Hashtag Recommendation Approach Based on Content and User Characteristics

ABSTRACT

Twitter has become a popular microblogging service that allows millions of active users share news, emergent social events, personal opinions, etc. That leads to a large amount of data producing every day and the problem of managing tweets becomes extremely difficult. To categorize the tweets and make easily in searching, the users can use the hashtags embedding in their tweets. However, valid hashtags are not restricted which lead to a very heterogeneous set of hashtags created on Twitter, increasing the difficulty of tweet categorization. In this paper, we propose a hashtag recommendation method based on analyzing the content of tweets, user characteristics, and currently popular hashtags on Twitter. The proposed method uses personal profiles of the users to discover the relevant hashtags. First, a combination of tweet contents and user characteristics is used to find the top-k similar tweets. We exploit the content of historical tweets, used hashtags, and the social interaction to build the user profiles. The user characteristics can help to find the close users and enhance the accuracy of finding the similar tweets to extract the hashtag candidates. Then a set of hashtag candidates is ranked based on their popularity in long and short periods. The experiments on tweet data showed that the proposed method significantly improves the performance of hashtag recommendation systems.     

Twitter analysis algorithms for Intelligence Circulation System

The convergence of broadcasting and broadband communications network technologies has attracted increasing attention as a means to enrich the television viewing experience of viewers. Toward this end, this study proposes the ‘Intelligence Circulation System (ICS)’, which provides several services, by using newly developed algorithms for analysing Twitter messages. Twitter users often post messages about on-air TV programmes. ICS obtains viewer responses from tweets without requiring any new infrastructure or changes in users’ habits or behaviours, and it generates and provides several outputs to heterogeneous devices based on the analysis results. The algorithms—designed by considering the characteristics of Twitter messages about TV programmes—use auxiliary programme information, similarity between messages, and time series of messages. An evaluation of our algorithms using Twitter messages about all programme genres for a month showed that the accuracy of topic extraction was 85 % for an emphasis on quality (with 56 % of messages processed) and 65 % for an emphasis on quantity (with 95 % of messages processed). The accuracy of message sentimental classification was 66 %. We also describe social recommendation services using the analysis result. We have created a Social TV site for a large-scale field trial, and we have analysed users’ behaviours by comparing four types of social recommendation services on it. The experimental result shows that active and passive communication users had different needs with regard to the recommendations. ICS can generate recommendations for satisfying the needs of both user types by using the analysis result of Twitter messages.     

The dynamic competitive recommendation algorithm in social network services

As the number of Twitter users exceeds 175 million and the scale of social network increases, it is facing with a challenge to how to help people find right people and information conveniently. For this purpose, current social network services are adopting personalized recommender systems. Existing recommendation algorithms largely depend on one of content-based algorithm, collaborative filtering, or influential ranking analysis. However, these algorithms tend to suffer from the performance fluctuation phenomenon in common whenever an active user changes, and it is due to the diversities of personal characteristics such as the local social graph size, the number of followers, or sparsity of profile content. To overcome this limitation and to provide consistent and stable recommendation in social networks, this study proposes the dynamic competitive recommendation algorithm based on the competition of multiple component algorithms. This study shows that it outperforms previous approaches through performance evaluation on actual Twitter dataset.     

Supporting Creativity through the Interactive Exploratory Search Paradigm

In creative tasks, there is a need to explore the space of available information in order to come up with diverse views before converging to a solution. In such tasks, typical search engines that follow the direct search paradigm fail to inspire users. It is hypothesized that contrary to typical engines, interactive exploratory search, which aims at revealing latent, alternative directions in the information space enabling user orientation and engagement, is better suited to assist users in their quest for serendipitous discoveries and inspiration. In this study, an interactive exploratory search tool that combines diversification of content and sources with a user interface design that visualizes clues from the social chatter – generated with micro-blogging services such as Twitter – and lets users interactively explore the available information space is presented. A profiling service and recommendation module in charge of delivering personalized social content complements the setting. A pilot and two task-based user studies comparing our system to a query-based baseline indicate that our system significantly improves inspirational discoveries by providing access to more interesting and serendipitous information.     

