基于標(biāo)簽關(guān)聯(lián)規(guī)則的協(xié)同過濾算法研究
發(fā)布時(shí)間：2018-12-10 07:23
【摘要】：隨著互聯(lián)網(wǎng)的快速普及,信息檢索工具的發(fā)展經(jīng)歷了三個(gè)階段:從分類導(dǎo)航到搜索引擎,再到現(xiàn)在的推薦系統(tǒng)。推薦系統(tǒng)及相關(guān)推薦技術(shù)已經(jīng)不知不覺中深入了人們的生活中,無論是視頻網(wǎng)站、音樂網(wǎng)站或APP、社交網(wǎng)站、甚至是平日瀏覽的新聞網(wǎng)站都離不開推薦技術(shù),處處能看到推薦技術(shù)的痕跡。傳統(tǒng)的基于協(xié)同過濾推薦算法存在很多的缺陷,如稀疏性問題、冷啟動(dòng)問題、可擴(kuò)展性問題、用戶多興趣問題等等。協(xié)同過濾算法只考慮用戶間或項(xiàng)目間的相似性來給用戶進(jìn)行推薦,忽略了用戶對(duì)項(xiàng)目的主觀感受。隨著Web2.0的發(fā)展,在社會(huì)化標(biāo)注系統(tǒng)中加入的標(biāo)簽(TAG)元素為用戶提供了一種新的方式來表達(dá)對(duì)項(xiàng)目的主觀感受。標(biāo)簽體現(xiàn)了用戶對(duì)項(xiàng)目的觀點(diǎn)和用戶的興趣,而且也實(shí)現(xiàn)了對(duì)項(xiàng)目內(nèi)容相對(duì)精確的描述。通過對(duì)用戶產(chǎn)生的內(nèi)容(UGC)來對(duì)互聯(lián)網(wǎng)中的戶進(jìn)行社會(huì)興趣挖掘具有非常重要的意義。本文提出了一種引入用戶自定義標(biāo)簽內(nèi)容的基于標(biāo)簽關(guān)聯(lián)規(guī)則的協(xié)同過濾算法。算法在對(duì)評(píng)分矩陣填充的過程中引用了基于項(xiàng)目的協(xié)同過濾方法,有效的解決了傳統(tǒng)的協(xié)同過濾算法的稀疏性問題。接著對(duì)用戶的相似度的計(jì)算進(jìn)行了改進(jìn),引入了用戶關(guān)注度矩陣,對(duì)用戶評(píng)分相似度和用戶關(guān)注度相似度兩部分相似度進(jìn)行了改進(jìn)。在這里我們引入Apriori關(guān)聯(lián)規(guī)則中計(jì)算頻繁項(xiàng)集的思想,訓(xùn)練出合適的最小支持度閾值,求出頻繁項(xiàng)集,對(duì)頻繁項(xiàng)集分解得到用戶興趣點(diǎn),再逆向遍歷用戶集合,按照用戶興趣點(diǎn)對(duì)用戶進(jìn)行聚類。得到用戶聚類后,按照前面介紹的改進(jìn)的用戶相似度方法,求出最近鄰居用戶集合,進(jìn)而求出用戶對(duì)項(xiàng)目的預(yù)測(cè)評(píng)分,最后將結(jié)果推薦給用戶。實(shí)驗(yàn)采用MovieLens電影評(píng)分?jǐn)?shù)據(jù)集,通過一系列的實(shí)驗(yàn)對(duì)各推薦算法進(jìn)行對(duì)比。實(shí)驗(yàn)表明該方法能有效的降低評(píng)分矩陣稀疏帶來的影響,提高了預(yù)測(cè)精度。
[Abstract]:With the rapid popularization of the Internet, the development of information retrieval tools has experienced three stages: from classification navigation to search engine, and then to the present recommendation system. Recommendation systems and related recommendation technologies have unconsciously penetrated into people's lives, whether it is video sites, music sites or APP, social networking sites, or even the news sites that they visit all the time are inseparable from the recommendation technology. Everywhere you can see the traces of recommended technology. The traditional collaborative filtering recommendation algorithm has many defects, such as sparse problem, cold start problem, scalability problem, user multi-interest problem and so on. Collaborative filtering algorithm only considers the similarity between users or items to recommend to users, ignoring the subjective feelings of users. With the development of Web2.0, the tag (TAG) element added in the social tagging system provides a new way for users to express their subjective feelings about the project. Tags reflect the user's view and interest in the project, and also achieve a relatively accurate description of the project content. It is of great significance to mine the social interest of the users through the user generated content (UGC). A collaborative filtering algorithm based on tag association rules is proposed in this paper. In the process of filling the scoring matrix, the algorithm uses the item-based collaborative filtering method, which effectively solves the sparse problem of the traditional collaborative filtering algorithm. Then, the user similarity calculation is improved, user attention matrix is introduced, and the user score similarity and user concern similarity are improved. In this paper, we introduce the idea of calculating frequent itemsets in Apriori association rules, train appropriate minimum support threshold, find frequent itemsets, decompose frequent itemsets to get user interest points, and then traverse user sets backwards. Cluster the users according to the points of interest. After the user clustering is obtained, the nearest neighbor user set is obtained according to the improved user similarity method, and then the forecast score of the user is obtained. Finally, the result is recommended to the user. The experiment adopts MovieLens film score data set, and compares each recommendation algorithm through a series of experiments. Experiments show that this method can effectively reduce the impact of sparse scoring matrix and improve the prediction accuracy.
