本文關(guān)鍵詞： 推薦系統(tǒng) 協(xié)同過(guò)濾 相似度計(jì)算 社交網(wǎng)絡(luò)　出處：《華南理工大學(xué)》2013年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著互聯(lián)網(wǎng)技術(shù)和社交網(wǎng)站的迅猛發(fā)展，信息過(guò)載問(wèn)題越來(lái)越嚴(yán)峻。個(gè)性化推薦系統(tǒng)可以主動(dòng)分析用戶(hù)的行為，挖掘用戶(hù)的興趣，從而為用戶(hù)推薦滿(mǎn)足他需求的信息資源，成為了解決信息過(guò)載問(wèn)題的一個(gè)重要工具。其中協(xié)同過(guò)濾推薦算法由于其簡(jiǎn)單且普適性強(qiáng)，在各個(gè)領(lǐng)域的推薦系統(tǒng)中得到了廣泛的應(yīng)用。 本文論述了推薦系統(tǒng)的研究背景、現(xiàn)狀和意義，詳細(xì)介紹了協(xié)同過(guò)濾推薦算法的基本思想和實(shí)現(xiàn)過(guò)程，分析其采用的相似度計(jì)算方法存在的不足，以及算法單獨(dú)依賴(lài)評(píng)分?jǐn)?shù)據(jù)的局限。對(duì)此，我們從改善相似度計(jì)算方法和如何借助社交網(wǎng)絡(luò)改善協(xié)同過(guò)濾推薦算法兩個(gè)方面展開(kāi)研究。本文的主要工作和貢獻(xiàn)如下： 1、提出一種融合Jaccard系數(shù)規(guī)范化歐氏距離方法（JNED）來(lái)度量用戶(hù)之間的相似度。該方法使得處于不同評(píng)分維度空間用戶(hù)的相似度具有可比性且可靠度更高。通過(guò)實(shí)例情景驗(yàn)證和具體實(shí)驗(yàn)統(tǒng)計(jì)表明，JNED方法得到的相似度結(jié)果和實(shí)際情況比較吻合，同時(shí)具有較高的信息利用率。 2、提出一種基于社交網(wǎng)絡(luò)的協(xié)同過(guò)濾推薦算法(SNCF)。SNCF通過(guò)社交網(wǎng)絡(luò)為目標(biāo)用戶(hù)搜索候選鄰居集，，結(jié)合用戶(hù)熟識(shí)度和評(píng)分相似度作為最終的相似度，以此生成最近鄰居并預(yù)測(cè)評(píng)分，產(chǎn)生推薦。該方法避免了單獨(dú)依賴(lài)評(píng)分相似度的局限，可以更加準(zhǔn)確的獲得更多的鄰居用戶(hù)，從而提高推薦算法的準(zhǔn)確度和覆蓋率。 3、利用爬蟲(chóng)從豆瓣網(wǎng)采集真實(shí)社交網(wǎng)絡(luò)數(shù)據(jù)和電影評(píng)分?jǐn)?shù)據(jù)進(jìn)行算法驗(yàn)證實(shí)驗(yàn)。利用這些數(shù)據(jù)對(duì)本文提出的JNED相似度計(jì)算方法和SNCF推薦算法進(jìn)行驗(yàn)證。實(shí)驗(yàn)結(jié)果表明，相對(duì)于傳統(tǒng)的相似度計(jì)算方法和基于用戶(hù)的協(xié)同過(guò)濾推薦算法，JNED相似度計(jì)算方法和SNCF算法在預(yù)測(cè)評(píng)分準(zhǔn)確度、覆蓋率和新穎度都有提升。
[Abstract]:With the rapid development of Internet technology and social network, the problem of information overload is becoming more and more serious. It has become an important tool to solve the problem of information overload. Because of its simplicity and universality, collaborative filtering recommendation algorithm has been widely used in recommendation systems in various fields. This paper discusses the research background, current situation and significance of recommendation system, introduces in detail the basic idea and implementation process of collaborative filtering recommendation algorithm, and analyzes the shortcomings of the similarity calculation method. As well as the limitation that the algorithm depends on the score data alone. In this paper, we study the two aspects of improving similarity calculation method and how to improve collaborative filtering recommendation algorithm with the help of social network. The main work and contributions of this paper are as follows:. 1. A Jaccard coefficient normalized Euclidean distance (Euclidean distance method) is proposed to measure the similarity between users. This method makes the similarity of users in different dimensions of score more comparable and more reliable. The results of scene verification and experimental statistics show that the similarity obtained by JNED method is in good agreement with the actual situation. At the same time, it has high information utilization ratio. 2. A collaborative filtering recommendation algorithm based on social network (SNS) is proposed to search candidate neighbor set for target users through social network, which combines user familiarity and score similarity as the final similarity, so as to generate nearest neighbor and predict score. This method avoids the limitation of relying solely on the similarity of score, and can obtain more neighbor users more accurately, thus improving the accuracy and coverage of the recommendation algorithm. 3. The crawler is used to collect real social network data and movie score data from Douban net for algorithm verification. The JNED similarity calculation method and the SNCF recommendation algorithm proposed in this paper are verified by these data. The experimental results show that, Compared with the traditional similarity calculation method, the user based collaborative filtering recommendation algorithm and the SNCF algorithm, the prediction accuracy, coverage and novelty are improved.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 劉建國(guó);周濤;郭強(qiáng);汪秉宏;;個(gè)性化推薦系統(tǒng)評(píng)價(jià)方法綜述[J];復(fù)雜系統(tǒng)與復(fù)雜性科學(xué);2009年03期

2 劉建國(guó);周濤;汪秉宏;;個(gè)性化推薦系統(tǒng)的研究進(jìn)展[J];自然科學(xué)進(jìn)展;2009年01期

本文編號(hào)：1516028