本文選題：推薦系統(tǒng) + 深度學(xué)習(xí)��； 參考：《廣東工業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著互聯(lián)網(wǎng)的快速發(fā)展,網(wǎng)絡(luò)信息呈現(xiàn)爆炸式的增長(zhǎng),其結(jié)構(gòu)也變得越加復(fù)雜。海量信息的呈現(xiàn),使得用戶很難從中發(fā)現(xiàn)自己感興趣的內(nèi)容,而推薦系統(tǒng)可以幫助用戶發(fā)掘更深次的需求,給用戶帶來(lái)個(gè)性化的體驗(yàn)。此外,推薦系統(tǒng)可以幫助用戶更容易地找到他們需要的產(chǎn)品,也可以通過(guò)改進(jìn)用戶體驗(yàn)幫助企業(yè)提升用戶忠誠(chéng)度從而把更多的潛在用戶轉(zhuǎn)換為產(chǎn)品購(gòu)買者。同時(shí),推薦系統(tǒng)也具有研究?jī)r(jià)值,涉及計(jì)算數(shù)學(xué),認(rèn)知科學(xué),信息科學(xué)等學(xué)科。在推薦系統(tǒng)中,協(xié)同過(guò)濾是目前應(yīng)用最廣泛的一種個(gè)性化推薦技術(shù)。傳統(tǒng)的協(xié)同過(guò)濾方法僅僅使用用戶對(duì)物品的評(píng)分矩陣進(jìn)行推薦。在實(shí)際情況中,通常用戶的評(píng)分矩陣非常稀疏,從而導(dǎo)致推薦效果不佳。在這種情況下,一些模型嘗試使用物品內(nèi)容信息來(lái)緩解數(shù)據(jù)稀疏和冷啟動(dòng)問(wèn)題。然而,當(dāng)這些內(nèi)容信息也非常稀疏時(shí),很難從這些模型中學(xué)習(xí)到準(zhǔn)確的特征表示進(jìn)行推薦。為了應(yīng)對(duì)這些問(wèn)題,本文提出了基于深度學(xué)習(xí)和社交關(guān)系正則化的混合協(xié)同過(guò)濾推薦模型(CDL-SR)。其中,社交正則化在推薦系統(tǒng)中表示一種社交約束。該模型利用深度學(xué)習(xí)強(qiáng)大的特征表達(dá)能力,將通過(guò)深度學(xué)習(xí)算法自動(dòng)學(xué)習(xí)到的物品特征表達(dá)向量同矩陣分解后的評(píng)分矩陣有效融合,并通過(guò)在目標(biāo)函數(shù)中加入社交正則項(xiàng),讓存在社交關(guān)系的物品(如存在引用關(guān)系的論文)的隱式特征向量具有較高相似度以進(jìn)一步提高推薦效果。C D L-S R模型不僅可以提供新用戶的個(gè)性化推薦信息(冷啟動(dòng)),還有利于解決用戶評(píng)分矩陣及物品的文本、屬性、碼流等信息的數(shù)據(jù)稀疏問(wèn)題。本文以Cite Ulike論文集為樣本進(jìn)行實(shí)驗(yàn)研究表明,本文采用的深度學(xué)習(xí)與社交網(wǎng)絡(luò)信息相結(jié)合的方法能夠提供更好的推薦性能。特別是在稀疏數(shù)據(jù)集下,該方法相比于目前流行的協(xié)同主題回歸模型(CTR),召回率提升了66.7%。此外,該推薦系統(tǒng)在推薦結(jié)果中可以給出較為準(zhǔn)確和令人信服的推薦理由,進(jìn)一步提高了用戶對(duì)系統(tǒng)的滿意度。
[Abstract]:With the rapid development of the Internet, the network information explosive growth, its structure has become more and more complex. The presentation of mass information makes it difficult for users to find the content they are interested in, and recommendation system can help users to explore deeper needs and bring personalized experience to users. In addition, recommendation systems can help users find the products they need more easily, and can also help businesses improve their customer loyalty by improving their user experience, thus transforming more potential users into product buyers. At the same time, recommendation system also has research value, involving computational mathematics, cognitive science, information science and other disciplines. Collaborative filtering is the most widely used personalized recommendation technology in recommendation systems. The traditional collaborative filtering method only uses the user's scoring matrix to recommend items. In practice, the user's rating matrix is usually very sparse, resulting in poor recommendation results. In this case, some models attempt to use item content information to alleviate data sparsity and cold startup problems. However, when the content information is sparse, it is difficult to learn the exact feature representation from these models to recommend. In order to solve these problems, a hybrid collaborative filtering recommendation model based on deep learning and social relationship regularization is proposed in this paper. Social regularization represents a social constraint in a recommendation system. Using the strong feature expression ability of depth learning, the model effectively integrates the feature expression vector of objects automatically learned by the depth learning algorithm with the score matrix after matrix decomposition, and adds social regular items to the objective function. The implicit feature vectors of objects with social relationships (such as papers with reference relationships) have high similarity so as to further improve the recommendation effect. The CD-L-S R model can not only provide personalized recommendation information for new users ( Cold boot can also help to solve the user rating matrix and the text of the item. Attribute, bitstream and other information sparse problem. In this paper, the experimental results show that the combination of in-depth learning and social network information can provide better recommendation performance. Especially in sparse data sets, the recall rate of this method is 66.7% higher than that of CTRN, a popular cotopic regression model. In addition, the recommendation system can give more accurate and convincing recommendation reasons in the recommendation results, which can further improve the satisfaction of users to the system.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 鄒本友;李翠平;譚力文;陳紅;王紹卿;;基于用戶信任和張量分解的社會(huì)網(wǎng)絡(luò)推薦[J];軟件學(xué)報(bào);2014年12期

，

本文編號(hào)：1986894