基于社會(huì)化媒體的若干興趣點(diǎn)推薦關(guān)鍵技術(shù)研究
發(fā)布時(shí)間：2019-01-28 13:04
【摘要】：隨著以Web2.0技術(shù)為基礎(chǔ)的社會(huì)化媒體的興起,基于位置的社交網(wǎng)絡(luò)(LBSN,Location Based Social Network)服務(wù)、各種移動(dòng)端社會(huì)化媒體的出現(xiàn)以及城市的快速發(fā)展,興趣點(diǎn)(POI,Point-of-Interest)的數(shù)量也隨之增長(zhǎng),人們通常喜歡探索城市與鄰近的地方,根據(jù)自已的個(gè)人興趣選擇與自已偏好相關(guān)的興趣點(diǎn)�；谖恢玫纳缃痪W(wǎng)絡(luò)為研究人們移動(dòng)行為提供了前所未有的機(jī)會(huì),用戶喜歡在這些基于位置的社交網(wǎng)絡(luò)平臺(tái)上,分享他們對(duì)各個(gè)地方的簽到記錄與興趣愛好,以及他們對(duì)服務(wù)、產(chǎn)品的評(píng)價(jià)與體驗(yàn),并且建立與維護(hù)他們的社會(huì)關(guān)系,從而展現(xiàn)自已的偏好與個(gè)性。這些基于位置的社交網(wǎng)絡(luò)的創(chuàng)建者也更加重視對(duì)用戶基礎(chǔ)數(shù)據(jù)和行為數(shù)據(jù)進(jìn)行采集、挖掘與分析,更好地理解用戶的移動(dòng)行為,從而更加了解他們的用戶,利用興趣點(diǎn)推薦改善用戶體驗(yàn)并滿足用戶需求。同時(shí)社會(huì)化媒體的興趣點(diǎn)推薦會(huì)面臨一些新的問題:如何綜合利用社會(huì)化媒體中的多樣數(shù)據(jù)?如何解決用戶簽到數(shù)據(jù)的稀疏性?如何處理隱式的用戶反饋與復(fù)雜的用戶關(guān)系?如何應(yīng)對(duì)用戶生成內(nèi)容的時(shí)效性?針對(duì)這些挑戰(zhàn),本文提出并設(shè)計(jì)一系列融合上下文信息的興趣點(diǎn)推薦算法,提高并改善社會(huì)化媒體中的興趣點(diǎn)推薦效果以及用戶體驗(yàn)。本文創(chuàng)新工作如下:1.基于位置社交網(wǎng)絡(luò)的上下文感知的興趣點(diǎn)推薦�；谖恢蒙缃痪W(wǎng)絡(luò)中的興趣點(diǎn)簽到矩陣是高稀疏的,用戶興趣隨著不同時(shí)間與地理位置是動(dòng)態(tài)變化的。針對(duì)此問題,本文提出一種上下文感知的概率矩陣分解興趣點(diǎn)推薦算法。首先利用潛在狄利克雷分配(LDA,Latent Dirichlet Allocation)模型挖掘興趣點(diǎn)相關(guān)的文本信息學(xué)習(xí)用戶的興趣話題生成興趣相關(guān)分?jǐn)?shù);其次提出一種自適應(yīng)帶寬核評(píng)估方法構(gòu)建地理相關(guān)性生成地理相關(guān)分?jǐn)?shù);然后通過用戶社會(huì)關(guān)系的冪律分布構(gòu)建社會(huì)相關(guān)性生成社會(huì)相關(guān)分?jǐn)?shù);結(jié)合用戶的分類偏好與興趣點(diǎn)的流行度構(gòu)建分類相關(guān)性生成分類相關(guān)分?jǐn)?shù);將這四種相關(guān)分?jǐn)?shù)進(jìn)行分?jǐn)?shù)匹配生成偏好分?jǐn)?shù);最后將其有效融合到概率矩陣分解模型(PMF, Probabilistic MatrixFactorization),生成用戶感興趣的興趣點(diǎn)推薦列表。實(shí)驗(yàn)結(jié)果表明,該模型明顯優(yōu)于先進(jìn)的NCPD算法,在Foursquare數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 27%和24%;在Twitter數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 26%和25%,顯著提高了興趣點(diǎn)推薦的精確度。2.基于用戶簽到行為的興趣點(diǎn)推薦。目前缺乏一種綜合分析地理影響、時(shí)間效應(yīng)、社會(huì)相關(guān)性、內(nèi)容信息和流行度影響這些因素共同作用的方法來(lái)處理興趣點(diǎn)推薦稀疏性問題,特別是異地推薦場(chǎng)景。針對(duì)此問題,本文提出一種聯(lián)合概率生成模型,第一個(gè)同時(shí)將上述因素進(jìn)行有效融合的聯(lián)合效應(yīng)模型,模擬用戶簽到行為的決策過程,利用地理相關(guān)性設(shè)計(jì)一個(gè)良好的空間索引結(jié)構(gòu)即空間金字塔,對(duì)當(dāng)?shù)仄眠M(jìn)行平滑優(yōu)化,進(jìn)一步緩解數(shù)據(jù)稀疏問題。該模型包括離線模型和在線推薦兩個(gè)部分,支持本地和異地兩種推薦場(chǎng)景,并利用一個(gè)可擴(kuò)展的查詢過程技術(shù)閾值算法加速在線推薦過程。實(shí)驗(yàn)結(jié)果表明該模型明顯優(yōu)于先進(jìn)的SVDFeature算法,異地推薦場(chǎng)景中,在Foursquare數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 24%和26%,在Twitter數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 21%和23%,在豆瓣數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 22%和24%;本地推薦場(chǎng)景中,在Foursquare數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 14%和16%,在Twitter數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 23%和20%,在豆瓣數(shù)據(jù)集上,準(zhǔn)確率和召回率分別提高了 15%和17%,顯著提高了興趣點(diǎn)推薦的精確度。3.基于社會(huì)化媒體挖掘與可視化的興趣點(diǎn)推薦。社會(huì)化媒體的社交網(wǎng)絡(luò)中,圖像還沒有很好地被利用到興趣點(diǎn)推薦研究。針對(duì)此問題,本文提出一種社會(huì)化媒體主題模型,充分利用Twitter的文本、圖像、位置、時(shí)間和哈希標(biāo)簽這五個(gè)特征之間的內(nèi)在關(guān)聯(lián)性構(gòu)建一個(gè)聯(lián)合概率生成模型。并研究Twitter上的圖像對(duì)興趣點(diǎn)推薦的影響,解決噪聲圖像問題,預(yù)先定義三個(gè)標(biāo)準(zhǔn):可視化一致性、可視化相關(guān)性與可視化多樣性,利用卷積神經(jīng)網(wǎng)絡(luò)(CNN, Convolutional Neural Network)選擇代表性的圖像對(duì)興趣點(diǎn)進(jìn)行可視化。實(shí)驗(yàn)結(jié)果表明,該模型明顯優(yōu)于先進(jìn)的TRM算法,在Twitter數(shù)據(jù)集上,平均準(zhǔn)確率提高了 22%,顯著提高了興趣點(diǎn)推薦的精確度。
[Abstract]:With the rise of the social media based on the Web 2.0 technology, the location-based social network (LBSN, Location Based Social Network) service, the emergence of various mobile-end social media and the rapid development of the city, the number of points of interest (POI, Point-of-Interest) has also increased, People often like to explore cities and nearby places, and choose the points of interest related to their own preferences based on their personal interests. The location-based social network provides unprecedented opportunities for the study of people's mobile behavior, and users like to share their location-based social networking platforms, share their sign-in records and interests at various places, and their evaluation and experience of services, products, and establish and maintain their social relations so as to show their own preferences and personalities. The