基于三度影响力的社交好友推荐机制

针对社交网络中的好友推荐问题,提出了一种基于三度影响力理论的好友推荐算法。社交网络用户节点间的联系除了共同好友外,还存在其他不同长度的连通关系。该算法不再局限于仅以用户间共同好友的数量作为好友推荐的主要依据,而是在此基础上引入三度影响力理论进一步拓展关系连接,即把用户间距离三度以内的强连接用户都考虑进来,并通过为不同距离长度的连通关系分配相应的权重,实现好友关系强度的计算,来进行推荐。通过在新浪微博和Facebook社交网站上的实验结果表明,该算法比仅依据用户间共同好友数量的推荐算法在查准率和查全率上分别提高了约5%和0.8%,显著提升了社交平台好友推荐的效果,从而为社交平台改进推荐机制,以进一步增强用户体验提供了理论支撑。     

Combining long-term and short-term user interest for personalized hashtag recommendation

Hashtags, terms prefixed by a hash-symbol #, are widely used and inserted anywhere within short messages (tweets) on micro-blogging systems as they present rich sentiment information on topics that people are interested in. In this paper, we focus on the problem of hashtag recommendation considering their personalized and temporal aspects. As far as we know, this is the first work addressing this issue specially to recommend personalized hashtags combining longterm and short-term user interest.We introduce three features to capture personal and temporal user interest: 1) hashtag textual information; 2) user behavior; and 3) time. We offer two recommendation models for comparison: a linearcombined model, and an enhanced session-based temporal graph (STG) model, Topic-STG, considering the features to learn user preferences and subsequently recommend personalized hashtags. Experiments on two real tweet datasets illustrate the effectiveness of the proposed models and algorithms.     

An Analytical Model for Identifying Suspected Users on Twitter

Abstract

With the use of identity resolution, both information leakage and identity hacking can be reduced to some extent. In this paper, a prototype has been developed to classify Twitter users as suspicious and nonsuspicious on the basis of features which identify user demographics and their tweeting activity using Twitter APIs. A model has been devised based upon user and tweet meta-data which is used to calculate user score and tweet score, and further aggregate the values generated by these scores to label suspicious and nonsuspicious users in the collected dataset of around 21,492 Twitter users. Further, support vector machine classifier has been used to classify the labeled data. Through this paper, our analysis about the role of features and the characteristics of dataset used for the categorization of users in Twitter has been reported. The experimental results illustrate that the proposed system can identify suspicious users with an accuracy of 94.1%.     

基于SSD和时序模型的微博好友推荐算法

社交网络用户的指数型增长,导致用户在网络中难以找到适合自己的好友.提出一种基于多目标检测算法SSD和时序模型的微博好友推荐算法BSBT-FR,首先利用SSD对搜集到的用户图像进行信息提取,再利用时序模型在时间维度上对提取到的信息做进一步处理,然后利用JS散度公式计算用户间的相似度,最后与基于用户个人信息得出的相似度进行加权式融合,得出综合的用户相似度,使用Top-K思想进行用户推荐.在新浪微博用户数据集上的实验表明,参考因素的权重取值会影响推荐结果,BSBT-FR算法与只考虑用户属性或用户图像的算法相比,精准度更高.     

一种融合个性化与多样性的人物标签推荐方法

针对人物标签推荐中多样性及推荐标签质量问题,该文提出了一种融合个性化与多样性的人物标签推荐方法。该方法使用主题模型对用户关注对象建模,通过聚类分析把具有相似言论的对象划分到同一类簇;然后对每个类簇的标签进行冗余处理,并选取代表性标签;最后对不同类簇中的标签融合排序,以获取Top-K个标签推荐给用户。实验结果表明,与已有推荐方法相比,该方法在反映用户兴趣爱好的同时,能显著提高标签推荐质量和推荐结果的多样性。     

一种面向获取空间信息的潜在好友推荐算法

随着社交网络的不断发展,朋友推荐已成为各大社交网络的青睐对象,在能够帮助用户拓宽社交圈的同时可以通过新朋友获取大量信息.由此朋友推荐应该着眼于拓宽社交圈和获取信息,然而传统的朋友推荐算法几乎没有考虑从获取信息的角度为用户推荐潜在好友,大多是依赖于用户在线的个人资料和共同的物理空间中的签到信息.而由于人们活动具有空间局部性,被推荐的好友分布在用户了解的地理空间,并不能够满足用户通过推荐的朋友获取更多地理信息的需求.本文采用用户在物理世界中的签到行为代替虚拟社交网络中的用户资料,挖掘真实世界中用户之间的签到行为的相似性,为用户推荐具有相似的签到行为且地理位置分布更广泛的陌生人,能够增加用户接受被推荐的陌生人成为朋友的可能性和在保证一定的推荐精度的基础上增加用户的信息获取量.本文采用核密度估计估算用户签到行为概率分布,用时间熵度量签到行为在时间上的集中程度,选择可以为用户带来更多新的地理信息的陌生人作为推荐的对象,通过大规模Foursquare的用户签到数据集验证本文的算法在精度上保证了与目前已有LBSN上陌生人推荐算法的相似性,在信息扩大程度上高于上述已有算法.     

