發(fā)布時(shí)間：2018-04-08 19:15

  本文選題：新聞推薦　切入點(diǎn)：推薦系統(tǒng)　出處：《北京交通大學(xué)》2017年碩士論文

【摘要】：信息的指數(shù)爆炸帶來(lái)了信息過(guò)載問(wèn)題,從而產(chǎn)生了分類(lèi)目錄技術(shù)和搜索引擎技術(shù),然而分類(lèi)目錄只能覆蓋熱門(mén)分類(lèi),搜索引擎只能由用戶(hù)主動(dòng)輸入關(guān)鍵詞檢索信息,于是個(gè)性化新聞推薦系統(tǒng)應(yīng)運(yùn)而生。單一的算法很難從多個(gè)角度為用戶(hù)進(jìn)行推薦,易導(dǎo)致推薦結(jié)果多樣性欠缺。為提高推薦的準(zhǔn)確率和多樣性,本文就目前已有的推薦算法展開(kāi)研究,結(jié)合傳統(tǒng)的推薦技術(shù)設(shè)計(jì)了混合加權(quán)的新聞推薦策略,將基于內(nèi)容的推薦算法和基于用戶(hù)的協(xié)同過(guò)濾算法按不同權(quán)重進(jìn)行加權(quán)混合,使之達(dá)到取長(zhǎng)補(bǔ)短的目的,提高了推薦結(jié)果的準(zhǔn)確性,更好的為用戶(hù)進(jìn)行個(gè)性化的新聞推薦。本文將新聞內(nèi)容建模、用戶(hù)興趣建模和混合算法建模三部分作為推薦系統(tǒng)的核心內(nèi)容。對(duì)于新聞內(nèi)容建模,首先介紹了新聞文本預(yù)處理的相關(guān)理論,針對(duì)新聞內(nèi)容的特點(diǎn),采取線性加權(quán)的方式進(jìn)行新聞關(guān)鍵詞的提取,并使用支持向量機(jī)實(shí)現(xiàn)了對(duì)新聞的分類(lèi);對(duì)于用戶(hù)興趣建模,通過(guò)對(duì)用戶(hù)行為日志的收集,分析用戶(hù)的新聞瀏覽偏好,進(jìn)而完成對(duì)用戶(hù)興趣模型的建立與更新;對(duì)于混合算法建模,基于內(nèi)容的推薦算法主要通過(guò)計(jì)算新聞內(nèi)容向量和用戶(hù)興趣向量的夾角余弦相似度確定新聞推薦列表,基于用戶(hù)的協(xié)同過(guò)濾算法通過(guò)建立用戶(hù)相似度矩陣來(lái)推薦相似用戶(hù)喜歡的新聞,然后將兩者召回的結(jié)果按不同權(quán)值進(jìn)行加權(quán)混合,并通過(guò)多次訓(xùn)練得出加權(quán)效果最好的權(quán)值比,確保推薦系統(tǒng)的準(zhǔn)確性。另外還設(shè)置了新聞時(shí)間閥值,對(duì)推薦返回的結(jié)果進(jìn)行適當(dāng)過(guò)濾,在一定程度上保障了推薦結(jié)果的時(shí)效性。論文首先通過(guò)介紹系統(tǒng)的背景意義及國(guó)內(nèi)外研究現(xiàn)狀確立了基本工作內(nèi)容,然后就典型推薦算法進(jìn)行詳細(xì)描述,分析了系統(tǒng)需求。針對(duì)新聞推薦系統(tǒng)數(shù)據(jù)規(guī)模大、用戶(hù)興趣時(shí)效性高等需求,構(gòu)建了本系統(tǒng),勾勒出實(shí)時(shí)新聞推薦系統(tǒng)的框架,然后敘述了推薦系統(tǒng)的總體設(shè)計(jì),并對(duì)系統(tǒng)的架構(gòu)及關(guān)鍵模塊的實(shí)現(xiàn)過(guò)程進(jìn)行了詳細(xì)分析,為用戶(hù)提供了更加個(gè)性化、實(shí)時(shí)化的新聞推薦。
[Abstract]:The exponential explosion of information brings about the problem of information overload, which leads to the classification catalogue technology and search engine technology. However, the classified directory can only cover the popular classification, and the search engine can only input the keyword information actively by the user.So personalized news recommendation system came into being.It is difficult for a single algorithm to recommend users from multiple angles, which leads to the lack of diversity of recommendation results.In order to improve the accuracy and diversity of recommendation, this paper studies the existing recommendation algorithms and designs a mixed weighted news recommendation strategy combined with traditional recommendation technology.The content-based recommendation algorithm and the user-based collaborative filtering algorithm are weighted according to different weights to achieve the purpose of complementing each other, improving the accuracy of the recommendation results and making personalized news recommendations for usersIn this paper, news content modeling, user interest modeling and hybrid algorithm modeling are taken as the core contents of recommendation system.For news content modeling, this paper first introduces the relevant theory of news text preprocessing, according to the characteristics of news content, adopts the method of linear weighting to extract news keywords, and uses support vector machine to realize the classification of news.For user interest modeling, through collecting user behavior log, analyzing user's news browsing preference, and then completing the establishment and updating of user interest model; for hybrid algorithm modeling,The content-based recommendation algorithm determines the news recommendation list by calculating the angle cosine similarity between the news content vector and the user's interest vector.Based on the user collaborative filtering algorithm, the user similarity matrix is established to recommend the news that similar users like, and then the recall results are weighted and mixed according to different weights, and the weight value ratio with the best weighting effect is obtained through multiple training.Ensure the accuracy of the recommendation system.In addition, the news time threshold is set and the recommended return results are filtered properly to ensure the timeliness of the recommended results to a certain extent.This paper first introduces the background significance of the system and the current research situation at home and abroad to establish the basic work content, then describes the typical recommendation algorithm in detail, and analyzes the system requirements.Aiming at the large scale of news recommendation system and the high demand of user interest, this paper constructs the system, outlines the frame of the real-time news recommendation system, and then describes the overall design of the recommendation system.The architecture of the system and the implementation process of the key modules are analyzed in detail, which provides users with more personalized and real-time news recommendation.
【學(xué)位授予單位】：北京交通大學(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9條

