Empowering Sentiment Analysis with Deep Learning Model: Evaluating Social Media's Benefits and Drawbacks
DOI:
https://doi.org/10.21015/vtcs.v12i2.2041Abstract
Online social networks (OSNs) have revolutionized communication by facilitating unprecedented information sharing and global connections. Despite these benefits, OSNs also present significant challenges, including the spread of misinformation, increased distraction, and adverse mental health effects. This study examines a dataset of 3,904 user reviews collected from online sources and personal networks, revealing a polarized sentiment distribution with 56% positive, 43.1% negative and 0.9% neutral views on the impact of social platforms. To capture the nuanced sentiments expressed, Long Short-Term Memory (LSTM) enhanced with preprocessing techniques such as tokenization, lemmatization, and word embeddings with Word2Vec was employed. The LSTM model achieved an accuracy of 86.43% in sentiment classification, significantly outperforming traditional baseline methods. These findings provide valuable information for platform developers, policymakers, and researchers aiming to understand and mitigate the social and psychological effects of digital platforms. Future research will focus on expanding the dataset and addressing class imbalance to further refine and enhance sentiment analysis models.
References
Statista, “Number of internet and social media users worldwide as of October 2024,” Online. Available: https://www.statista.com/statistics/617136/digital-population-worldwide/. Accessed: Nov. 15, 2024.
S. Kemp, “Digital 2023: Global Overview Report,” Online. Available: https://datareportal.com/. Accessed: Nov. 15, 2024.
A. Kumar and A. Jaiswal, "Systematic literature review of sentiment analysis on Twitter using soft computing techniques," Concurrency and Computation: Practice and Experience, vol. 32, no. 1, p. e5107, 2020.
N. R. Chowdhury, M. Z. Islam, and F. Alam, "Challenges of sentiment analysis on social media data," in 2021 International Conference on Computer Communication and Informatics (ICCCI), 2021, pp. 1–5.
S. A. Alotaibi, "Challenges in sentiment analysis for Arabic social media," Journal of Information Science, vol. 46, no. 6, pp. 816–827, 2020.
C. J. Hutto and E. Gilbert, "VADER: A parsimonious rule-based model for sentiment analysis of social media text," in Proc. Int. AAAI Conf. Web Social Media, vol. 14, 2020, pp. 216–225.
K. Zhao and J. Liu, "Deep learning for sentiment analysis of social media," Computational Intelligence and Neuroscience, vol. 2021, pp. 1–9, 2021.
J. Gao et al., "Mental health problems and social media exposure during COVID-19 outbreak," PLoS One, vol. 15, no. 4, p. e0231924, 2020.
M. B. Alvi, N. A. Mahoto, M. A. Unar, and M. A. Shaikh, "Xtractor: A two-step tweet extractor for sentiment analysis," in 2024 5th International Conference on Advancements in Computational Sciences (ICACS), 2024, pp. 1–6.
M. B. Alvi et al., "Count Me Too: Sentiment analysis of Roman Sindhi script," SAGE Open, vol. 13, no. 3, p. 21582440231197452, 2023.
E. Tamam and O. F. Yanik, "Hybrid approaches for sentiment analysis in social media," J. Ambient Intell. Humaniz. Comput., vol. 12, no. 4, pp. 4053–4065, 2021.
L. Jiang and W. Zhang, "Deep learning for punctuation normalization in social media text," Neural Comput. Appl., vol. 32, no. 24, pp. 18073–18083, 2020.
Y. Tang and H. Wang, "Contextual lemmatization for improved sentiment analysis," J. Artif. Intell. Res., vol. 70, pp. 1–20, 2021.
L. Wang and M. Sun, "A comprehensive study on spell correction techniques for NLP applications," Expert Syst. Appl., vol. 185, p. 115598, 2022.
I. Habernal and I. Gurevych, "Understanding emoji usage in social media: A sentiment analysis approach," J. Comput.-Mediat. Commun., vol. 25, no. 6, pp. 414–429, 2020.
R. Agarwal and A. Gupta, "SlangNet: A deep learning approach to handle slang and abbreviations in social media," in Proc. 2021 Conf. Empirical Methods Nat. Lang. Process., 2021, pp. 5678–5688.
