【摘要】：垃圾網(wǎng)頁(yè)是指一些網(wǎng)頁(yè)通過(guò)不正當(dāng)?shù)氖侄蝸?lái)誤導(dǎo)搜索引擎,使網(wǎng)頁(yè)獲得高于其應(yīng)有的排名,從而獲得更多的訪問(wèn)量。它不僅降低了網(wǎng)頁(yè)的質(zhì)量,同時(shí)也導(dǎo)致了嚴(yán)重的Web信息安全問(wèn)題。傳統(tǒng)的垃圾網(wǎng)頁(yè)檢測(cè)通常使用經(jīng)典的機(jī)器學(xué)習(xí)方法包括貝葉斯算法、SVM、C4.5等,這些算法對(duì)垃圾網(wǎng)頁(yè)的檢測(cè)有一定的效果。在前人的研究基礎(chǔ)上提出一種基于免疫克隆選擇的垃圾網(wǎng)頁(yè)檢測(cè)方法。利用人工免疫系統(tǒng)的自學(xué)習(xí)及自適應(yīng)能力來(lái)檢測(cè)利用新作弊技術(shù)的垃圾網(wǎng)頁(yè),并與廣泛用于垃圾網(wǎng)頁(yè)檢測(cè)的貝葉斯算法對(duì)比。實(shí)驗(yàn)表明該方法能有效、可靠地檢測(cè)出垃圾網(wǎng)頁(yè)。
[Abstract]:Spam page refers to some pages through improper means to mislead the search engine, so that the page gets higher than it should rank, so as to get more visitors. It not only reduces the quality of web pages, but also leads to serious Web information security problems. Classical machine learning methods such as Bayesian algorithm, SVM,C4.5 and so on are usually used in the traditional spam detection. These algorithms have a certain effect on the detection of garbage pages. On the basis of previous studies, a method of spam page detection based on immune clone selection is proposed. The self-learning and adaptive ability of the artificial immune system is used to detect spam pages using the new cheating technology and compared with Bayesian algorithm which is widely used in spam detection. Experiments show that the method is effective and reliable in detecting garbage pages.
【作者單位】： 西南交通大學(xué)信息科學(xué)與技術(shù)學(xué)院;
【基金】：四川省學(xué)術(shù)帶頭人培養(yǎng)基金項(xiàng)目(x8000912371309)
【分類(lèi)號(hào)】：TP393.092

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 周茜,趙明生,扈e，

本文編號(hào)：2391656