PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

 

e-ISSN 2231-8526
ISSN 0128-7680

Home / Regular Issue / JST Vol. 32 (3) Apr. 2024 / JST-4583-2023

 

An Empirical Evaluation of Adapting Hybrid Parameters for CNN-based Sentiment Analysis

Mohammed Maree, Mujahed Eleyat and Shatha Rabayah

Pertanika Journal of Science & Technology, Volume 32, Issue 3, April 2024

DOI: https://doi.org/10.47836/pjst.32.3.05

Keywords: CNN, deep learning, GloVe word embedding, machine learning, sentiment classification

Published on: 24 April 2024

Sentiment analysis aims to understand human emotions and perceptions through various machine-learning pipelines. However, feature engineering and inherent semantic gap constraints often hinder conventional machine learning techniques and limit their accuracy. Newer neural network models have been proposed to automate the feature learning process and enrich learned features with word contextual embeddings to identify their semantic orientations to address these challenges. This article aims to analyze the influence of different factors on the accuracy of sentiment classification predictions by employing Feedforward and Convolutional Neural Networks. To assess the performance of these neural network models, we utilize four diverse real-world datasets, namely 50,000 movie reviews from IMDB, 10,662 sentences from LightSide Movie_Reviews, 300 public movie reviews, and 1,600,000 tweets extracted from Sentiment140. We experimentally investigate the impact of exploiting GloVe word embeddings on enriching feature vectors extracted from sentiment sentences. Findings indicate that using larger dimensions of GloVe word embeddings increases the sentiment classification accuracy. In particular, results demonstrate that the accuracy of the CNN with a larger feature map, a smaller filter window, and the ReLU activation function in the convolutional layer was 90.56% using the IMDB dataset. In comparison, it was 80.73% and 77.64% using the sentiment140 and the 300 sentiment sentences dataset, respectively. However, it is worth mentioning that, with large-size sentiment sentences (LightSide’s Movie Reviews) and using the same parameters, only a 64.44% level of accuracy was achieved.

  • Alam, S., & Yao, N. (2019). The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis. Computational and Mathematical Organization Theory, 25, 319-335. https://doi.org/10.1007/s10588-018-9266-8

  • Cao, D., Huang, Y., Li, H., Zhao, X., Chen, H., & Fu, Y. (2020, August 25-27). Text sentiment classification based on attention mechanism and decomposition convolutional neural network model. [Paper presentation]. IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), Dalian, China. https://doi.org/10.1109/AEECA49918.2020.9213672

  • Dos-Santos, C., & Gatti, M. (2014, August 23-29). Deep convolutional neural networks for sentiment analysis of short texts. [Paper presentation]. Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, Dublin, Ireland.

  • Haddi, E., Liu, X., & Shi, Y. (2013). The role of text pre-processing in sentiment analysis. Procedia Computer Science, 17, 26-32. https://doi.org/10.1016/j.procs.2013.05.005

  • He, Y. (2023, July 14-16). BERT-CNN-BiLSTM: A Hybrid Deep Learning Model for Accurate Sentiment Analysis. [Paper presentation]. IEEE 5th International Conference on Power, Intelligent Computing and Systems (ICPICS), Shenyang, China. https://doi.org/10.1109/ICPICS58376.2023.10235335

  • Horakova, M. (2015). Sentiment analysis tool using machine learning. Global Journal on Technology, 2015(5), 195-204.

  • Hussein, D. M. E. D. M. (2018). A survey on sentiment analysis challenges. Journal of King Saud University - Engineering Sciences, 30(4), 330-338. https://doi.org/10.1016/j.jksues.2016.04.002

  • Krouska, A., Troussas, C., & Virvou, M. (2016, July 13-15). The effect of preprocessing techniques on Twitter sentiment analysis. [Paper presentation]. 7th International Conference on Information, Intelligence, Systems & Applications (IISA), Chalkidiki, Greece. https://doi.org/10.1109/IISA.2016.7785373

  • Maree, M., & Eleyat, M. (2020). Semantic graph based term expansion for sentence-level sentiment analysis. International Journal of Computing 19(4), 647-655. https://doi.org/10.47839/ijc.19.4.2000

  • Ni, R., & Cao, H. (2020, July 27-29). Sentiment analysis based on GloVe and LSTM-GRU. [Paper presentation]. 39th Chinese Control Conference (CCC), Shenyang, China. https://doi.org/10.23919/CCC50068.2020.9188578

  • Qaisar, S. M. (2020, October 13-15). Sentiment analysis of IMDb movie reviews using long short-term memory. [Paper presentation]. 2nd International Conference on Computer and Information Sciences (ICCIS), Sakaka, Saudi Arabia. https://doi.org/10.1109/ICCIS49240.2020.9257657

  • Rusandi, M. R., Sutoyo, E., & Widartha, V. P. (2021, November 3-4). Convolutional neural network for predicting sentiment: Case study in tourism. [Paper presentation]. Sixth International Conference on Informatics and Computing (ICIC), Jakarta, Indonesia.

  • Shaukat, Z., Zulfiqar, A. A., Xiao, C., Azeem, M., & Mahmood, T. (2020). Sentiment analysis on IMDB using lexicon and neural networks. SN Applied Sciences, 2(2), Article 148. https://doi.org/10.1007/s42452-019-1926-x

  • Stojanovski, D., Strezoski, G., Madjarov, G., & Dimitrovski, I. (2015). Twitter sentiment analysis using deep convolutional neural network. In E. Onieva, I. Santos, E. Osaba, H. Quintian & E. Carchado (Eds.), Hybrid Artificial Intelligence Systems (pp. 726-737). Springer. https://doi.org/10.1007/978-3-319-19644-2_60

  • Vielma, C., Verma, A., & Bein, D. (2020). Single and multibranch CNN-bidirectional LSTM for IMDb sentiment analysis. In S. Latifi. (Ed.), 17th International Conference on Information Technology–New Generations (pp. 401-406). Springer. https://doi.org/10.1007/978-3-030-43020-7_53

  • Wang, M., Chen, S., & He, L. (2018). Sentiment classification using neural networks with sentiment centroids. In D. Phung, V. S. Tseng, G. O. Webb, B. Ho, M. Ganji & L. Rashidi (Eds.), Advances in Knowledge Discovery and Data Mining (pp. 56-67). Springer. https://doi.org/10.1007/978-3-319-93034-3_5

  • Wilson, T., Wiebe, J., & Hoffmann, P. (2009). Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Computational Linguistics, 35(3), 399-433. https://doi.org/10.1162/coli.08-012-R1-06-90

  • Yang, P., & Chen, Y. (2017, December 15-17). A survey on sentiment analysis by using machine learning methods. [Paper presentation]. IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, China. https://doi.org/10.1109/ITNEC.2017.8284920

  • Yenter, A., & Verma, A. (2017, October 19-21). Deep CNN-LSTM with combined kernels from multiple branches for IMDb review sentiment analysis. [Paper presentation]. IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York. USA. https://doi.org/10.1109/UEMCON.2017.8249013

  • Zhang, L., Wang, S., & Liu, B. (2018). Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), Article e1253. https://doi.org/https://doi.org/10.1002/widm.1253

  • Zhang, Y., & Wallace, B. (2015). A Sensitivity Analysis of (and practitioners’ guide to) Convolutional Neural Networks for Sentence Classification. arXiv preprint arXiv:1510.03820. https://doi.org/10.48550/arXiv.1510.03820