文字分類是基本的機器學習問題,可應用於各種產品。在本指南中,我們將文字分類工作流程分成幾個步驟。針對每個步驟,我們根據特定資料集的特徵,建議採用客製化方法。具體來說,我們會根據樣本數與每個樣本的字數比率,建議能快速達到最佳成效的模型類型。其他步驟都是根據這項選擇設計。我們希望透過本指南、隨附程式碼和流程圖,協助您瞭解並快速找出文字分類問題的初步解決方案。
結語
除非另有註明,否則本頁面中的內容是採用創用 CC 姓名標示 4.0 授權,程式碼範例則為阿帕契 2.0 授權。詳情請參閱《Google Developers 網站政策》。Java 是 Oracle 和/或其關聯企業的註冊商標。
上次更新時間:2025-07-27 (世界標準時間)。
[null,null,["上次更新時間:2025-07-27 (世界標準時間)。"],[[["\u003cp\u003eThis guide provides a structured workflow for text classification, breaking it down into manageable steps tailored to your dataset's characteristics.\u003c/p\u003e\n"],["\u003cp\u003eModel selection is guided by the ratio of samples to words per sample, helping you quickly identify a suitable model for optimal performance.\u003c/p\u003e\n"],["\u003cp\u003eThe guide includes code and a flowchart to facilitate learning, understanding, and implementing a first-cut solution for your text classification problem.\u003c/p\u003e\n"]]],[],null,["# Conclusion\n\nText classification is a fundamental machine learning problem with applications\nacross various products. In this guide, we have broken down the text\nclassification workflow into several steps. For each step, we have suggested a\ncustomized approach based on the characteristics of your specific dataset. In\nparticular, using the ratio of number of samples to the number of words per\nsample, we suggest a model type that gets you closer to the best performance\nquickly. The other steps are engineered around this choice. We hope that\nfollowing the guide, the\n[accompanying code](https://github.com/google/eng-edu/tree/master/ml/guides/text_classification),\nand the\n[flowchart](/machine-learning/guides/text-classification/step-2-5#figure-5)\nwill help you learn, understand, and get a swift first-cut solution to your text\nclassification problem."]]