creators of these location-based social networks also pay more attention to the collection, mining, and analysis of user-based data and behavior data, to better understand the user's mobile behavior, to better understand their users, to use the point of interest to recommend to improve the user experience and to meet the user's needs. At the same time, the point of interest of the social media is recommended to face some new problems: how to make comprehensive use of the diverse data in the social media? How to solve the sparsity of user sign-in data? How to handle implicit user feedback and complex user relations? How to deal with the timeliness of user-generated content? In view of these challenges, a series of point-of-interest recommendation algorithms for integrating context information are proposed and designed, and the recommendation effect and user experience of the interest point in the social media are improved and improved. The innovative work of this paper is as follows: 1. A location-based social network-based context-aware point of interest recommendation. The sign-in matrix of the point of interest in the location-based social network is highly sparse, and the user's interest is dynamically changed with the different time and the geographic location. In this paper, a context-aware probability matrix decomposition point-of-interest recommendation algorithm is presented in this paper. firstly, using a potential Dirichlet allocation (LDA) model to mine the interest point-related text information to study the interest topic of the user to generate an interest-related score; secondly, a self-adaptive bandwidth core evaluation method is proposed to construct a geographic correlation to generate a geographic correlation score; then building a social correlation to generate a social correlation score through the power law distribution of the social relation of the user; building a classification correlation score according to the popularity of the user's classification preference and the popularity of the interest point; and carrying out score matching on the four related scores to generate a preference score; Finally, it is effectively fused to the probability matrix decomposition model (PMF, Probabble MatrixFactorization) to generate a list of the recommended points of interest for the user. The experimental results show that the model is better than the advanced NCPD algorithm, and the accuracy and recall rate are increased by 27% and 24% respectively on the Foursquare data set, and the accuracy and recall rate are increased by 26% and 25% respectively on the Twitter data set, and the recommended accuracy of the point of interest is significantly improved. Recommendation for the point of interest based on the user's sign-in behavior. At present, there is a lack of a method to comprehensively analyze the geographical influence, time effect, social relevance, content information and popularity influence the common function of these factors to treat the point of interest and to recommend the sparsity problem, in particular to the recommendation scene in different places. In order to solve this problem, a joint probability generation model is proposed, the first is the combined effect model of the effective fusion of the above factors, the decision-making process of the user sign-in behavior is simulated, and a good spatial index structure, i.e. the spatial pyramid, is designed by using the geographic relevance. The local preference is optimized to further alleviate the data sparse problem. The model includes the off-line model and the on-line recommendation two parts, supports both local and off-site recommendation scenarios, and uses an extensible query process technology threshold algorithm to accelerate the on-line recommendation process. The experimental results show that the model is superior to the advanced SVDFeature algorithm, and the accuracy and recall rate are increased by 24% and 26% respectively on the Foursquare data set, and the accuracy and recall rate are increased by 21% and 23% on the Twitter data set, respectively. The accuracy and recall rate increased by 22% and 24%, respectively. In the local recommendation