Predictors of user perceptions of web recommender systems: How the basis for generating experience and search product recommendations affects user responses

One critical question suggested by Web 2.0 is as follows: When is it better to leverage the knowledge of other users vs. rely on the product characteristic-based metrics for online product recommenders? Three recent and notable changes of recommender systems have been as follows: (1) a shift from characteristic-based recommendation algorithms to social-based recommendation algorithms; (2) an increase in the number of dimensions on which algorithms are based; and (3) availability of products that cannot be examined for quality before purchase. The combination of these elements is affecting users’ perceptions and attitudes regarding recommender systems and the products recommended by them, but the psychological effects of these trends remain unexplored. The current study empirically examines the effects of these elements, using a 2 (recommendation approach: content-based vs. collaborative-based, within)×2 (dimensions used to generate recommendations: 6 vs. 30, between)×2 (product type: experience products (fragrances) vs. search products (rugs), between) Web-based study (N=80). Participants were told that they would use two recommender systems distinguished by recommendation approach (in fact, the recommendations were identical). There were no substantive main effects, but all three variables exhibited two-way interactions, indicating that design strategies must be grounded in a multi-dimensional understanding of these variables. The implications of this research for the psychology and design of recommender systems are presented.     

Joint user knowledge and matrix factorization for recommender systems

Currently, most of the existing recommendation methods treat social network users equally, which assume that the effect of recommendation on a user is decided by the user’s own preferences and social influence. However, a user’s own knowledge in a field has not been considered. In other words, to what extent does a user accept recommendations in social networks need to consider the user’s own knowledge or expertise in the field. In this paper, we propose a novel matrix factorization recommendation algorithm based on integrating social network information such as trust relationships, rating information of users and users’ own knowledge. Specifically, since we cannot directly measure a user’s knowledge in the field, we first use a user’s status in a social network to indicate a user’s knowledge in a field, and users’ status is inferred from the distributions of users’ ratings and followers across fields or the structure of domain-specific social network. Then, we model the final rating of decision-making as a linear combination of the user’s own preferences, social influence and user’s own knowledge. Experimental results on real world data sets show that our proposed approach generally outperforms the state-of-the-art recommendation algorithms that do not consider the knowledge level difference between the users.     

How scales influence user rating behaviour in recommender systems

Many websites allow users to rate items and share their ratings with others, for social or personalisation purposes. In recommender systems in particular, personalised suggestions are generated by predicting ratings for items that users are unaware of, based on the ratings users provided for other items. Explicit user ratings are collected by means of graphical widgets referred to as ‘rating scales’. Each system or website normally uses a specific rating scale, in many cases differing from scales used by other systems in their granularity, visual metaphor, numbering or availability of a neutral position. While many works in the field of survey design reported on the effects of rating scales on user ratings, these, however, are normally regarded as neutral tools when it comes to recommender systems. In this paper, we challenge this view and provide new empirical information about the impact of rating scales on user ratings, presenting the results of three new studies carried out in different domains. Based on these results, we demonstrate that a static mathematical mapping is not the best method to compare ratings coming from scales with different features, and suggest when it is possible to use linear functions instead.     

Noisy but non-malicious user detection in social recommender systems

Social recommender systems largely rely on user-contributed data to infer users’ preference. While this feature has enabled many interesting applications in social networking services, it also introduces unreliability to recommenders as users are allowed to insert data freely. Although detecting malicious attacks from social spammers has been studied for years, little work was done for detecting Noisy but Non-Malicious Users (NNMUs), which refers to those genuine users who may provide some untruthful data due to their imperfect behaviors. Unlike colluded malicious attacks that can be detected by finding similarly-behaved user profiles, NNMUs are more difficult to identify since their profiles are neither similar nor correlated from one another. In this article, we study how to detect NNMUs in social recommender systems. Based on the assumption that the ratings provided by a same user on closely correlated items should have similar scores, we propose an effective method for NNMU detection by capturing and accumulating user’s “self-contradictions”, i.e., the cases that a user provides very different rating scores on closely correlated items. We show that self-contradiction capturing can be formulated as a constrained quadratic optimization problem w.r.t. a set of slack variables, which can be further used to quantify the underlying noise in each test user profile. We adopt three real-world data sets to empirically test the proposed method. The experimental results show that our method (i) is effective in real-world NNMU detection scenarios, (ii) can significantly outperform other noisy-user detection methods, and (iii) can improve recommendation performance for other users after removing detected NNMUs from the recommender system.     