P. Meakem and E. Bender, "Multilingual preprocessing techniques for sentiment analysis in social media," Comput. Linguist., vol. 47, no. 2, pp. 345–368, 2021.
Y. Liao, "Sentiment analysis by double classification of takeaway platform reviews based on deep learning LSTM models," Sci. Technol. Eng. Chem. Environ. Protect., vol. 1, no. 5, 2024.
E. S. Alamoudi and N. S. Alghamdi, "Sentiment classification and aspect-based sentiment analysis on Yelp reviews using deep learning and word embeddings," J. Decis. Syst., vol. 30, no. 2–3, pp. 259–281, 2021.
D. S. Asudani, N. K. Nagwani, and P. Singh, "Impact of word embedding models on text analytics in deep learning environment: A review," Artif. Intell. Rev., vol. 56, no. 9, pp. 10345–10425, 2023.
R. K. P. F. Muhammada et al., "Sentiment analysis using Word2Vec and long short-term memory (LSTM) for Indonesian hotel reviews," J. Inf. Commun. Technol., vol. 25, no. 4, pp. 567–580, 2020.
J. V. T. T. Diwan, "Sentiment analysis in textual, visual, and multimodal inputs using recurrent neural networks," Int. J. Comput. Sci. Inf. Secur., vol. 18, no. 3, pp. 45–52, 2020.
A. Alsharef et al., "[Retracted] An automated toxicity classification on social media using LSTM and word embedding," Comput. Intell. Neurosci., vol. 2022, no. 1, p. 8467349, 2022.
B. Bilen and F. Horasan, "LSTM network-based sentiment analysis for customer reviews," Politeknik Dergisi, vol. 25, no. 3, pp. 959–966, 2021.
M. Xuanyuan, L. Xiao, and M. Duan, "Sentiment classification algorithm based on multi-modal social media text information," IEEE Access, vol. 9, pp. 33410–33418, 2021.
R. Nawaz, H. Afzal, and A. Rauf, "Comparative analysis of deep learning-based techniques and traditional models for sentiment classification in social media," J. Ambient Intell. Humaniz. Comput., 2022.
M. Hasnain et al., "Comparative performance analysis of deep learning and traditional machine learning models for sentiment analysis," Multimed. Tools Appl., vol. 80, no. 7, pp. 10663–10686, 2021.
N. M. Alharbi et al., "Evaluation of sentiment analysis via word embedding and RNN variants for Amazon online reviews," Math. Probl. Eng., vol. 2021, no. 1, p. 5536560, 2021.
P. S. Idrovo-Berrezueta et al., "Enhancing sentiment analysis of corruption-related comments on social networks in Ecuador using machine learning techniques: LSTM, linear regression, and SVM," in Int. Conf. Inf. Technol. Syst., 2024, pp. 278–287.
R. K. Behera et al., "Co-LSTM: Convolutional LSTM model for sentiment analysis in social big data," Inf. Process. Manag., vol. 58, no. 1, p. 102435, 2021.
A. Chopra et al., "An efficient text classification framework using LSTM and pre-trained embedding layers on natural language datasets," J. Big Data, vol. 8, no. 1, pp. 1–13, 2021.
J. Carrell et al., "Evaluation of deep neural networks for sentiment classification in text," Int. J. Data Sci. Anal., vol. 12, no. 3, pp. 205–218, 2021.
Z. Wang et al., "Sentiment analysis using LSTM-CNN hybrid architectures and data augmentation," Inf. Sci., vol. 571, pp. 1–9, 2021.
S. Reddy and S. K. Kavala, "Regularization techniques to improve generalization in sentiment analysis models," Int. J. Artif. Intell. Appl., vol. 12, no. 5, pp. 11–23, 2022.
D. Asudani, T. Smith, and A. Khanna, "The Impact of Word Embedding Models on Text Analytics: GloVe, Word2Vec, and BERT in Noisy Domains," Journal of Applied Computational Linguistics, vol. 15, no. 2, pp. 45–59, 2023.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-By) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
