With the rapid growth of usage of online social media platforms in daily life there has also been an increase in opinion mining or sentiment analysis to extract the user’s sentiments or views towards any topic. Twitter’s data or tweets has been the focus point among the researchers as it provides abundant data and in a wide variety of fields. While most of the study in this field has been in the extraction of polarity scores of the sentiments namely positive negative and neutral in a tweet, this paper focuses on extracting the real sentiments such as love, hate, worry, sadness and more out of the tweets. This paper proposes different machine learning and deep learning techniques such as Random Forest, Bi-directional LSTM, BERT and more to present a comparative analysis of the performance of different techniques and extract the sentiments with high accuracy. Tweets have been collected from the Crowdflower dataset and experimental findings reveal that the methodology comprising BERT produces the maximum accuracy followed by the methodology that comprises bi-directional LSTM and then the rest of the model follows.

Sentiment Analysis, BERT, Bi-directional LSTM, Multi-class Classification, Random Forest, GloVe

[1] M. Bouazizi, T. Ohtsuki, “A pattern-based approach for multi-class sentiment analysis in Twitter”, IEEE Access, vol. 5, pp. 20617-20639, 2017.
[2] M. Bouazizi, T. Ohtsuki, “Sentiment analysis: From binary to multiclass classification: A pattern-based approach for multi-class sentiment analysis in Twitter”, In the Proceedings of 2016 IEEE International Conference on Communications (ICC), Malaysia, pp. 1-6, 2016.
[3] M.M. Madbouly, S.M. Darwish, R. Essameldin, “Modified fuzzy sentiment analysis approach based on user ranking suitable for online social networks”, IET software, Vol. 14, Issue 3, pp. 300-307, 2020.
[4] M. Bibi, W. Aziz, M. Almaraashi, I.H. Khan, M.S.A. Nadeem, N. Habib, “A Cooperative Binary-Clustering Framework Based on Majority Voting for Twitter Sentiment Analysis”, IEEE Access, Vol. 8, pp. 68580-68592, 2020.
[5] S.E. Saad, J. Yang, “Twitter sentiment analysis based on ordinal regression”, IEEE Access, Vol. 7, pp. 163677-163685, 2019.
[6] H. Rehioui, A. Idrissi, "New Clustering Algorithms for Twitter Sentiment Analysis", IEEE Systems Journal, Vol. 14, Issue 1, pp. 530-537, 2019.
[7] L. Wang, J. Niu, S. Yu, "SentiDiff: Combining textual information and sentiment diffusion patterns for Twitter sentiment analysis", IEEE Transactions on Knowledge and Data Engineering, Vol. 32, Issue 10, pp. 2026-2039, 2020.
[8] Z. Jianqiang, G. Xiaolin, Z. Xuejun, “Deep convolution neural networks for twitter sentiment analysis”, IEEE Access, Vol. 6, pp. 23253 - 23260, 2018.
[9] A.C. Pandey, D.S. Rajpoot, M. Saraswat, “Twitter sentiment analysis using hybrid cuckoo search method”, Information Processing & Management, Vol. 53, Issue 4, pp.764-779, 2017.
[10] U. Naseem, I. Razzak, K. Musial, M. Imran, "Transformer based deep intelligent contextual embedding for twitter sentiment analysis", Future Generation Computer Systems, Vol. 113, pp. 58-69, 2020.
[11] Y. AI. Amrani, M. Lazaar, KE. EI. Kadiri, “Random forest and support vector machine based hybrid approach to sentiment analysis", Procedia Computer Science, Vol. 127, pp. 511-520.
[12] J. Wang, L.C. Yu, K.R. Lai, X. Zhang, “Dimensional sentiment analysis using a regional CNN-LSTM model”, In the Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Vol. 2: short papers, pp. 225-230, 2016.
[13] Y. Zhang, J. Wang, X. Zhang, “YNU-HPCC at SemEval-2018 Task 1: BiLSTM with attention based sentiment analysis for affect in tweets", In the Proceedings of the 12th International Workshop on Semantic Evaluation, China, pp. 273-278, 2018.
[14] A.A. Sharfuddin, M.N. Tihami, M.S. Islam, “A deep recurrent neural network with bilstm model for sentiment classification”, In the Proceedings of the 2018 IEEE International Conference on Bangla Speech and Language Processing (ICBSLP), Sylhet, Bangladesh, pp. 1-4, 2018.
[15] M. Jabreel, A. Moreno, “Target-dependent Sentiment Analysis of Tweets using a Bi-directional Gated Recurrent Unit”, In the 13th International Conference on Web Information Systems and Technologies (WEBIST), pp. 80-87, 2017.
[16] M. Munikar, S. Shakya, and A. Shrestha. "Fine-grained sentiment classification using bert." In the Proceedings of the 2019 IEEE International Conference on Artificial Intelligence for Transforming Business and Society (AITB), Kathmandu, Nepal, pp. 1-5, Vol. 1, 2019.
[17] D. G. Aggarwal, “Sentiment Analysis: An insight into Techniques, Application and Challenges”, International Journal of Computer Sciences and Engineering, Vol.6, Issue.5, pp. 697-703, 2018.
[18] M.G. Huddar, S.S. Sannakki, V.S. Rajpurohit, “A Survey of Computational Approaches and Challenges in Multimodal Sentiment Analysis”, International Journal of Computer Sciences and Engineering, Vol.7, Issue.1, pp. 876-883, 2019.