一种核的上下文多臂赌博机推荐算法

个性化推荐服务在当今互联网时代越来越重要,但是传统推荐算法不适应一些高度变化场景。将线性上下文多臂赌博机算法(linear upper confidence bound, LinUCB)应用于个性化推荐可以有效改善传统推荐算法存在的问题,但遗憾的是准确率并不是很高。本文针对LinUCB算法推荐准确率不高这一问题,提出了一种改进算法K-UCB(kernel upper confidence bound)。该算法突破了LinUCB算法中不合理的线性假设前提,利用核方法拟合预测收益与上下文间的非线性关系,得到了一种新的在非线性数据下计算预测收益置信区间上界的方法,以解决推荐过程中的探索–利用困境。实验表明,本文提出的K-UCB算法相比其他基于多臂赌博机推荐算法有更高的点击率(click-through rate, CTR),能更好地适应变化场景下个性化推荐的需求。     

Combining user preferences and user opinions for accurate recommendation

Recommendation systems represent a popular research area with a variety of applications. Such systems provide personalized services to the user and help address the problem of information overload. Traditional recommendation methods such as collaborative filtering suffer from low accuracy because of data sparseness though. We propose a novel recommendation algorithm based on analysis of an online review. The algorithm incorporates two new methods for opinion mining and recommendation. As opposed to traditional methods, which are usually based on the similarity of ratings to infer user preferences, the proposed recommendation method analyzes the difference between the ratings and opinions of the user to identify the user’s preferences. This method considers explicit ratings and implicit opinions, an action that can address the problem of data sparseness. We propose a new feature and opinion extraction method based on the characteristics of online reviews to extract effectively the opinion of the user from a customer review written in Chinese. Based on these methods, we also conduct an empirical study of online restaurant customer reviews to create a restaurant recommendation system and demonstrate the effectiveness of the proposed methods.     

面向用户群体的Web服务推荐

针对Web服务推荐中服务用户调用Web服务的服务质量数据稀疏性导致的低推荐质量问题,提出了一种面向用户群体并基于协同过滤的Web服务推荐算法(WRUG)。首先,为每个服务用户根据用户相似性矩阵构建其个性化的相似用户群体;其次,以相似用户群体中心点代替群体从而计算用户群体相似性矩阵;最后,构造面向群体的Web服务推荐公式并为目标用户预测缺失的Web服务质量。通过对197万条真实Web服务质量调用记录的数据集进行对比实验,与传统基于协同过滤的推荐算法(TCF)和基于用户群体影响的协同过滤推荐算法(CFBUGI)相比,WRUG的平均绝对误差下降幅度分别为28.9%和4.57%;并且WRUG的覆盖率上升幅度分别为110%和22.5%。实验结果表明,在相同实验条件下WRUG不仅能提高Web服务推荐系统的预测准确性,而且能显著地提高其有效预测服务质量的百分比。     

基于用户中心访问行为的多臂缓存方法

针对现有的边缘缓存策略无法有效预测短时热内容集和冷内容集流行度时变规律,而基于探索的多臂算法缺乏有效机制解决探索过程的过量探索问题,提出了基于用户中心访问行为的多臂缓存方法（MACB）。MACB利用用户中心访问上下文缩小群体访问偏好内容集,在此基础上采用多臂算法的探索开发过程,有效学习短时热内容集和冷内容集的内容流行度变化规律。实验采用了中国移动用户记录数据集,并与相关缓存算法进行对比。结果显示MACB在缓存击中率上均高于其他对比缓存方法,表明了MACB缓存方法的有效性和优越性。     

