網路資訊流通快速，許多傳統商業行為轉變為網路行銷模式，消費者在進行消費決策時，無法有效評估產品品質，往往只能透過網路與親友的評論與實測來評估產品品質，由於在許多網路平台上評論的真實性無法詳細確認，因此本研究透過分析歷史消費評論幫助消費者進行消費決策以及紀錄產品全面且長期表現。
現今有許多平台針對不同產品提供消費者進行產品討論，由於大部份的平台都是中心化管理，並且不同族群喜好不一，使用的平台也不盡相同，因此本研究期望透過整合跨平台資料，針對產品評論進行情感分析並提供使用者一個較為客觀的指標進行決策分析，過往在自然語言處理情感分析方法有關鍵字識別、統計方法、詞彙關聯但這些方法對於深層且複雜多類別的主題並不那麼有效，本研究透過使用大型語言模型針對產品多面向的發展採用較為全面的情感分析。
結合去中心化技術和智能合約能更有效地保證評論的不可竄改性，從而使情感分析指標更加可信，透過智能合約，中心化平台可以避免人為竄改的風險，進一步增強此去中心化應用系統的可靠性。

In the fast-paced world of internet information flow, many traditional commercial behaviors have shifted towards online marketing models. Consumers, when making purchasing decisions, are often unable to effectively evaluate product quality and typically rely on internet and personal acquaintances' reviews and hands-on tests. Given that the authenticity of reviews on many online platforms cannot be thoroughly verified, this study aims to assist consumers in making purchasing decisions by analyzing historical consumer reviews.
Currently, many platforms provide spaces for consumer discussions on various products. Most of these platforms are centrally managed, and preferences for them vary across different demographics, leading to the use of diverse platforms. This study seeks to integrate cross-platform data to conduct sentiment analysis on product reviews, offering users a more objective indicator for decision-making analysis. Traditional natural language processing sentiment analysis methods, such as keyword identification, statistical methods, and lexical association, are not as effective for multi-category topics. This research adopts a more comprehensive sentiment analysis approach by utilizing large language models to address the multifaceted development of products.
Decentralized technology and smart contracts can more ensure the immutability of reviews, thereby making sentiment analysis indicators more trustworthy. Through smart contracts, centralized platforms can avoid the risk of human tampering, further enhancing the reliability of this decentralized application system.

參考文獻

[1] S. Nakamoto, "Bitcoin: A peer-to-peer electronic cash system," 2008.
[2] L. Lamport, R. Shostak, and M. Pease, "The Byzantine generals problem," in Concurrency: the works of leslie lamport, 2019, pp. 203-226.
[3] G. Wood, "Ethereum: A secure decentralised generalised transaction ledger," Ethereum project yellow paper, vol. 151, no. 2014, pp. 1-32, 2014.
[4] W. Zou et al., "Smart contract development: Challenges and opportunities," IEEE transactions on software engineering, vol. 47, no. 10, pp. 2084-2106, 2019.
[5] A. Gervais, G. O. Karame, K. Wüst, V. Glykantzis, H. Ritzdorf, and S. Capkun, "On the security and performance of proof of work blockchains," in Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 2016, pp. 3-16.
[6] S. King and S. Nadal, "Ppcoin: Peer-to-peer crypto-currency with proof-of-stake," self-published paper, August, vol. 19, no. 1, 2012.
[7] J. Benet, "Ipfs-content addressed, versioned, p2p file system," arXiv preprint arXiv:1407.3561, 2014.
[8] W. X. Zhao et al., "A survey of large language models," arXiv preprint arXiv:2303.18223, 2023.
[9] S. Khan, M. Naseer, M. Hayat, S. W. Zamir, F. S. Khan, and M. Shah, "Transformers in vision: A survey," ACM computing surveys (CSUR), vol. 54, no. 10s, pp. 1-41, 2022.
[10] E. J. Hu et al., "Lora: Low-rank adaptation of large language models," arXiv preprint arXiv:2106.09685, 2021.
[11] T. Dettmers, A. Pagnoni, A. Holtzman, and L. Zettlemoyer, "Qlora: Efficient finetuning of quantized llms," Advances in Neural Information Processing Systems, vol. 36, 2024.
[12] W. Medhat, A. Hassan, and H. Korashy, "Sentiment analysis algorithms and applications: A survey," Ain Shams engineering journal, vol. 5, no. 4, pp. 1093-1113, 2014.
[13] M. Grinberg, Flask web development. " O'Reilly Media, Inc.", 2018.
[14] K. Bhosale, K. Akbarabbas, J. Deepak, and A. Sankhe, "Blockchain based secure data storage," International Research Journal of Engineering and Technology (IRJET), vol. 6, no. 3, pp. 5058-5061, 2019.
[15] S. U. S. Chebolu, F. Dernoncourt, N. Lipka, and T. Solorio, "Exploring conditional text generation for aspect-based sentiment analysis," arXiv preprint arXiv:2110.02334, 2021.
[16] C. Wu et al., "Multiple-element joint detection for aspect-based sentiment analysis," Knowledge-Based Systems, vol. 223, p. 107073, 2021.
[17] P. Barnaghi, P. Ghaffari, and J. G. Breslin, "Opinion mining and sentiment polarity on twitter and correlation between events and sentiment," in 2016 IEEE second international conference on big data computing service and applications (BigDataService), 2016: IEEE, pp. 52-57.
[18] H. Touvron et al., "Llama 2: Open foundation and fine-tuned chat models," arXiv preprint arXiv:2307.09288, 2023.
[19] W.-M. Lee, "Using the MetaMask crypto-wallet," in Beginning Ethereum Smart Contracts Programming: With Examples in Python, Solidity, and JavaScript: Springer, 2023, pp. 111-144.