【學(xué)位授予單位】：河北工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.3
本文編號(hào)：2370191
[Abstract]:With the rapid popularization of the Internet, the development of information retrieval tools has experienced three stages: from classification navigation to search engine, and then to the present recommendation system. Recommendation systems and related recommendation technologies have unconsciously penetrated into people's lives, whether it is video sites, music sites or APP, social networking sites, or even the news sites that they visit all the time are inseparable from the recommendation technology. Everywhere you can see the traces of recommended technology. The traditional collaborative filtering recommendation algorithm has many defects, such as sparse problem, cold start problem, scalability problem, user multi-interest problem and so on. Collaborative filtering algorithm only considers the similarity between users or items to recommend to users, ignoring the subjective feelings of users. With the development of Web2.0, the tag (TAG) element added in the social tagging system provides a new way for users to express their subjective feelings about the project. Tags reflect the user's view and interest in the project, and also achieve a relatively accurate description of the project content. It is of great significance to mine the social interest of the users through the user generated content (UGC). A collaborative filtering algorithm based on tag association rules is proposed in this paper. In the process of filling the scoring matrix, the algorithm uses the item-based collaborative filtering method, which effectively solves the sparse problem of the traditional collaborative filtering algorithm. Then, the user similarity calculation is improved, user attention matrix is introduced, and the user score similarity and user concern similarity are improved. In this paper, we introduce the idea of calculating frequent itemsets in Apriori association rules, train appropriate minimum support threshold, find frequent itemsets, decompose frequent itemsets to get user interest points, and then traverse user sets backwards. Cluster the users according to the points of interest. After the user clustering is obtained, the nearest neighbor user set is obtained according to the improved user similarity method, and then the forecast score of the user is obtained. Finally, the result is recommended to the user. The experiment adopts MovieLens film score data set, and compares each recommendation algorithm through a series of experiments. Experiments show that this method can effectively reduce the impact of sparse scoring matrix and improve the prediction accuracy.
【學(xué)位授予單位】：河北工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.3
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 盈艷;曹妍;牟向偉;;基于項(xiàng)目評(píng)分預(yù)測(cè)的混合式協(xié)同過濾推薦[J];現(xiàn)代圖書情報(bào)技術(shù);2015年06期
2 孫光福;吳樂;劉淇;朱琛;陳恩紅;;基于時(shí)序行為的協(xié)同過濾推薦算法[J];軟件學(xué)報(bào);2013年11期
3 楊晶;成衛(wèi)青;郭常忠;;基于標(biāo)準(zhǔn)標(biāo)簽的用戶興趣模型研究[J];計(jì)算機(jī)技術(shù)與發(fā)展;2013年10期
4 朱麗中;徐秀娟;劉宇;;基于項(xiàng)目和信任的協(xié)同過濾推薦算法[J];計(jì)算機(jī)工程;2013年01期
5 彭石;周志彬;王國軍;;基于評(píng)分矩陣預(yù)填充的協(xié)同過濾算法[J];計(jì)算機(jī)工程;2013年01期
6 楊陽;向陽;熊磊;;基于矩陣分解與用戶近鄰模型的協(xié)同過濾推薦算法[J];計(jì)算機(jī)應(yīng)用;2012年02期
7 李改;李磊;;基于矩陣分解的協(xié)同過濾算法[J];計(jì)算機(jī)工程與應(yīng)用;2011年30期
8 劉旭東;陳德人;王惠敏;;一種改進(jìn)的協(xié)同過濾推薦算法[J];武漢理工大學(xué)學(xué)報(bào)(信息與管理工程版);2010年04期
9 馬宏偉;張光衛(wèi);李鵬;;協(xié)同過濾推薦算法綜述[J];小型微型計(jì)算機(jī)系統(tǒng);2009年07期
10 查文琴;梁昌勇;曹鐳;;基于用戶聚類的協(xié)同過濾推薦方法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2009年06期
，本文編號(hào)：2370191
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2370191.html
最近更新
教材專著
