本文選題：活動(dòng)社交網(wǎng)絡(luò) + 推薦方法　； 參考：《西南大學(xué)》2017年碩士論文

【摘要】：伴隨著互聯(lián)網(wǎng)的快速發(fā)展與互聯(lián)網(wǎng)技術(shù)的不斷創(chuàng)新,社交網(wǎng)絡(luò)日益成熟和完善。在眾多的社交網(wǎng)絡(luò)類型中,有一種以活動(dòng)為媒介將線上與線下相結(jié)合的社交網(wǎng)絡(luò)——活動(dòng)社交網(wǎng)絡(luò)(Event-based Social Network,EBSN)。和傳統(tǒng)的社交網(wǎng)絡(luò)相比,活動(dòng)社交網(wǎng)絡(luò)中的用戶既可以線上瀏覽活動(dòng)信息,又有可以根據(jù)活動(dòng)信息決定是否線下參加該活動(dòng)。隨著時(shí)間的推移和網(wǎng)絡(luò)的發(fā)展,活動(dòng)社交網(wǎng)絡(luò)中產(chǎn)生的海量數(shù)據(jù)使得用戶難以快速找到自己感興趣的活動(dòng)。因此,急需基于活動(dòng)社交網(wǎng)絡(luò)的推薦系統(tǒng)來為用戶做活動(dòng)推薦,提高用戶體驗(yàn)。社交活動(dòng)推薦與傳統(tǒng)的推薦有所不同,主要有:(1)活動(dòng)的“一次性消費(fèi)”特性。活動(dòng)是人為發(fā)起的,具有特定主題、時(shí)間、地點(diǎn),用戶只能參加一次,無法像商品一樣反復(fù)購買,且沒有歷史評(píng)價(jià)記錄。(2)活動(dòng)社交網(wǎng)絡(luò)中有更多的信息可用于推薦�；顒�(dòng)社交網(wǎng)絡(luò)可以形成兩種社交關(guān)系,一種是用戶通過加入興趣小組等形成的線上社交關(guān)系,另一種是用戶通過參與相同的社交活動(dòng)而形成的線下社交關(guān)系。此外,還有用戶和活動(dòng)的時(shí)間、地理位置等信息。這些不同使得活動(dòng)推薦不能直接采用傳統(tǒng)的推薦方法,因此本文研究社交活動(dòng)推薦。本文針對(duì)上述特點(diǎn)和現(xiàn)有的社交活動(dòng)推薦中存在不足之處,在已有的推薦相關(guān)理論與技術(shù)的基礎(chǔ)上,給出了本文的基于社交網(wǎng)絡(luò)的同城活動(dòng)推薦方法并對(duì)其進(jìn)行有效性驗(yàn)證。本文的主要工作包括:(1)給出了一種基于社交網(wǎng)絡(luò)的同城活動(dòng)推薦模型。模型包括數(shù)據(jù)獲取模塊、特征提取模塊、學(xué)習(xí)排序模塊和推薦模塊。數(shù)據(jù)獲取模塊解決數(shù)據(jù)獲取問題,并將數(shù)據(jù)分為訓(xùn)練數(shù)據(jù)和待推薦數(shù)據(jù)。特征提取模塊是分析數(shù)據(jù)信息,提取出用戶偏好、好友影響、時(shí)間匹配度、位置匹配度、活動(dòng)主題流行度五個(gè)特征。學(xué)習(xí)排序模塊是將推薦問題轉(zhuǎn)化為學(xué)習(xí)排序問題,通過對(duì)活動(dòng)進(jìn)行學(xué)習(xí)排序,得到衡量所有特征的最優(yōu)權(quán)重W。推薦模塊是根據(jù)用戶IP判斷用戶城市,從而選擇用戶的候選活動(dòng),根據(jù)最優(yōu)權(quán)重W計(jì)算出用戶對(duì)候選活動(dòng)的評(píng)分,根據(jù)評(píng)分為用戶推薦top-N的活動(dòng)。(2)分析并提取了用戶偏好、好友影響、時(shí)間匹配度、位置匹配度、活動(dòng)主題流行度五個(gè)特征,并給出各個(gè)特征的計(jì)算方法。用戶偏好采用基于內(nèi)容的推薦方法,計(jì)算出用戶與活動(dòng)在主題向量的相似度。使用LDA方法表示對(duì)用戶和活動(dòng)主題向量,降低了文本維度,緩解了數(shù)據(jù)稀疏問題。好友影響采用協(xié)同過濾方法,將用戶偏好視為用戶評(píng)分,同時(shí)將與用戶主題相似度最高的K個(gè)用戶視為其好友。時(shí)間匹配度和位置匹配度分別挖掘用戶在時(shí)間和位置特征上的行為規(guī)律,計(jì)算用戶和活動(dòng)在時(shí)間與位置上的相似度�；顒�(dòng)主題流行度這一特征是為了衡量活動(dòng)主題與城市流行主題之間的相似度,城市流行主題是指該城市近期的參與度最高的M個(gè)活動(dòng)的主題。同時(shí),活動(dòng)主題流行度可以在一定程度上可以降低冷啟動(dòng)問題對(duì)活動(dòng)推薦的影響。(3)給出了一種基于社交網(wǎng)絡(luò)的同城活動(dòng)推薦算法。將活動(dòng)推薦問題轉(zhuǎn)化為學(xué)習(xí)排序問題,并借助成對(duì)學(xué)習(xí)排序的思想,將活動(dòng)組成序列對(duì),分為正序列對(duì)和負(fù)序列對(duì),從而將問題轉(zhuǎn)化為針對(duì)活動(dòng)序列對(duì)的二分分類問題。為綜合考慮各個(gè)特征的影響,本文對(duì)邏輯回歸方法進(jìn)行改進(jìn),使其適用于成對(duì)學(xué)習(xí)排序問題。采用平方損失作為損失函數(shù),在求解過程中,采用批梯度下降法進(jìn)行求解,并為損失函數(shù)添加正則化項(xiàng)以防止過擬合,同時(shí)添加用戶系數(shù)以調(diào)節(jié)用戶數(shù)據(jù)不均衡帶來的影響。本文的活動(dòng)推薦方法是:采用改進(jìn)的邏輯回歸排序方法融合用戶偏好、好友影響、時(shí)間匹配度、位置匹配度、活動(dòng)主題流行度五個(gè)特征,計(jì)算出用戶對(duì)候選活動(dòng)的綜合評(píng)分,并以此進(jìn)行活動(dòng)推薦。為驗(yàn)證本文給出的方法的有效性,實(shí)驗(yàn)選取準(zhǔn)確率和召回率作為推薦結(jié)果評(píng)估指標(biāo),利用豆瓣同城中的數(shù)據(jù),與現(xiàn)有的常用的幾種活動(dòng)推薦方法進(jìn)行對(duì)比分析。實(shí)驗(yàn)結(jié)果表明:相對(duì)于單一特征的推薦方法,本文的融合了多特征的活動(dòng)推薦方法效果更好;相對(duì)于其他四種經(jīng)典的活動(dòng)推薦方法,本文的改進(jìn)的邏輯回歸排序的活動(dòng)推薦方法效果更好,能夠更有效地為用戶進(jìn)行活動(dòng)推薦,提高用戶的體驗(yàn),滿足用戶需求。
[Abstract]:With the rapid development of the Internet and the continuous innovation of Internet technology, social networks are increasingly mature and perfect. In many social network types, there is a social network (Event-based Social Network, EBSN) that combines online and offline with activity as a medium. Users in social networks can not only browse activities online, but also decide whether to take part in the activity according to the activity information. As time goes on and the network develops, the mass data produced in the social network makes it difficult for users to find their own activities quickly. Therefore, the active social network is urgently needed. Recommending systems to recommend activities for users to improve user experience. Social activities recommendation is different from traditional recommendations, mainly: (1) the "one-time consumption" feature of activities. Activities are initiated by people, with specific topics, time, locations, users can only take part in one time, can not be purchased as repeatedly as a commodity, and there is no historical evaluation (2) active social networks have more information to recommend. Active social networks can form two social relationships, one is a user's online social relationship by joining an interest group, the other is a user's