scenario, the accuracy and recall rate increased by 14% and 16% respectively on the Foursquare data set, and the accuracy and recall rate were increased by 23% and 20% on the Twitter data set, respectively. The accuracy and recall rate increased by 15% and 17%, respectively, and the recommended accuracy of the point of interest was significantly improved. The recommendation of the interest point based on the social media mining and visualization. In the social network of the social media, the image has not been well used to the point of interest recommendation study. In order to solve this problem, this paper proposes a social media subject model, and makes full use of the inherent relationship between the five features of the text, image, location, time and hash tag of Twitter to construct a joint probability generation model. In this paper, the effect of the image on the recommendation of the point of interest is studied, the problem of the noise image is solved, and the three criteria are defined in advance: the visual consistency, the visual correlation and the visual diversity, and the representative image is selected by the convolution neural network (CNN, Convolutional Neural Network) to visualize the points of interest. The experimental results show that the model is better than the advanced TRM algorithm. On the Twitter data set, the average accuracy of the model is increased by 22%, and the recommended accuracy of the point of interest is significantly improved.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3
本文編號(hào)：2417093
[Abstract]:With the rise of the social media based on the Web 2.0 technology, the location-based social network (LBSN, Location Based Social Network) service, the emergence of various mobile-end social media and the rapid development of the city, the number of points of interest (POI, Point-of-Interest) has also increased, People often like to explore cities and nearby places, and choose the points of interest related to their own preferences based on their personal interests. The location-based social network provides unprecedented opportunities for the study of people's mobile behavior, and users like to share their location-based social networking platforms, share their sign-in records and interests at various places, and their evaluation and experience of services, products, and establish and maintain their social relations so as to show their own preferences and personalities. The creators of these location-based social networks also pay more attention to the collection, mining, and analysis of user-based data and behavior data, to better understand the user's mobile behavior, to better understand their users, to use the point of interest to recommend to improve the user experience and to meet the user's needs. At the same time, the point of interest of the social media is recommended to face some new problems: how to make comprehensive use of the diverse data in the social media? How to solve the sparsity of user sign-in data? How to handle implicit user feedback and complex user relations? How to deal with the timeliness of user-generated content? In view of these challenges, a series of point-of-interest recommendation algorithms for integrating context information are proposed and designed, and the recommendation effect and user experience of the interest point in the social media are improved and improved. The innovative work of this paper is as follows: 1. A location-based social network-based context-aware point of interest recommendation. The sign-in matrix of the point of interest in the location-based social network is highly sparse, and the user's interest is dynamically changed with the different time and the geographic location. In this paper, a context-aware probability matrix decomposition point-of-interest recommendation algorithm is presented in this paper. firstly, using a potential Dirichlet allocation (LDA) model to mine the interest point-related text information to study the interest topic of the user to generate an interest-related score; secondly, a self-adaptive bandwidth core evaluation method is proposed to construct a geographic correlation to generate a geographic