Location-aware online learning for top-k recommendation

We address the problem of recommending highly volatile items for users, both with potentially ambiguous location that may change in time. The three main ingredients of our method include (1) using online machine learning for the highly volatile items; (2) learning the personalized importance of hierarchical geolocation (for example, town, region, country, continent); finally (3) modeling temporal relevance by counting recent items with an exponential decay in recency.For (1), we consider a time-aware setting, where evaluation is cumbersome by traditional measures since we have different top recommendations at different times. We describe a time-aware framework based on individual item discounted gain. For (2), we observe that trends and geolocation turns out to be more important than personalized user preferences: user–item and content-item matrix factorization improves in combination with our geo-trend learning methods, but in itself, they are greatly inferior to our location based models. In fact, since our best performing methods are based on spatiotemporal data, they are applicable in the user cold start setting as well and perform even better than content based cold start methods. Finally for (3), we estimate the probability that the item will be viewed by its previous views to obtain a powerful model that combines item popularity and recency.To generate realistic data for measuring our new methods, we rely on Twitter messages with known GPS location and consider hashtags as items that we recommend the users to be included in their next message.     

Discovering user profiles for Web personalized recommendation

With the growing popularity of the World Wide Web, large volume of user access data has been gathered automatically by Web servers and stored in Web logs. Discovering and understanding user behavior patterns from log files can provide Web personalized recommendation services. In this paper, a novel clustering method is presented for log files called Clustering large Weblog based on Key Path Model (CWKPM), which is based on user browsing key path model, to get user behavior profiles. Compared with the previous Boolean model, key path model considers the major features of users‘ accessing to the Web: ordinal, contiguous and duplicate. Moreover, for clustering, it has fewer dimensions. The analysis and experiments show that CWKPM is an efficient and effective approach for clustering large and high-dimension Web logs.     

面向在线社区用户的群体推荐算法研究

结合现有两种主要群体推荐算法的优势, 建立新的算法框架, 并引入差异度因素对模型进行优化。另外, 考虑到在线社区用户的特点, 定义互动度指标来描述群体成员间的互动程度, 通过分析其与推荐精度之间的关系, 探讨互动度对群体推荐的影响。选取豆瓣网数据进行实验, 并与传统方法进行比较, 结果表明, 融入差异度的算法具有更好的推荐效果, 且有效的互动机制能够保证较高的推荐精度。     

Semantic user profiling techniques for personalised multimedia recommendation

Due to the explosion of news materials available through broadcast and other channels, there is an increasing need for personalised news video retrieval. In this work, we introduce a semantic-based user modelling technique to capture users’ evolving information needs. Our approach exploits implicit user interaction to capture long-term user interests in a profile. The organised interests are used to retrieve and recommend news stories to the users. In this paper, we exploit the Linked Open Data Cloud to identify similar news stories that match the users’ interest. We evaluate various recommendation parameters by introducing a simulation-based evaluation scheme.     

面向不一致用户评价准则的在线服务推荐

客观上,用户的评价准则是由主观意识决定的,用户之间的评价准则不同导致多个用户对同一服务的评分不具备可比较性,不考虑不同用户评分的不可比较性所获得的服务推荐将难以满足用户个性偏好及其真实需求。为此,提出一种面向不一致用户评价准则的在线服务推荐方法,考虑用户偏好不一致时用户对在线服务的偏好关系,以偏好关系计算用户之间的相似度,并以此获得在线服务推荐结果。首先以用户-服务评分矩阵为基础建立用户对服务的偏好关系,其次根据偏好关系计算用户之间的相似度,然后以用户相似度为基础对用户未评分的服务进行评分预测,最后以预测评分的排序结果作为推荐结果。与经典的协同过滤推荐方法的比较实验,验证了本方法的有效性。实验表明,本方法获得的推荐结果能满足大多数用户的服务偏好,同时获得了比经典的协同过滤推荐方法更好的准确率。     

融合用户属性信息的冷启动推荐算法

协同过滤算法广泛应用于个性化推荐系统中。现有的基于社群相似性的协同过滤算法在新用户新商品的冷启动场景中难以使用,性能较差。对此,提出了一种基于矩阵分解和神经网络映射的冷启动推荐算法。首先,使用矩阵分解方法求出用户在潜在兴趣空间的向量表示;然后,训练神经网络学习从用户属性数据到潜在兴趣向量的映射关系;最后,融合用户的历史评分数据与属性数据各自生成的兴趣向量,给出平滑的推荐预测值。实验表明,当用户的评分记录很少时,预测性能有明显提升,融合用户的属性信息能较好地改善"冷启动"情况下推荐系统的性能。     

