發(fā)布時(shí)間：2018-05-19 19:44

  本文選題：推薦算法 + 協(xié)同過濾　； 參考：《河北師范大學(xué)》2016年碩士論文

【摘要】：互聯(lián)網(wǎng)的快速發(fā)展,尤其是Web 2.0的興起,為人們提供了豐富大量的信息資源,人們?cè)跁秤涡畔⒑Ｑ蟮耐瑫r(shí),“信息過載”給人們帶來的困惑也越來越多。面對(duì)大量的信息,人們往往無從選擇,想要尋找自己需要的信息必須花費(fèi)大量的時(shí)間和精力。推薦系統(tǒng)應(yīng)運(yùn)而生,很好的解決了信息過載問題,并在電子商務(wù)平臺(tái)得到廣泛應(yīng)用且成為重要組成部分。目前,在眾多的推薦技術(shù)中,協(xié)同過濾是應(yīng)用最廣泛的推薦技術(shù),尤其是在電子商務(wù)平臺(tái),其應(yīng)用效果表現(xiàn)的更為突出。在傳統(tǒng)的協(xié)同過濾推薦系統(tǒng)中,推薦結(jié)果的產(chǎn)生是利用用戶的評(píng)分來完成的。這種方法存在的問題是:一方面,隨著用戶數(shù)和項(xiàng)目數(shù)的增加,用戶—項(xiàng)目評(píng)分矩陣的數(shù)據(jù)嚴(yán)重稀疏;另一方面,用戶的評(píng)分反映了用戶對(duì)所購(gòu)產(chǎn)品的整體喜好,但用戶對(duì)產(chǎn)品的某一特征或?qū)傩缘钠脧恼w評(píng)分上并不能夠得到體現(xiàn)。為了能夠充分了解到用戶對(duì)產(chǎn)品不同特征層面的偏好,大量研究者們通過對(duì)用戶評(píng)論進(jìn)行特征—情感詞對(duì)抽取來獲取用戶偏好,從而為用戶提供更準(zhǔn)確的推薦。本文針對(duì)圖書推薦算法,主要從以下幾個(gè)方面進(jìn)行了深入的研究和探討。首先,對(duì)用戶評(píng)論語料進(jìn)行預(yù)處理,抽取出特征—情感詞對(duì),量化產(chǎn)品在不同特征層面的分?jǐn)?shù),構(gòu)建項(xiàng)目-特征評(píng)分矩陣,在此基礎(chǔ)上獲得用戶在項(xiàng)目特征層面的偏好。其次,在進(jìn)行項(xiàng)目相似度評(píng)分預(yù)測(cè)時(shí),提出利用基于項(xiàng)目的評(píng)分相似度和特征相似度的綜合相似度來預(yù)測(cè)評(píng)分,填充評(píng)分矩陣,解決數(shù)據(jù)稀疏性問題。然后,針對(duì)傳統(tǒng)的基于用戶的協(xié)同過濾算法在用戶相似度計(jì)算時(shí),只是考慮用戶評(píng)分上的相似而未考慮用戶偏好相似的問題,提出在用戶相似度計(jì)算時(shí)加入偏好相似度計(jì)算的方法。最后,使用來自Stanford SNAP的公共圖書數(shù)據(jù)集,通過實(shí)驗(yàn)驗(yàn)證本文提出的算法的有效性。實(shí)驗(yàn)結(jié)果表明,我們的方法與傳統(tǒng)的算法相比,達(dá)到了良好的推薦效果。
[Abstract]:The rapid development of the Internet, especially the rise of Web 2.0, provides people with a wealth of information resources, while people swim the ocean of information, "information overload" brings people more and more confusion. In the face of a large amount of information, people often have no choice, to find the information they need must spend a lot of time and energy. Recommendation system emerges as the times require, which solves the problem of information overload, and is widely used in e-commerce platform and become an important part. At present, collaborative filtering is the most widely used recommendation technology, especially in e-commerce platform, and its application effect is more prominent. In the traditional collaborative filtering recommendation system, the result of recommendation is produced by the user's score. The problem with this approach is that, on the one hand, as the number of users and items increases, the data of the user-item scoring matrix is severely sparse; on the other hand, the users' ratings reflect the overall preferences of the products they purchase. However, the user's preference for a particular feature or attribute of the product can not be reflected in the overall score. In order to fully understand users' preferences on different feature levels of products, a large number of researchers obtain user preferences by extracting feature-affective word pairs from user comments, thus providing users with more accurate recommendations. In this paper, the book recommendation algorithm, mainly from the following aspects of in-depth research and discussion. Firstly, we preprocess the user comment corpus, extract the feature-affective word pairs, quantify the product scores at different feature levels, construct the item-feature score matrix, and then obtain the user preferences at the item feature level. Secondly, in the prediction of item similarity score, a new method is proposed to predict the score, fill the score matrix, and solve the problem of data sparsity by using the comprehensive similarity based on item score similarity and feature similarity. Then, the traditional collaborative filtering algorithm based on users only considers the similarity of users' scores, but not the similarity of user preferences. This paper presents a method of adding preference similarity to user similarity calculation. Finally, the effectiveness of the proposed algorithm is verified by using the common book data set from Stanford SNAP. The experimental results show that our method achieves a good recommendation effect compared with the traditional algorithm.
【學(xué)位授予單位】：河北師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 阮光冊(cè);;網(wǎng)絡(luò)用戶評(píng)論的語義挖掘研究[J];情報(bào)科學(xué);2015年11期

2 王全民;王莉;曹建奇;;基于評(píng)論挖掘的改進(jìn)的協(xié)同過濾推薦算法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2015年10期

3 劉羽;曹瑞娟;;基于觀點(diǎn)挖掘的產(chǎn)品特征提取[J];計(jì)算機(jī)應(yīng)用與軟件;2014年01期

4 賀桂和;;基于用戶偏好挖掘的電子商務(wù)協(xié)同過濾推薦算法研究[J];情報(bào)科學(xué);2013年12期

5 扈中凱;鄭小林;吳亞峰;陳德人;;基于用戶評(píng)論挖掘的產(chǎn)品推薦算法[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2013年08期

6 張玉芳;代金龍;熊忠陽;;分步填充緩解數(shù)據(jù)稀疏性的協(xié)同過濾算法[J];計(jì)算機(jī)應(yīng)用研究;2013年09期

7 韋素云;業(yè)寧;朱健;黃霞;張碩;;基于項(xiàng)目聚類的全局最近鄰的協(xié)同過濾算法[J];計(jì)算機(jī)科學(xué);2012年12期

8 江海洋;;基于評(píng)論挖掘和用戶偏好學(xué)習(xí)的評(píng)分預(yù)測(cè)協(xié)同過濾[J];計(jì)算機(jī)應(yīng)用研究;2010年12期

9 陳健;印鑒;;基于影響集的協(xié)作過濾推薦算法[J];軟件學(xué)報(bào);2007年07期

10 鄧愛林,左子葉,朱揚(yáng)勇;基于項(xiàng)目聚類的協(xié)同過濾推薦算法[J];小型微型計(jì)算機(jī)系統(tǒng);2004年09期

，

本文編號(hào)：1911392