In recent years, a variety of review-based recommender systems have been developed, with the goal of incorporating the valuable information in user-generated textual reviews into the user modeling and recommending process. Advanced text analysis and opinion mining techniques enable the extraction of various types of review elements, such as the discussed topics, the multi-faceted nature of opinions, contextual information, comparative opinions, and reviewers' emotions. In this article, we provide a comprehensive overview of how the review elements have been exploited to improve standard content-based recommending, collaborative filtering, and preference-based product ranking techniques. The review-based recommender system's ability to alleviate the well-known rating sparsity and cold-start problems is emphasized. This survey classifies state-of-the-art studies into two principal branches: review-based user profile building and review-based product profile building. In the user profile sub-branch, the reviews are not only used to create term-based profiles, but also to infer or enhance ratings. Multi-faceted opinions can further be exploited to derive the weight/value preferences that users place on particular features. In another sub-branch, the product profile can be enriched with feature opinions or comparative opinions to better reflect its assessment quality. The merit of each branch of work is discussed in terms of both algorithm development and the way in which the proposed algorithms are evaluated. In addition, we discuss several future trends based on the survey, which may inspire investigators to pursue additional studies in this area.

Recommender systems based on user reviews: the state of the art

Collaborative filtering (CF), one of the most successful recommendation approaches, continues to attract interest in both academia and industry. However, one key issue limiting the success of collaborative filtering in certain application domains is the cold-start problem, a situation where historical data is too sparse (known as the sparsity problem), new users have not rated enough items (known as the new user problem), or both. In this paper, we aim at addressing the cold-start problem by incorporating human personality into the collaborative filtering framework. We propose three approaches: the first is a recommendation method based on users' personality information alone; the second is based on a linear combination of both personality and rating information; and the third uses a cascade mechanism to leverage both resources. To evaluate their effectiveness, we have conducted an experimental study comparing the proposed approaches with the traditional rating-based CF in two cold-start scenarios: sparse data sets and new users. Our results show that the proposed CF variations, which consider personality characteristics, can significantly improve the performance of the traditional rating-based CF in terms of the evaluation metrics MAE and ROC sensitivity.

/pdf/enhancing-collaborative-filtering-systems-with-personality-39wz5w1igm.pdf

Enhancing collaborative filtering systems with personality information

Predicting and Detecting the Relevant Contextual Information in a Movie-Recommender System

Recommender systems have already proved to be valuable for coping with the information overload problem in several application domains. They provide people with suggestions for items which are likely to be of interest for them; hence, a primary function of recommender systems is to help people make good choices and decisions. However, most previous research has focused on recommendation techniques and algorithms, and less attention has been devoted to the decision making processes adopted by the users and possibly supported by the system. There is still a gap between the importance that the community gives to the assessment of recommendation algorithms and the current range of ongoing research activities concerning human decision making. Different decision-psychological phenomena can influence the decision making of users of recommender systems, and research along these lines is becoming increasingly important and popular. This special issue highlights how the coupling of recommendation algorithms with the understanding of human choice and decision making theory has the potential to benefit research and practice on recommender systems and to enable users to achieve a good balance between decision accuracy and decision effort.

Human Decision Making and Recommender Systems

Affective labeling of multimedia content has proved to be useful in recommender systems. In this paper we present a methodology for the implicit acquisition of affective labels for images. It is based on an emotion detection technique that takes as input the video sequences of the users' facial expressions. It extracts Gabor low level features from the video frames and employs a k nearest neighbors machine learning technique to generate affective labels in the valence-arousal-dominance space. We performed a comparative study of the performance of a content-based recommender (CBR) system for images that uses three types of metadata to model the users and the items: (i) generic metadata, (ii) explicitly acquired affective labels and (iii) implicitly acquired affective labels with the proposed methodology. The results show that the CBR performs best when explicit labels are used. However, implicitly acquired labels yield a significantly better performance of the CBR than generic metadata while being an unobtrusive feedback tool.

Affective Labeling in a Content-Based Recommender System for Images

Emotions are crucial for user's decision making in recommendation processes. We first introduce ambient recommender systems, which arise from the analysis of new trends on the exploitation of the emotional context in the next generation of recommender systems. We then explain some results of these new trends in real-world applications through the smart prediction assistant (SPA) platform in an intelligent learning guide with more than three million users. While most approaches to recommending have focused on algorithm performance. SPA makes recommendations to users on the basis of emotional information acquired in an incremental way. This article provides a cross-disciplinary perspective to achieve this goal in such recommender systems through a SPA platform. The methodology applied in SPA is the result of a bunch of technology transfer projects for large real-world rccommender systems.

/pdf/embedding-emotional-context-in-recommender-systems-3jk56uudo5.pdf

Embedding Emotional Context in Recommender Systems

This paper describes the state of the art for social currencies and cognitive capitalism, which is used to found a new currency based on knowledge. This new currency better reflects the wealth of nations throughout the world, supports more social economic activity and is better adapted to the challenges of digital business ecosystems. The basic premise of the new currency is a knowledge measurement pattern that is formulated as a new alternative social currency. Therefore, it is a first step contributing to the worldwide evolution towards a knowledge society. It is a currency to facilitate the conservation and storage of knowledge, its organization and categorization, but chiefly its transference and exploitation. The proposal turns recommender agents into the new currency. An example is presented to show how recommender agents receive a new use, transforming them into objects of transaction.

Social Currencies And Knowledge Currencies

In this paper we present research into obtaining complete FAQs that provide users with satisfactory information. To achieve that we join FAQ technology with the emerging wiki technology to obtain a tool we call WikiFAQ which includes all the basics elements of a FAQ combined with the properties of wikis, and in which we include a set of Knowledge Contribution Methods (KCM) based on bidding and auctioning systems, and a reward mechanism (RM) based on points as in trust and reputation systems. We use Citizen Information Services (CIS) in local governments as an application domain for WikiFAQ because they are a rich source of diverse and dispersed users with direct and relevant experience.

WIKIFAQ: Obtaining Complete FAQs

Our approach is to give privacy to the profile and behaviour of the user; the state of the art for privacy consists of encryption algorithms, occultation and temporary association of a user's information. In all cases these aspects present pros and cons. A primary disadvantage is that within a certain amount of time an attacker is capable of reconstruct the original information (encryptation), finding the information (occultation) and relating it to the original user (temporary association). In our approach, full dissociation is used to impede any relation with the original user. It is the concept of full dissociation which considerably reduces the available time for an attacker to discover the relation with the original user.

Sonia Delfin

Papers

Embedding Emotional Context in Recommender Systems

Social Currencies And Knowledge Currencies

WIKIFAQ: Obtaining Complete FAQs

Improving Privacy of Recommender Agents by Means of Full Dissociation