面向兴趣主题的个性化好友推荐

个性化的好友推荐是促进社交网络服务不断提高的重要途径,在大规模的社交网络环境中,准确地为用户推荐兴趣主题相似的好友能够使得用户的粘性更强,然而海量数据的稀疏性使得现有的大多数社交网络都不能够准确根据用户间兴趣的相似性进行好友推荐。为此,提出一种面向用户兴趣主题的个性化好友推荐方法(ITOR)。该方法首先采用k-core分析法提取用户的兴趣主题,在拥有相似兴趣主题的基础上结合用户属性信息,通过先验概率计算出有相同属性信息的用户成为好友的概率,进一步强化推荐结果的准确性和满意度。最后,通过爬取2015年9月份发布的新浪微博数据进行实验分析,验证了本推荐方法的有效性。     

Neural TV program recommendation with label and user dual attention

TV program recommendation is very important for users to find interesting TV programs and avoid confusing users with a lot of information. Currently, they are basically traditional collaborative filtering algorithms, which only recommend through the interactive data between users and programs ignoring the important value of some auxiliary information. In addition, the neural network method based on attention mechanism can well capture the relationship between program labels to obtain accurate program and user representations. In this paper, we propose a neural TV program recommendation with label and user dual attention (NPR-LUA), which can focus on auxiliary information in program and user modules. In the program encoder module, we learn the auxiliary information from program labels through neural networks and word attention to identify important program labels. In the user encoder module, we learn the user representation through the programs that the user watches and use personalized attention mechanism to distinguish the importance of programs for each user. Experiments on real data sets show that our method can effectively improve the effectiveness of TV program recommendations than other existing models.

     

Research on personalized recommendation hybrid algorithm for interactive experience equipment

Interactive calligraphy experience equipment has the characteristics of a large amount of data, various types, and strong homogeneity, which makes it difficult for users to find interesting resources. In this article, a hybrid personalized recommendation algorithm is proposed, which uses collaborative filtering and content-based recommendation methods in turn to make recommendations. In the initial recommendation, Latent Dirichlet Allocation (LDA) topic model is used to reduce the dimension of high-dimensional user behavior data and establish a user-writing theme matrix to reduce inaccurate recommendation caused by high sparsity data in collaborative filtering algorithm. The user interest list is obtained by calculating the similarity between users. Then, on the basis of the preliminary recommendation results, VGG16 model is used to extract the feature vector of the calligraphy image and calculate the similarity between the user's calligraphy words and the primary recommended calligraphy words, thus obtaining the final recommendation results. The experimental results verify the effectiveness and accuracy of the recommendation algorithm, which are better than other recommendation algorithms on the whole, and have important engineering guiding significance.     

A Bayesian network and analytic hierarchy process based personalized recommendations for tourist attractions over the Internet

Selecting tourist attractions to visit at a destination is a main stage in planning a trip. Although various online travel recommendation systems have been developed to support users in the task of travel planning during the last decade, few systems focus on recommending specific tourist attractions. In this paper, an intelligent system to provide personalized recommendations of tourist attractions in an unfamiliar city is presented. Through a tourism ontology, the system allows integration of heterogeneous online travel information. Based on Bayesian network technique and the analytic hierarchy process (AHP) method, the system recommends tourist attractions to a user by taking into account the travel behavior both of the user and of other users. Spatial web services technology is embedded in the system to provide GIS functions. In addition, the system provides an interactive geographic interface for displaying the recommendation results as well as obtaining users’ feedback. The experiments show that the system can provide personalized recommendations on tourist attractions that satisfy the user.     

