本文關(guān)鍵詞： 推薦算法 協(xié)同過(guò)濾 項(xiàng)目相似度學(xué)習(xí) 社交網(wǎng)絡(luò) 標(biāo)簽　出處：《安徽大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：隨著互聯(lián)網(wǎng)的發(fā)展,推薦算法已經(jīng)應(yīng)用到很多領(lǐng)域,協(xié)同過(guò)濾推薦算法是經(jīng)典的、應(yīng)用廣泛的推薦算法。然而傳統(tǒng)的協(xié)同過(guò)濾推薦算法面臨著很多問(wèn)題,其中最嚴(yán)重的是冷啟動(dòng)問(wèn)題、數(shù)據(jù)稀疏問(wèn)題和擴(kuò)展性問(wèn)題。本文針對(duì)這些問(wèn)題,對(duì)傳統(tǒng)的協(xié)同過(guò)濾推薦算法做了一定的改進(jìn)。首先,針對(duì)數(shù)據(jù)稀疏性問(wèn)題,本文提出了一種基于項(xiàng)目相似度學(xué)習(xí)的協(xié)同過(guò)濾推薦算法。該算法首先根據(jù)項(xiàng)目屬性相似性度量方法計(jì)算出所有項(xiàng)目的相似度矩陣,然后選取目標(biāo)項(xiàng)目的前K個(gè)最相似的項(xiàng)目作為其初始鄰近集;再將訓(xùn)練集中目標(biāo)項(xiàng)目的評(píng)分向量作為期望輸出,目標(biāo)項(xiàng)目的K個(gè)鄰近項(xiàng)目的評(píng)分向量輸入到RBF神經(jīng)網(wǎng)絡(luò)中進(jìn)行學(xué)習(xí),得到項(xiàng)目相似度訓(xùn)練模型;再將測(cè)試數(shù)據(jù)集中的目標(biāo)項(xiàng)目的K個(gè)鄰近項(xiàng)目的評(píng)分向量輸入訓(xùn)練模型,最后輸出目標(biāo)項(xiàng)目的預(yù)測(cè)評(píng)分向量。針對(duì)新項(xiàng)目冷啟動(dòng)問(wèn)題,我們計(jì)算出新加入項(xiàng)目與其他項(xiàng)目的屬性相似度,然后取出前K個(gè)最相似的項(xiàng)目構(gòu)成鄰近集并且計(jì)算出新加入項(xiàng)目的預(yù)測(cè)評(píng)分向量。最后取出對(duì)目標(biāo)項(xiàng)目評(píng)分大于等于3且分?jǐn)?shù)排在前N位的用戶,并將目標(biāo)項(xiàng)目推薦給這些用戶。其次,針對(duì)數(shù)據(jù)稀疏性和擴(kuò)展性問(wèn)題,本文提出了一種基于社交網(wǎng)絡(luò)和標(biāo)簽的協(xié)同過(guò)濾推薦算法。該算法將目標(biāo)用戶與他的朋友之間的信任度、熟悉度和標(biāo)簽信息反映的興趣偏好相似度結(jié)合起來(lái),計(jì)算出與他相似度較高的K個(gè)朋友作為鄰居集合,從而為目標(biāo)用戶推薦喜歡的項(xiàng)目;然后,針對(duì)新用戶冷啟動(dòng)問(wèn)題,提出了基于樸素貝葉斯算法的模型。它利用樸素貝葉斯算法對(duì)訓(xùn)練集中的用戶進(jìn)行分類(lèi),將新用戶劃分到所屬的類(lèi)別,即求出新用戶最喜歡的項(xiàng)目類(lèi)型,然后在這種類(lèi)型的項(xiàng)目里選擇評(píng)分最高的N個(gè)項(xiàng)目推薦給該用戶。最后,在Movielens數(shù)據(jù)集上實(shí)現(xiàn)基于項(xiàng)目相似度學(xué)習(xí)的協(xié)同過(guò)濾推薦算法,交叉實(shí)驗(yàn)表明,該算法在處理稀疏數(shù)據(jù)時(shí)表現(xiàn)出了較好的性能,并且得到了更準(zhǔn)確的推薦結(jié)果;在Last.fm數(shù)據(jù)集上實(shí)現(xiàn)基于社交網(wǎng)絡(luò)和標(biāo)簽的協(xié)同過(guò)濾推薦算法,與傳統(tǒng)的算法和一些經(jīng)典的算法相比,該算法具有較好的準(zhǔn)確性和高效性。最后,在Movielens數(shù)據(jù)集上驗(yàn)證了項(xiàng)目冷啟動(dòng)和用戶冷啟動(dòng)問(wèn)題,實(shí)驗(yàn)表明算法在一定程度上解決了冷啟動(dòng)問(wèn)題。
[Abstract]:With the development of the Internet, recommendation algorithms have been applied to many fields. Collaborative filtering recommendation algorithms are classic and widely used. However, the traditional collaborative filtering recommendation algorithms face many problems. The most serious problems are cold start problem, data sparse problem and expansibility problem. In this paper, some improvements are made to the traditional collaborative filtering recommendation algorithm. In this paper, a collaborative filtering recommendation algorithm based on item similarity learning is proposed. Then the first K similar items of the target item are selected as its initial adjacent set, and the score vector of the target item in the training set is taken as the expected output. The score vectors of K adjacent items of the target items are input into the RBF neural network for learning, and the item similarity training model is obtained, and then the score vectors of K adjacent items in the test data set are input into the training model. Finally, we output the prediction score vector of the target item. For the cold start problem of the new project, we calculate the attribute similarity between the new item and other items. Then take out the first K most similar items to form the adjacent set and calculate the predicted score vector for the new item. Finally, take out the user whose target item score is greater than or equal to 3 and scores in the top N position. Secondly, a collaborative filtering recommendation algorithm based on social networks and tags is proposed to solve the problem of data sparsity and scalability, which brings forward the trust between the target user and his friend. By combining familiarity with interest preference similarity reflected by label information, K friends with high similarity are calculated as neighbors to recommend favorite items for target users. This paper presents a model based on naive Bayes algorithm, which classifies users in training set and divides new users into categories, that is, to find out the type of items that new users like most. Finally, a collaborative filtering recommendation algorithm based on item similarity learning is implemented on the Movielens dataset. The algorithm shows better performance in dealing with sparse data and gets more accurate recommendation results, and implements collaborative filtering recommendation algorithm based on social networks and tags on Last.fm datasets. Compared with the traditional algorithm and some classical algorithms, this algorithm has better accuracy and high efficiency. Finally, the cold start problem of the project and the cold start problem of the user are verified on the Movielens data set. Experiments show that the algorithm solves the cold start problem to some extent.
【學(xué)位授予單位】：安徽大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 賀懷清;范志亮;劉浩翰;;基于網(wǎng)絡(luò)社區(qū)劃分的協(xié)同推薦算法[J];中國(guó)民航大學(xué)學(xué)報(bào);2016年05期