Mediation of user models for enhanced personalization in recommender systems

Provision of personalized recommendations to users requires accurate modeling of their interests and needs. This work proposes a general framework and specific methodologies for enhancing the accuracy of user modeling in recommender systems by importing and integrating data collected by other recommender systems. Such a process is defined as user models mediation. The work discusses the details of such a generic user modeling mediation framework. It provides a generic user modeling data representation model, demonstrates its compatibility with existing recommendation techniques, and discusses the general steps of the mediation. Specifically, four major types of mediation are presented: cross-user, cross-item, cross-context, and cross-representation. Finally, the work reports the application of the mediation framework and illustrates it with practical mediation scenarios. Evaluations of these scenarios demonstrate the potential benefits of user modeling data mediation, as in certain conditions it allows improving the quality of the recommendations provided to the users.

Collaborative user modeling with user-generated tags for social recommender systems

With the popularity of social media services, the sheer amount of content is increasing exponentially on the Social Web that leads to attract considerable attention to recommender systems. Recommender systems provide users with recommendations of items suited to their needs. To provide proper recommendations to users, recommender systems require an accurate user model that can reflect a user’s characteristics, preferences and needs. In this study, by leveraging user-generated tags as preference indicators, we propose a new collaborative approach to user modeling that can be exploited to recommender systems. Our approach first discovers relevant and irrelevant topics for users, and then enriches an individual user model with collaboration from other similar users. In order to evaluate the performance of our model, we compare experimental results with a user model based on collaborative filtering approaches and a vector space model. The experimental results have shown the proposed model provides a better representation in user interests and achieves better recommendation results in terms of accuracy and ranking.     

Collaborative user modeling for enhanced content filtering in recommender systems

Recommender systems, which have emerged in response to the problem of information overload, provide users with recommendations of content suited to their needs. To provide proper recommendations to users, personalized recommender systems require accurate user models of characteristics, preferences and needs. In this study, we propose a collaborative approach to user modeling for enhancing personalized recommendations to users. Our approach first discovers useful and meaningful user patterns, and then enriches the personal model with collaboration from other similar users. In order to evaluate the performance of our approach, we compare experimental results with those of a probabilistic learning model, a user model based on collaborative filtering approaches, and a vector space model. We present experimental results that show how our model performs better than existing alternatives.     

用于推荐系统聚类分析的用户兴趣度研究

根据推荐系统对用户（商品）聚类的要求,探讨采用用户（网页）兴趣度进行聚类分析的合理思想。通过用户浏览时间、浏览行为以及网页信息量差异等因素的对比,得出用户对某类商品的兴趣度计算方法。借助阈值的设定,定义了用户感兴趣的商品集、商品的感兴趣用户集和兴趣相似的用户集,得到了基于用户兴趣度的用户聚类的一般过程,具有一定的推广价值和借鉴意义。     

Keyword clustering for user interest profiling refinement within paper recommender systems

To refine user interest profiling, this paper focuses on extending scientific subject ontology via keyword clustering and on improving the accuracy and effectiveness of recommendation of the electronic academic publications in online services. A clustering approach is proposed for domain keywords for the purpose of the subject ontology extension. Based on the keyword clusters, the construction of user interest profiles is presented on a rather fine granularity level. In the construction of user interest profiles, we apply two types of interest profiles: explicit profiles and implicit profiles. The explicit profiles are obtained by relating users’ interest-topic relevance factors to users’ interest measurements of these topics computed by a conventional ontology-based method, and the implicit profiles are acquired on the basis of the correlative relationships among the topic nodes in topic network graphs. Three experiments are conducted which reveal that the uses of the subject ontology extension approach as well as the two types of interest profiles satisfyingly contribute to an improvement in the accuracy of recommendation.     