用户个性化推荐系统的设计与实现

为实现个性化服务,理解用户兴趣就成了提供服务的关键任务,因此,提出了隐性采集用户浏览内容、用户浏览时间和用户操作时间的信息方法,通过对网络爬虫程序抓取的网页进行内容清洗提取出主要内容之后,利用VSM建立文档模型,并采用SVM分类方法建立推荐库.基于从客户端采集的用户兴趣信息建模,以及根据该模型和推荐库的相似度,给用户推荐信息.此外,给出了基于该模型的推荐原型系统的实现,使用查准率来评价该系统.试验结果表明,系统较好地实现了基于用户兴趣来推荐阅读的信息.     

Preference-based user rating correction process for interactive recommendation systems

In most of the recommendation systems, user rating is an important user activity that reflects their opinions. Once the users return their ratings about items the systems have suggested, the user ratings can be used to adjust the recommendation process.However, while rating the items users can make some mistakes (e.g., natural noises). As the recommendation systems receive more incorrect ratings, the performance of such systems may decrease. In this paper, we focus on an interactive recommendation system which can help users to correct their own ratings. Thereby, we propose a method to determine whether the ratings from users are consistent to their own preferences (represented as a set of dominant attribute values) or not and eventually to correct these ratings to improve recommendation. The proposed interactive recommendation system has been particularly applied to two user rating datasets (e.g., MovieLens and Netflix) and it has shown better recommendation performance (i.e., lower error ratings).     

基于用户关注度的个性化新闻推荐系统

为满足用户需求,以用户为中心,解决用户关注度不断变化、数据稀疏性、优化时间和空间效率等问题,提出基于用户关注度的个性化新闻推荐系统。推荐系统引入个人兴趣和场景兴趣来描述用户关注度,使用雅克比度量用户相似性,对相似度加权求和预测用户关注度,从而提供给用户经过排序的新闻推荐列表。实验结果表明,推荐系统有效地提高了推荐精准度和覆盖度,改善了系统可扩展性和自动更新能力,具有良好的推荐效果。     

Leveraging proficiency and preference for online Karaoke recommendation

Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these platforms.In the meantime,the system automatically evaluates user proficiency according to their singing behavior.Recommending approximate songs to users can initialize singers5 participation and improve users,loyalty to these platforms.However,this is not an easy task due to the unique characteristics of these platforms.First,since users may be not achieving high scores evaluated by the system on their favorite songs,how to balance user preferences with user proficiency on singing for song recommendation is still open.Second,the sparsity of the user-song interaction behavior may greatly impact the recommendation task.To solve the above two challenges,in this paper,we propose an informationfused song recommendation model by considering the unique characteristics of the singing data.Specifically,we first devise a pseudo-rating matrix by combing users’singing behavior and the system evaluations,thus users'preferences and proficiency are leveraged.Then we mitigate the data sparsity problem by fusing users*and songs'rich information in the matrix factorization process of the pseudo-rating matrix.Finally,extensive experimental results on a real-world dataset show the effectiveness of our proposed model.     

Privacy-preserving distributed projected one-point bandit online optimization over directed graphs

The distributed online optimization (DOO) problem with privacy-preserving properties over multiple agents is considered in this paper, where the network model is built by a strongly connected directed graph. To solve this problem, a stochastic bandit DOO algorithm based on differential privacy is proposed. This algorithm uses row- and column-stochastic matrix as the weighting matrices, the requirement of the double random weighting matrix is released. To handle the unknown objective function, the one-point bandit is used to estimate the true gradient information, and the estimated gradient information is used to update of decision variables. Different from the existing DOO algorithms that ignore privacy issues, this algorithm successfully protects the privacy of nodes through a differential privacy policy. Theoretical results show that the algorithm can not only achieve sublinear regret bounds but also protect the privacy of nodes. Finally, simulation results verify the effectiveness of the algorithm.     