social relationship by participating in the same social activity. In addition, there are also users and activities. This paper studies social activities recommendation. This paper, based on the existing recommendation related theories and techniques, presents the social network based on the existing recommendation related theories and techniques. The main work of this paper is as follows: (1) a city activity recommendation model based on social network is given. The model includes data acquisition module, feature extraction module, learning sorting module and recommendation module. Data acquisition module solves the problem of data acquisition and divides data into training. The feature extraction module is the analysis of data information, which extracts five characteristics: user preference, friend influence, time matching degree, position matching degree, and activity theme popularity. The learning sorting module is to transform the recommendation problem into a learning sort problem. The optimal weight W. recommendation module is based on the user's IP to judge the user's city, and then selects the user's candidate activities, calculates the user's score on the candidate activity according to the optimal weight W, and according to the score the user recommends the activity of the top-N. (2) analyze and extract the user preference, the friend influence, the time matching degree, the position matching degree, the activity theme popularity five The user preference uses a content based recommendation method to calculate the similarity between the user and the activity in the subject vector. Using the LDA method to represent the user and the activity theme vector, the text dimension is reduced and the data sparsity is alleviated. The friend influence uses the collaborative filtering method to use the user preferences. The K users with the highest similarity of the user's theme are considered as their friends. The time matching and position matching degree is used to discover the behavior rules of the user on the time and position characteristics, and calculate the similarity between the user and the activity in the time and position. The feature of the activity topic flow degree is to measure the activity theme and the activity topic. Similarity between urban popular themes, urban popular theme refers to the theme of the city's most recent M activities. At the same time, activity theme popularity can reduce the impact of cold start problems on activities recommendation. (3) a city based activity recommendation algorithm based on social network is given. The problem of recommendation is transformed into a learning sort problem, and by means of the idea of a pair learning sort, the activity is composed of sequence pairs, which are divided into positive sequence pairs and negative sequence pairs, and then the problem is converted into a two classification problem aiming at the sequence pairs of activity. In order to consider the influence of each characteristic, the paper improves the logic regression method to make it suitable for the pair. We use the square loss as the loss function. In the process of solving the problem, the batch gradient method is used to solve the problem, and the regularization term is added to the loss function to prevent the overfitting. At the same time, the user coefficient is added to adjust the influence of the user's data imbalance. In order to verify the validity of the method given in this paper, the accuracy and recall rate are selected as the evaluation index of the recommended results. The order method combines five characteristics of user preference, friend influence, time matching degree, position matching degree and activity theme popularity. The data in the same city are compared with the existing methods of active recommendation. The experimental results show that the combination of the multi feature recommendation method is better than the single feature recommendation method. Compared with the other four classical methods of activity recommendation, the improved logical regression sequencing is used in this paper. The recommendation method has better effect, can more effectively recommend activities for users, improve user experience and meet user needs.