Fuzzy-genetic approach to recommender systems based on a novel hybrid user model

The main strengths of collaborative filtering (CF), the most successful and widely used filtering technique for recommender systems, are its cross-genre or ‘outside the box’ recommendation ability and that it is completely independent of any machine-readable representation of the items being recommended. However, CF suffers from sparsity, scalability, and loss of neighbor transitivity. CF techniques are either memory-based or model-based. While the former is more accurate, its scalability compared to model-based is poor. An important contribution of this paper is a hybrid fuzzy-genetic approach to recommender systems that retains the accuracy of memory-based CF and the scalability of model-based CF. Using hybrid features, a novel user model is built that helped in achieving significant reduction in system complexity, sparsity, and made the neighbor transitivity relationship hold. The user model is employed to find a set of like-minded users within which a memory-based search is carried out. This set is much smaller than the entire set, thus improving system’s scalability. Besides our proposed approaches are scalable and compact in size, computational results reveal that they outperform the classical approach.     

A flexible framework for evaluating user and item fairness in recommender systems

User Modeling and User-Adapted Interaction - One common characteristic of research works focused on fairness evaluation (in machine learning) is that they call for some form of parity (equality)...     

An efficient hybrid similarity measure based on user interests for recommender systems

Recommender systems are used to suggest items to users based on their interests. They have been used widely in various domains, including online stores, web advertisements, and social networks. As part of their process, recommender systems use a set of similarity measurements that would assist in finding interesting items. Although many similarity measurements have been proposed in the literature, they have not concentrated on actual user interests. This paper proposes a new efficient hybrid similarity measure for recommender systems based on user interests. This similarity measure is a combination of two novel base similarity measurements: the user interest–user interest similarity measure and the user interest–item similarity measure. This hybrid similarity measure improves the existing work in three aspects. First, it improves the current recommender systems by using actual user interests. Second, it provides a comprehensive evaluation of an efficient solution to the cold start problem. Third, this similarity measure works well even when no corated items exist between two users. Our experiments show that our proposed similarity measure is efficient in terms of accuracy, execution time, and applicability. Specifically, our proposed similarity measure achieves a mean absolute error (MAE) as low as 0.42, with 64% applicability and an execution time as low as 0.03 s, whereas the existing similarity measures from the literature achieve an MAE of 0.88 at their best; these results demonstrate the superiority of our proposed similarity measure in terms of accuracy, as well as having a high applicability percentage and a very short execution time.     

Evaluating the impact of proactivity in the user experience of a context-aware restaurant recommender for Android smartphones

Proactivity has recently gained much attention in the area of cyber physical systems as sensing the users’ real world environment is needed to achieve it. Proactive recommenders are a good example because they push recommendations to the user when the current situation seems appropriate, without explicit user request. Evaluating whether users would accept proactive recommendations, how to properly notify them and how to present recommended items are important research questions. In this article, we present the scenario related to a context-aware restaurant recommender for Android smartphones. Two options to achieve proactivity have been designed: a widget- and a notification-based solution. In addition, our mobile user interface includes a visualization of recommended items and allows for user feedback. The approach was evaluated in a survey among users with good results regarding usefulness and effectiveness. The results also showed that test users preferred the widget-based solution in terms of user experience.     