correlation score; then building a social correlation to generate a social correlation score through the power law distribution of the social relation of the user; building a classification correlation score according to the popularity of the user's classification preference and the popularity of the interest point; and carrying out score matching on the four related scores to generate a preference score; Finally, it is effectively fused to the probability matrix decomposition model (PMF, Probabble MatrixFactorization) to generate a list of the recommended points of interest for the user. The experimental results show that the model is better than the advanced NCPD algorithm, and the accuracy and recall rate are increased by 27% and 24% respectively on the Foursquare data set, and the accuracy and recall rate are increased by 26% and 25% respectively on the Twitter data set, and the recommended accuracy of the point of interest is significantly improved. Recommendation for the point of interest based on the user's sign-in behavior. At present, there is a lack of a method to comprehensively analyze the geographical influence, time effect, social relevance, content information and popularity influence the common function of these factors to treat the point of interest and to recommend the sparsity problem, in particular to the recommendation scene in different places. In order to solve this problem, a joint probability generation model is proposed, the first is the combined effect model of the effective fusion of the above factors, the decision-making process of the user sign-in behavior is simulated, and a good spatial index structure, i.e. the spatial pyramid, is designed by using the geographic relevance. The local preference is optimized to further alleviate the data sparse problem. The model includes the off-line model and the on-line recommendation two parts, supports both local and off-site recommendation scenarios, and uses an extensible query process technology threshold algorithm to accelerate the on-line recommendation process. The experimental results show that the model is superior to the advanced SVDFeature algorithm, and the accuracy and recall rate are increased by 24% and 26% respectively on the Foursquare data set, and the accuracy and recall rate are increased by 21% and 23% on the Twitter data set, respectively. The accuracy and recall rate increased by 22% and 24%, respectively. In the local recommendation scenario, the accuracy and recall rate increased by 14% and 16% respectively on the Foursquare data set, and the accuracy and recall rate were increased by 23% and 20% on the Twitter data set, respectively. The accuracy and recall rate increased by 15% and 17%, respectively, and the recommended accuracy of the point of interest was significantly improved. The recommendation of the interest point based on the social media mining and visualization. In the social network of the social media, the image has not been well used to the point of interest recommendation study. In order to solve this problem, this paper proposes a social media subject model, and makes full use of the inherent relationship between the five features of the text, image, location, time and hash tag of Twitter to construct a joint probability generation model. In this paper, the effect of the image on the recommendation of the point of interest is studied, the problem of the noise image is solved, and the three criteria are defined in advance: the visual consistency, the visual correlation and the visual diversity, and the representative image is selected by the convolution neural network (CNN, Convolutional Neural Network) to visualize the points of interest. The experimental results show that the model is better than the advanced TRM algorithm. On the Twitter data set, the average accuracy of the model is increased by 22%, and the recommended accuracy of the point of interest is significantly improved.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.3
【參考文獻(xiàn)】
相關(guān)博士學(xué)位論文 前1條
1 陰紅志;社會(huì)化媒體中若干時(shí)空相關(guān)的推薦問題研究[D];北京大學(xué);2014年
，本文編號(hào)：2417093
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2417093.html
最近更新
教材專著
