Deciphering Public Sentiment on iPhone 14: A BERT-Based Analysis of Twitter Discourse
Abstract
The study delves into understanding the sentiment of Twitter users towards the iPhone 14 by employing sentiment analysis models. Recognizing the limitations of traditional sentiment analysis tools, the research utilizes the BERT model, known for its bidirectional understanding of textual context. Initially, the study observed a prevailing negative sentiment using general models. However, after refining the approach using BERT, a more balanced representation of sentiments was observed. The BERT model's results highlighted both positive and negative reactions towards the iPhone 14 on Twitter, with distinct peaks in sentiment scores. The research underscores the importance of leveraging advanced models like BERT for tasks requiring nuanced understanding, providing stakeholders in the technology domain with comprehensive insights into public sentiment.
References
- Kauffmann, Peral, Gil, Ferrández, Sellers, & Mora. (2019). Managing Marketing Decision-Making with Sentiment Analysis: An Evaluation of the Main Product Features Using Text Data Mining. Sustainability, 11(15), 4235. MDPI AG. Retrieved from http://dx.doi.org/10.3390/su11154235
- Nandwani, P., & Verma, R. (2021). A review on sentiment analysis and emotion detection from text. Social Network Analysis and Mining, 11(1), 81. https://doi.org/10.1007/s13278-021-00776-6
- Shewale, R. (2023, August 10). Twitter statistics in 2023 - (facts after “X” rebranding). DemandSage. https://www.demandsage.com/twitter-statistics/
- Karami, A., Lundy, M., Webb, F., & Dwivedi, Y. K. (2020). Twitter and Research: A Systematic Literature Review Through Text Mining. IEEE Access, 8, 67698-67717. https://doi.org/10.1109/ACCESS.2020.2983656
- Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv, 1810.04805.