Assessing user interfaces for diverse user groups: evaluation strategies and defining characteristics

User interface designers are challenged to design for diverse users, including those of different genders, cultures and abilities; however, little research has been directed at this problem. One factor which may inhibit such research is its cost. This paper presents an approach which offers a way to seek out important characteristics of designs in a cost-effective way and reports on the results. In a study reported here, subjects from different nationalities and of both genders evaluated three dialog boxes specifically designed for 'white American women'. 'European adult male intellectuals', and 'English-speaking-internationals'. The dialog boxes were evaluated with conjoint techniques of preference rankings, and factor-analysed adjective ratings. These results showed that female subjects had stronger and more consistent patterns of preferences than the male subjects. All subjects preferred interfaces rated high on an accessibility factor and disliked complex layouts; this effect was even stronger for women. Nationality did not effect ratings. Gender had a stronger effect on the outcome than nationality.     

Assessing user interfaces for diverse user groups: Evaluation strategies and defining characteristics

User interface designers are challenged to design for diverse users, including those of different genders, cultures and abilities; however, little research has been directed at this problem. One factor which may inhibit such research is its cost. This paper presents an approach which offers a way to seek out important characteristics of designs in a cost-effective way and reports on the results. In a study reported here, subjects from different nationalities and of both genders evaluated three dialog boxes specifically designed for 'white American women'. 'European adult male intellectuals', and 'English-speaking-internationals'. The dialog boxes were evaluated with conjoint techniques of preference rankings, and factor-analysed adjective ratings. These results showed that female subjects had stronger and more consistent patterns of preferences than the male subjects. All subjects preferred interfaces rated high on an accessibility factor and disliked complex layouts; this effect was even stronger for women. Nationality did not effect ratings. Gender had a stronger effect on the outcome than nationality.     

Personalizing recommendation diversity based on user personality

In recent years, diversity has attracted increasing attention in the field of recommender systems because of its ability of catching users’ various interests by providing a set of dissimilar items. There are few endeavors to personalize the recommendation diversity being tailored to individual users’ diversity needs. However, they mainly depend on users’ behavior history such as ratings to customize diversity, which has two limitations: (1) They neglect taking into account a user’s needs that are inherently caused by some personal factors such as personality; (2) they fail to work well for new users who have little behavior history. In order to address these issues, this paper proposes a generalized, dynamic personality-based greedy re-ranking approach to generating the recommendation list. On one hand, personality is used to estimate each user’s diversity preference. On the other hand, personality is leveraged to alleviate the cold-start problem of collaborative filtering recommendations. The experimental results demonstrate that our approach significantly outperforms related methods (including both non-diversity-oriented and diversity-oriented methods) in terms of metrics measuring recommendation accuracy and personalized diversity degree, especially in the cold-start setting.     

Exploiting user feedback for online filtering in event-based systems

Modern large-scale internet applications represent today a fundamental source of information for millions of users. The larger is the user base, the more difficult it is to control the quality of data that is spread from producers to consumers. This can easily hamper the usability of such systems as the amount of low quality data received by consumers grows uncontrolled. In this paper we propose a novel solution to automatically filter new data injected in event-based systems with the aim of delivering only content consumers are actually interested in. Filtering is executed by profiling producers and consumers, and matching their profiles as new data is produced. Profiles are built by aggregating feedback submitted by consumers on previously received data.     

考虑非对称用户偏好的推荐算法

为解决常见的相似性方法存在未考虑用户间共同评分项在目标用户所评项目中的比例以及用户评分偏好的问题。提出了非对称因子和偏好因子,用于提高用户相似性计算的准确性。在公开的MovieLens和Yahoo Music数据集上的实验表明,引入这两个因子后,相似性模型的预测误差下降显著,优于其他相似性方法。非对称因子和偏好因子的引入更合理地体现出用户间的评分差异性,有效地处理了用户偏好问题,提高了推荐质量。