關於TF-IDF的source code,它用Perl語言寫成。 http://infomotions.com/blog/tag/term-frequencyinverse-document-frequency-tfidf/ 另一個是用C#寫的: http://www.codeproject.com/KB/cs/tfidf.aspx 其它相關的參考資源: 1. Ranking text documents based on TF-IDF 2. tf-idf (term frequency–inverse document frequency) 3. Information Retrieval (這文章講解得很詳細)