Leveraging Large Language Models for Sentiment Analysis: Multi-Modal Analysis of Decentraland’s MANA Token

利用大语言模型进行情感分析：Decentraland MANA 代币的多模态分析

Abstract: Decentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate virtual asset transactions and governance. This study investigates the integration of Discord community sentiment with multi-modal financial data to enhance cryptocurrency price prediction within virtual world economies.

摘要： Decentraland 是一个在不断扩展的元宇宙生态系统中运行的去中心化虚拟现实平台，它利用其原生代币 MANA 来促进虚拟资产交易和治理。本研究探讨了将 Discord 社区情感与多模态金融数据相结合，以增强虚拟世界经济中加密货币价格预测的方法。

We address: (1) identifying sentiment patterns within Decentraland’s Discord community, and (2) evaluating the impact of multi-modal features on token return forecasting. Using a BERT-based large language model for sentiment analysis, we develop two LSTM architectures: a baseline incorporating historical prices and a multi-modal variant integrating sentiment scores, trading volume, and market capitalization.

我们旨在解决以下问题：(1) 识别 Decentraland Discord 社区内的情感模式；(2) 评估多模态特征对代币收益预测的影响。通过使用基于 BERT 的大语言模型进行情感分析，我们开发了两种 LSTM 架构：一种是结合历史价格的基准模型，另一种是整合了情感得分、交易量和市值的多模态变体模型。

Results indicate predominantly neutral community sentiment with a positive skew. The multi-modal model significantly outperforms the price-only baseline in prediction accuracy. These findings demonstrate the predictive value of community-derived signals for virtual economy forecasting and establish a foundation for future research at the intersection of immersive virtual environments, natural language processing, and cryptocurrency market analysis.

研究结果表明，社区情感以中性为主，并呈现正向偏态。在预测准确性方面，多模态模型显著优于仅基于价格的基准模型。这些发现证明了社区衍生信号在虚拟经济预测中的预测价值，并为沉浸式虚拟环境、自然语言处理和加密货币市场分析交叉领域的未来研究奠定了基础。

---

Paper Details:

• Authors: Xintong Wu, Peiting Tsai, Jing Yuan, Michael Yu, Greg Sun, Luyao Zhang
• Subject: Computation and Language (cs.CL)
• Date: 4 Apr 2026
• DOI: 10.48550/arXiv.2605.20192

论文详情：

• 作者： Xintong Wu, Peiting Tsai, Jing Yuan, Michael Yu, Greg Sun, Luyao Zhang
• 学科： 计算与语言 (cs.CL)
• 日期： 2026年4月4日
• DOI： 10.48550/arXiv.2605.20192