--- title: "Dustin Liang (@dustinliang) | Hashnode" description: "Dustin Liang (@dustinliang) writes on Hashnode. Read their latest articles and follow their work." url: "https://hashnode.com/@dustinliang" --- @dustinliang # Dustin Liang @dustinliang · Joined October 2026 ### [Mentions per Agency: A Simple Ratio for Measuring Discussion Concentration in Stock Heat Data](https://dustinliang.hashnode.dev/mentions-per-agency-a-simple-ratio-for-measuring-discussion-concentration-in-stock-heat-data?utm_source=hashnode&utm_medium=feed) Two stocks can sit side by side on a heat ranking with exactly the same mention count and still have very different stories behind them. One might be mentioned once each by forty different institution 7 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/mentions-per-agency-a-simple-ratio-for-measuring-discussion-concentration-in-stock-heat-data?utm_source=hashnode&utm_medium=feed) [57m ago](https://hashnode.com/posts/mentions-per-agency-a-simple-ratio-for-measuring-discussion-concentration-in-stock-heat-data/6af934e6580b3cbddea477ba) ### [How to Compare Stock Heat Across a Basket: Raw Mentions, Group Share, and Self-Relative Z-Scores](https://dustinliang.hashnode.dev/how-to-compare-stock-heat-across-a-basket-raw-mentions-group-share-and-self-relative-z-scores?utm_source=hashnode&utm_medium=feed) Put five stocks from the same sector next to each other on a heat chart and the result is almost always the same: the largest, most widely followed names sit on top. That is not wrong, but it is rarel 7 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/how-to-compare-stock-heat-across-a-basket-raw-mentions-group-share-and-self-relative-z-scores?utm_source=hashnode&utm_medium=feed) [58m ago](https://hashnode.com/posts/how-to-compare-stock-heat-across-a-basket-raw-mentions-group-share-and-self-relative-z-scores/6af934c4436186ffae1b1cd5) ### [Sector Heat Rolling Window Comparison: Unit-Testing AI Theme Heat from 1h to 3d](https://dustinliang.hashnode.dev/sector-heat-rolling-window-comparison-unit-testing-ai-theme-heat-from-1h-to-3d?utm_source=hashnode&utm_medium=feed) An AI-related concept ranks second on the one-hour heat board and eleventh on the three-day board. Is that a sudden burst, or a theme cooling off? Usually it is neither. It is two rolling windows meas 8 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/sector-heat-rolling-window-comparison-unit-testing-ai-theme-heat-from-1h-to-3d?utm_source=hashnode&utm_medium=feed) [59m ago](https://hashnode.com/posts/sector-heat-rolling-window-comparison-unit-testing-ai-theme-heat-from-1h-to-3d/6af9347c9a7413182fbcca95) ### [股票MCP是什么意思：A 股消息面热度数据接入 AI Agent 的工具选型与调用示例](https://dustinliang.hashnode.dev/stock-mcp-meaning-a-share-news-heat?utm_source=hashnode&utm_medium=feed) 摘要 股票MCP是什么意思？MCP（Model Context Protocol，模型上下文协议）是一种让 AI 客户端调用外部工具与数据的开放协议；「股票 MCP」就是以 MCP 形式提供股票数据的服务端。接入之后，你可以在支持 MCP 的 AI 办公软件或自建 Agent 里直接用中文提问，例如「宁德时代最近一周消息面热不热」，模型会自己选择工具、填参数、读取结构化结果，而不是凭训练数据猜。 4 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/stock-mcp-meaning-a-share-news-heat?utm_source=hashnode&utm_medium=feed) [4h ago](https://hashnode.com/posts/stock-mcp-meaning-a-share-news-heat/6af907ed5cd3a6d8f90505fe) ### [情绪因子量化怎么做：用熔岩消息面热度构建 A 股情绪因子的关注度分量](https://dustinliang.hashnode.dev/sentiment-factor-attention-component?utm_source=hashnode&utm_medium=feed) 摘要 情绪因子量化怎么做？业界常见的新闻情绪因子大致由四个部分组成：个股与文本的关联、每条文本的情感方向、相关度加权与时间衰减，以及按交易日的聚合。其中「这只股票被讨论了多少、被谁讨论」是关注度分量，「讨论偏正面还是偏负面」是方向分量。熔岩（Lava）提供的是前者：按个股与概念聚合的消息面提及数 mentions、参与主体数 agencies、按机构/大V 分加权的 weighted\_heat，以 3 min read · [dustinliang.hashnode.dev](https://dustinliang.hashnode.dev/sentiment-factor-attention-component?utm_source=hashnode&utm_medium=feed) [4h ago](https://hashnode.com/posts/sentiment-factor-attention-component/6af90791fb4d4fd1c8c338c0)