2 時(shí)念云;葛曉偉;馬力;;基于用戶人口統(tǒng)計(jì)特征與信任機(jī)制的協(xié)同推薦[J];計(jì)算機(jī)工程;2016年06期

3 王升升;趙海燕;陳慶奎;曹健;;個(gè)性化推薦中的隱語(yǔ)義模型[J];小型微型計(jì)算機(jī)系統(tǒng);2016年05期

4 王升升;趙海燕;陳慶奎;曹健;;基于社交標(biāo)簽和社交信任的概率矩陣分解推薦算法[J];小型微型計(jì)算機(jī)系統(tǒng);2016年05期

5 趙文濤;王春春;成亞飛;孟令軍;趙好好;;基于用戶多屬性與興趣的協(xié)同過(guò)濾算法[J];計(jì)算機(jī)應(yīng)用研究;2016年12期

6 韓亞楠;曹菡;劉亮亮;;基于評(píng)分矩陣填充與用戶興趣的協(xié)同過(guò)濾推薦算法[J];計(jì)算機(jī)工程;2016年01期

7 王夢(mèng)恬;魏晶晶;廖祥文;林錦賢;陳國(guó)龍;;融合評(píng)論標(biāo)簽的個(gè)性化推薦算法[J];計(jì)算機(jī)科學(xué)與探索;2016年10期

8 葉錫君;龔s，

本文編號(hào)：1547918