结合非负矩阵分解的主题社区好友推荐算法

为用户推荐好友是在线社交网络的重要个性化服务。好友推荐可以帮助用户发现他们感兴趣的好友,减轻信息过载的现象。然而,目前现有的推荐方法仅考虑用户链接或内容信息,推荐精度不高,不足以提供高质量的服务。在本文中,考虑了用户之间的链接和内容信息,提出了一种结合非负矩阵因式分解的主题社区好友推荐算法(T-NMF)。该算法给出了主题社区和综合相似度计算方法,产生好友推荐列表。实验表明,该算法可以更好的反映用户的偏好,并且具有比传统方法更好的推荐性能。     

Followee recommendation based on text analysis of micro-blogging activity

Nowadays, more and more users keep up with news through information streams coming from real-time micro-blogging activity offered by services such as Twitter. In these sites, information is shared via a followers/followees social network structure in which a follower receives all the micro-blogs from his/her followees. Recent research efforts on understanding micro-blogging as a novel form of communication and news spreading medium have identified three different categories of users in these systems: information sources, information seekers and friends. As social networks grow in the number of registered users, finding relevant and reliable users to receive interesting information becomes essential. In this paper we propose a followee recommender system based on both the analysis of the content of micro-blogs to detect users' interests and in the exploration of the topology of the network to find candidate users for recommendation. Experimental evaluation was conducted in order to determine the impact of different profiling strategies based on the text analysis of micro-blogs as well as several factors that allows the identification of users acting as good information sources. We found that user-generated content available in the network is a rich source of information for profiling users and finding like-minded people.     

一种支持个性化Web推荐的聚类分析

提出基于关联的聚类分析方法,挖掘具有相似访问兴趣的用户访问模式,分离不相关的用户模式,并提出基于关联的聚类算法。实验证明,该算法大量减少不相关的用户访问模式,提高个性化推荐质量。为进一步研究个性化推荐技术奠定基础。     

基于Web日志的煤矿企业网站个性化推荐服务研究

为了解决煤矿企业网站用户查找信息难的问题,提出了一种基于Web日志的煤矿企业网站个性化推荐服务模型。该模型应用关联规则对新用户进行页面推荐,应用聚类算法对老用户进行页面推荐;并结合点击网页的次数、网页的浏览时间、雅可系数与最长公共路径系数来度量用户兴趣度的方法,可为用户准确地推荐其感兴趣的页面。测试结果表明,该模型能够有效地对网页资源进行分类并进行个性化推荐。     

kNN processing with co-space distance in SoLoMo systems

With the increasing popularity of smart phones, SoLoMo (Social-Location-Mobile) systems are expected to be fast-growing and become a popular mobile social networking platform. A main challenge in such systems is on the creation of stable links between users. For each online user, the current SoLoMo system continuously returns his/her kNN (k Nearest Neighbor) users based on their geo-locations. Such a recommendation approach is simple, but fails to create sustainable friendships. Instead, it would be more effective to tap onto the existing social relationships in conventional social networks, such as Facebook and Twitter, to provide a “better” friend recommendations.To measure the similarity between users, we propose a new metric, co-space distance, by considering both the user distances in the real world (physical distance) and the virtual world (social distance). The co-space distance measures the similarity of two users in the SoLoMo system. We compute the social distances between users based on their public information in the conventional social networks, which can be achieved by a few MapReduce jobs. To facilitate efficient computation of the social distance, we build a distributed index on top of the key-value store, and maintain the users’ geo-locations using an R-tree. For each query on finding potential friends around a location, we return kNN neighbors to each user based on their co-space distances. We propose a progressive top-k processing strategy and an adaptive-caching strategy to facilitate efficient query processing. Experiments with Gowalla dataset¹ show the effectiveness and efficiency of our recommendation approach.     

Personalized recommender system based on friendship strength in social network services

The rapid growth of social network services has produced a considerable amount of data, called big social data. Big social data are helpful for improving personalized recommender systems because these enormous data have various characteristics. Therefore, many personalized recommender systems based on big social data have been proposed, in particular models that use people relationship information. However, most existing studies have provided recommendations on special purpose and single-domain SNS that have a set of users with similar tastes, such as MovieLens and Last.fm; nonetheless, they have considered closeness relation. In this paper, we introduce an appropriate measure to calculate the closeness between users in a social circle, namely, the friendship strength. Further, we propose a friendship strength-based personalized recommender system that recommends topics or interests users might have in order to analyze big social data, using Twitter in particular. The proposed measure provides precise recommendations in multi-domain environments that have various topics. We evaluated the proposed system using one month's Twitter data based on various evaluation metrics. Our experimental results show that our personalized recommender system outperforms the baseline systems, and friendship strength is of great importance in personalized recommendation.