%J International Journal of Applied Information Systems
%V 12
%N 30
%P 6-12
%R 10.5120/ijais2020451862
%I Foundation of Computer Science (FCS), NY, USA
Abstract
At the present time, people corresponding to share their thoughts, emotions and ideas through social media. Twitter is one of the most widespread sites among them. The goal of this study is to classify positive and negative emotions accurately by with a dataset of Twitter tweets. For this work, machine learning (Naïve Bayes, SVM, Logistic Regression using tf-idf and count vectors), deep learning(Stacked Long short-term memory (LSTM), Stacked LSTM with 1D convolution, CNN with pre-trained word embedding) and a BERT based model have been used. The CNN model with pre-trained word embedding has performed the best among all models with 84.1% accuracy after 3 epochs only. Among all machine learning and deep learning models, deep learning models have performed better than machine learning models.
References
- R. Sawyer and G.-M. Chen, “The impact of social media on intercultural adaptation,”2012.
- “What is Twitter.”https://esrc.ukri.org/research/impact-toolkit/social-media/twitter/what-is-twitter/.Accessed: 2019-05-30.
- KaliCornn,”Identifying Depression on Social Media.”
- M. Cai, “Sentiment analysis of tweets using deep neural architectures,”
- M. Hoang, O. A. Bihorac, and J. Rouces, “Aspect-based sentiment analysis using bert,”in NEAL Proceedings of the 22nd Nordic Conference on Computional Linguistics (NoDaL-iDa), September 30-October 2, Turku, Finland, no. 167, pp. 187–196, Linköping University Electronic Press, 2019.
- S. t. S. T. Avudaiappan.T, Jenifer, “Twitter sentimental analysis using neural network,” in INTERNATIONAL JOURNAL OF SCIENTIFIC TECHNOLOGY RESEARCH VOLUME 9, ISSUE 02, pp. 2277–8616, 2020.
- J. Camacho-Collados and M. T. Pilehvar, “On the role of text preprocessing in neural network architectures: An evaluation study on text categorization and sentiment analysis,” arXiv preprint arXiv:1707.01780, 2017.
- G. U. Srikanth et al., “Survey of sentiment analysis using deep learning techniques,”in2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), pp. 1–9, IEEE, 2019.
- A. Hassan and A. Mahmood, “Deep learning approach for sentiment analysis of short texts,” in2017 3rd international conference on control, automation and robotics (IC-CAR), pp. 705–710, IEEE, 2017.
- A. M. Ramadhani and H. S. Goo, “Twitter sentiment analysis using deep learning methods,” in2017 7th International Annual Engineering Seminar (InAES), pp. 1–4, IEEE, 2017.
- H. Nguyen and M.-L. Nguyen, “A deep neural architecture for sentence-level sentiment classification in twitter social networking,” in International Conference of the Pacific Association for Computational Linguistics, pp. 15–27, Springer, 2017.
- “Dataset.”http://help.sentiment140.com/for-students/.Ac-cessed: 2019-06-01.
- “Tfidf.”https://www.geeksforgeeks.org/tf-idf-model-for-page-ranking/. Accessed: 2019-07-27.
- “Countvectors.”https://medium.com/greyatom/an-introduction-to-bag-of-words-in-nlp-ac967d43b428.Accessed: 2019-07-27.
- Y. Kim, “Convolutional neural networks for sentence classification,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),pp. 1746–1751, 2014.
- “Googlnewsword2vecmodel.”https://mccormickml.com/2016/04/12/googles-pretrainedword2vec-model-in-python/.Accessed:2019-07-16.
- “Stackedlstm.”https://machinelearningmastery.com/stacked-long-short-term-memory-networks/.Accessed:2019-07-15.
Index Terms
Keywords