A web search-centric approach to recommender systems with URLs as minimal user contexts

In service-oriented computing, a recommender system can be wrapped as a web service with machine-readable interface. However, owing to the cross-organizational privacy issue, the internal dataset of an organization is seldom exposed to external services. In this paper, we propose a higher level recommender strategy INSERT that guides the underlying external universal recommender to suggest a set of indexes. INSERT then matches the title of each top-ranked index entry with the domain-specific keywords in the organization's internal dataset, and further directs the universal recommender to verify the popularity of such matching. INSERT finally makes recommendation based on the verification results. INSERT also employs URLs taken from a client as user contexts, which is challenging because URLs contain little content. Our experiment shows that this strategy is feasible and effective.     

Experiments on user experiences with recommender interfaces

Recommender systems have been increasingly adopted as personalisation services in e-commerce. They facilitate users to locate items which they would be interested in viewing or purchasing. However, most studies have emphasised on the algorithm's performance, rather than on in-depth analysis of user experiences with the recommender interface. In this article, we report the results of two studies that compared two recommender interfaces: the organisation-based interface (where recommendations are presented in a category structure via the preference-based organisation method) and the standard ranked list (where recommendations are listed one after the other as ordered by their prediction scores).The first study focuses on evaluating users' eye-movement behaviour in these interfaces. With the help of an eye tracker, we found that the organisation interface (ORG) can significantly attract users' attentions to more recommended items. As a result, more users made product choices in that interface. The second, larger-scale, cross-cultural user survey further shows that the ORG performed significantly better in terms of enhancing users' perceived recommendation quality, perceived ease of use and perceived usefulness of the system. Hence, these empirical findings suggest that the change of recommender interface design can not only alter users' attention distribution, but also influence their subjective attitudes towards the system.     

A flexible semantic inference methodology to reason about user preferences in knowledge-based recommender systems

Recommender systems arose with the goal of helping users search in overloaded information domains (like e-commerce, e-learning or Digital TV). These tools automatically select items (commercial products, educational courses, TV programs, etc.) that may be appealing to each user taking into account his/her personal preferences. The personalization strategies used to compare these preferences with the available items suffer from well-known deficiencies that reduce the quality of the recommendations. Most of the limitations arise from using syntactic matching techniques because they miss a lot of useful knowledge during the recommendation process. In this paper, we propose a personalization strategy that overcomes these drawbacks by applying inference techniques borrowed from the Semantic Web. Our approach reasons about the semantics of items and user preferences to discover complex associations between them. These semantic associations provide additional knowledge about the user preferences, and permit the recommender system to compare them with the available items in a more effective way. The proposed strategy is flexible enough to be applied in many recommender systems, regardless of their application domain. Here, we illustrate its use in AVATAR, a tool that selects appealing audiovisual programs from among the myriad available in Digital TV.     

Ubiquitous recommender systems

Ubiquitous recommender systems combine characteristics from ubiquitous systems and recommender systems in order to provide personalized recommendations to users in ubiquitous environments. Although not a new research area, ubiquitous recommender systems research has not yet been reviewed and classified in terms of ubiquitous research and recommender systems research, in order to deeply comprehend its nature, characteristics, relevant issues and challenges. It is our belief that ubiquitous recommenders can nowadays take advantage of the progress mobile phone technology has made in identifying items around, as well as utilize the faster wireless connections and the endless capabilities of modern mobile devices in order to provide users with more personalized and context-aware recommendations on location to aid them with their task at hand. This work focuses on ubiquitous recommender systems, while a brief analysis of the two fundamental areas from which they emerged, ubiquitous computing and recommender systems research is also conducted. Related work is provided, followed by a classification schema and a discussion about the correlation of ubiquitous recommenders with classic ubiquitous systems and recommender systems: similarities inevitably exist, however their fundamental differences are crucial. The paper concludes by proposing UbiCARS: a new class of ubiquitous recommender systems that will combine characteristics from ubiquitous systems and context-aware recommender systems in order to utilize multidimensional context modeling techniques not previously met in ubiquitous recommender systems.     

A comparative analysis of recommender systems based on item aspect opinions extracted from user reviews

User Modeling and User-Adapted Interaction - In popular applications such as e-commerce sites and social media, users provide online reviews giving personal opinions about a wide array of items,...