1 王慶福;;推薦系統(tǒng)架構(gòu)設(shè)計(jì)研究[J];信息通信;2016年07期

2 劉楊;楊明川;;推薦引擎原理及發(fā)展綜述[J];電信技術(shù);2015年06期

3 李瓊;陳利;;一種改進(jìn)的支持向量機(jī)文本分類(lèi)方法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2015年05期

4 黎佳;;淺談中文切詞算法[J];軟件;2013年07期

5 孫雨生;劉偉;仇蓉蓉;黃傳慧;;國(guó)內(nèi)用戶(hù)興趣建模研究進(jìn)展[J];情報(bào)雜志;2013年05期

6 陸麗;;需求分析在軟件開(kāi)發(fā)過(guò)程中的重要性[J];電腦知識(shí)與技術(shù);2012年21期

7 夏建勛;;基于用戶(hù)的協(xié)同過(guò)濾推薦技術(shù)[J];商場(chǎng)現(xiàn)代化;2009年09期

8 李書(shū)寧;互聯(lián)網(wǎng)信息環(huán)境中信息超載問(wèn)題研究[J];情報(bào)科學(xué);2005年10期

9 代六玲,黃河燕,陳肇雄;中文文本分類(lèi)中特征抽取方法的比較研究[J];中文信息學(xué)報(bào);2004年01期

相關(guān)碩士學(xué)位論文 前4條

1 陳恭泳;個(gè)性化混合推薦算法及應(yīng)用研究[D];中央民族大學(xué);2016年

2 王星星;基于網(wǎng)絡(luò)熱點(diǎn)的個(gè)性化情報(bào)推薦系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)[D];華中師范大學(xué);2014年

3 曹昱翔;智慧商圈中基于個(gè)性化建模的混合推薦技術(shù)的研究與實(shí)現(xiàn)[D];上海交通大學(xué);2014年

4 李春城;個(gè)性化推薦系統(tǒng)在牛贊網(wǎng)中的應(yīng)用[D];電子科技大學(xué);2013年

，

本文編號(hào)：1722992