基于單頁語義特征的垃圾網(wǎng)頁檢測
電子技術(shù)應(yīng)用
陳木生1,2,高斐1,吳俊華1
(1.江西理工大學(xué) 軟件工程學(xué)院,江西 南昌 330013;2.南昌市虛擬數(shù)字工程與文化傳播重點(diǎn)實(shí)驗(yàn)室,江西 南昌 330013)
摘要: 為解決垃圾網(wǎng)頁檢測中特征提取難度高、計(jì)算量大的問題,提出一種僅基于當(dāng)前網(wǎng)頁的HTML腳本提取語義特征的方法。首先使用深度優(yōu)先搜索和動態(tài)規(guī)劃相結(jié)合的記憶化搜索算法對域名進(jìn)行單詞切割,采用隱含狄利克雷分布提取主題詞,基于Word2Vec詞向量和詞移距離計(jì)算3個(gè)單頁語義相似度特征;然后將單頁語義相似度特征融合單頁統(tǒng)計(jì)特征,使用隨機(jī)森林等分類算法構(gòu)建分類模型進(jìn)行垃圾網(wǎng)頁檢測。實(shí)驗(yàn)結(jié)果表明,基于單頁內(nèi)容提取語義特征融合單頁統(tǒng)計(jì)特征進(jìn)行分類的AUC值達(dá)到88.0%,比對照方法提高4%左右。
中圖分類號:TP391.6
文獻(xiàn)標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223376
中文引用格式: 陳木生,高斐,吳俊華. 基于單頁語義特征的垃圾網(wǎng)頁檢測[J]. 電子技術(shù)應(yīng)用,2023,49(6):24-29.
英文引用格式: Chen Musheng,Gao Fei,Wu Junhua. Web spam detection based on semantic features from current page[J]. Application of Electronic Technique,2023,49(6):24-29.
文獻(xiàn)標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223376
中文引用格式: 陳木生,高斐,吳俊華. 基于單頁語義特征的垃圾網(wǎng)頁檢測[J]. 電子技術(shù)應(yīng)用,2023,49(6):24-29.
英文引用格式: Chen Musheng,Gao Fei,Wu Junhua. Web spam detection based on semantic features from current page[J]. Application of Electronic Technique,2023,49(6):24-29.
Web spam detection based on semantic features from current page
Chen Musheng1,2,Gao Fei1,Wu Junhua1
(1.School of Software Engineering, Jiangxi University of Science and Technology, Nanchang 330013, China; 2.Nanchang Key Laboratory of Virtual Digital Engineering and Cultural Communication, Nanchang 330013, China)
Abstract: In order to solve the problem of high difficulty and large amount of computation in feature extraction for web spam detection, a method for extracting semantic features only based on the HTML script of the current page is proposed. Firstly, the domain name is segmented by a memorization search algorithm combining depth-first search and dynamic programming. Secondly, The latent Dirichlet distribution is used to extract subject words of the web page. Lastly, three single-page semantic similarity features are calculated based on Word2Vec and word mover distance. Combining the single-page semantic similarity features with single-page statistical features, classification algorithms such as random forest are used to build classification models for web spam detection. The experimental results show that the AUC value of single-page content extraction based on semantic and statistical features for classification reaches 88.0%, which is about 4% higher than that of the control method.
Key words : web spam detection;feature extraction;memory search;latent Dirichlet distribution;Word2Vec;word mover distance;random forest
0 引言
如今,隨著互聯(lián)網(wǎng)信息的快速增長,搜索引擎被認(rèn)為是訪問網(wǎng)站的關(guān)鍵工具,其用戶占到網(wǎng)絡(luò)用戶的80%以上[1]。但是有研究表明,大約60%的用戶只查看第一頁中最初的5個(gè)結(jié)果[2]。可以看出,在搜索結(jié)果中排名靠前的網(wǎng)頁會擁有更多的訪問者,由此帶來更多的收入。由于通過正常手段提高網(wǎng)頁排名非常困難,于是某些網(wǎng)站便通過非正常手段和技術(shù)欺騙搜索引擎提高網(wǎng)頁排名,這些網(wǎng)頁被稱為垃圾網(wǎng)頁[3]。垃圾網(wǎng)頁會降低搜索結(jié)果的質(zhì)量,浪費(fèi)用戶的時(shí)間,侵占搜索引擎公司和其他內(nèi)容網(wǎng)站的合法利益[4]。盡管搜索引擎公司已經(jīng)使用了各種方法來應(yīng)對垃圾網(wǎng)頁,但至今為止,垃圾網(wǎng)頁檢測依然是搜索引擎需要重點(diǎn)突破的難題,也是學(xué)術(shù)領(lǐng)域的一個(gè)前沿課題。因此,高效、準(zhǔn)確地檢測垃圾網(wǎng)頁具有重要意義。
本文詳細(xì)內(nèi)容請下載:http://theprogrammingfactory.com/resource/share/2000005343
作者信息:
陳木生1,2,高斐1,吳俊華1
(1.江西理工大學(xué) 軟件工程學(xué)院,江西 南昌 330013;2.南昌市虛擬數(shù)字工程與文化傳播重點(diǎn)實(shí)驗(yàn)室,江西 南昌 330013)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。