【學(xué)位授予單位】：西南大學(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 杜蓉;於志文;劉振魯;郭斌;;基于豆瓣同城活動(dòng)的線上線下社交影響研究[J];計(jì)算機(jī)學(xué)報(bào);2014年01期

相關(guān)碩士學(xué)位論文 前7條

1 栗歡;基于社區(qū)發(fā)現(xiàn)和關(guān)聯(lián)規(guī)則的論文混合推薦技術(shù)研究[D];華中師范大學(xué);2015年

2 張淼;基于位置社交網(wǎng)絡(luò)的興趣點(diǎn)推薦方法研究[D];西南大學(xué);2015年

3 李媛;基于位置的社交網(wǎng)絡(luò)推薦算法的研究與應(yīng)用[D];中國科學(xué)院研究生院（沈陽計(jì)算技術(shù)研究所）;2015年

4 何平;基于多特征的社交活動(dòng)推薦算法研究[D];浙江大學(xué);2015年

5 鄧瑩瑩;社交網(wǎng)站中基于用戶社會(huì)活動(dòng)和好友網(wǎng)絡(luò)的推薦技術(shù)研究[D];復(fù)旦大學(xué);2014年

6 王曉聰;基于位置的社交網(wǎng)絡(luò)用戶簽到行為研究[D];大連海事大學(xué);2012年

7 鄭悅浩;一種基于隨機(jī)梯度下降的ListNet排序算法[D];中山大學(xué);2011年

，

本文編號(hào)：1830742