Provider fairness across continents in collaborative recommender systems

When a recommender system suggests items to the end-users, it gives a certain exposure to the providers behind the recommended items. Indeed, the system offers a possibility to the items of those providers of being reached and consumed by the end-users. Hence, according to how recommendation lists are shaped, the experience of under-recommended providers in online platforms can be affected. To study this phenomenon, we focus on movie and book recommendation and enrich two datasets with the continent of production of an item. We use this data to characterize imbalances in the distribution of the user–item observations and regarding where items are produced (geographic imbalance). To assess if recommender systems generate a disparate impact and (dis)advantage a group, we divide items into groups, based on their continent of production, and characterize how represented is each group in the data. Then, we run state-of-the-art recommender systems and measure the visibility and exposure given to each group. We observe disparities that favor the most represented groups. We overcome these phenomena by introducing equity with a re-ranking approach that regulates the share of recommendations given to the items produced in a continent (visibility) and the positions in which items are ranked in the recommendation list (exposure), with a negligible loss in effectiveness, thus controlling fairness of providers coming from different continents. A comparison with the state of the art shows that our approach can provide more equity for providers, both in terms of visibility and of exposure.     

Building user profiles based on sequences for content and collaborative filtering

Modeling user profiles is a necessary step for most information filtering systems – such as recommender systems – to provide personalized recommendations. However, most of them work with users or items as vectors, by applying different types of mathematical operations between them and neglecting sequential or content-based information. Hence, in this paper we study how to propose an adaptive mechanism to obtain user sequences using different sources of information, allowing the generation of hybrid recommendations as a seamless, transparent technique from the system viewpoint. As a proof of concept, we develop the Longest Common Subsequence (LCS) algorithm as a similarity metric to compare the user sequences, where, in the process of adapting this algorithm to recommendation, we include different parameters to control the efficiency by reducing the information used in the algorithm (preference filter), to decide when a neighbor is considered useful enough to be included in the process (confidence filter), to identify whether two interactions are equivalent (δ-matching threshold), and to normalize the length of the LCS in a bounded interval (normalization functions). These parameters can be extended to work with any type of sequential algorithm.We evaluate our approach with several state-of-the-art recommendation algorithms using different evaluation metrics measuring the accuracy, diversity, and novelty of the recommendations, and analyze the impact of the proposed parameters. We have found that our approach offers a competitive performance, outperforming content, collaborative, and hybrid baselines, and producing positive results when either content- or rating-based information is exploited.     

Enhancing sequential recommendation with contrastive Generative Adversarial Network

Sequential recommendation models a user’s historical sequence to predict future items. Existing studies utilize deep learning methods and contrastive learning for data augmentation to alleviate data sparsity. However, these existing methods cannot learn accurate high-quality item representations while augmenting data. In addition, they usually ignore data noise and user cold-start issues. To solve the above issues, we investigate the possibility of Generative Adversarial Network (GAN) with contrastive learning for sequential recommendation to balance data sparsity and noise. Specifically, we propose a new framework, Enhanced Contrastive Learning with Generative Adversarial Network for Sequential Recommendation (ECGAN-Rec), which models the training process as a GAN and recommendation task as the main task of the discriminator. We design a sequence augmentation module and a contrastive GAN module to implement both data-level and model-level augmentations. In addition, the contrastive GAN learns more accurate high-quality item representations to alleviate data noise after data augmentation. Furthermore, we propose an enhanced Transformer recommender based on GAN to optimize the performance of the model. Experimental results on three open datasets validate the efficiency and effectiveness of the proposed model and the ability of the model to balance data noise and data sparsity. Specifically, the improvement of ECGAN-Rec in two evaluation metrics (HR@N and NDCG@N) compared to the state-of-the-art model performance on the Beauty, Sports and Yelp datasets are 34.95%, 36.68%, and 13.66%, respectively. Our implemented model is available via https://github.com/nishawn/ECGANRec-master.     

A social recommendation method based on an adaptive neighbor selection mechanism

Recommender systems are techniques to make personalized recommendations of items to users. In e-commerce sites and online sharing communities, providing high quality recommendations is an important issue which can help the users to make effective decisions to select a set of items. Collaborative filtering is an important type of the recommender systems that produces user specific recommendations of the items based on the patterns of ratings or usage (e.g. purchases). However, the quality of predicted ratings and neighbor selection for the users are important problems in the recommender systems. Selecting suitable neighbors set for the users leads to improve the accuracy of ratings prediction in recommendation process. In this paper, a novel social recommendation method is proposed which is based on an adaptive neighbor selection mechanism. In the proposed method first of all, initial neighbors set of the users is calculated using clustering algorithm. In this step, the combination of historical ratings and social information between the users are used to form initial neighbors set for the users. Then, these neighbor sets are used to predict initial ratings of the unseen items. Moreover, the quality of the initial predicted ratings is evaluated using a reliability measure which is based on the historical ratings and social information between the users. Then, a confidence model is proposed to remove useless users from the initial neighbors of the users and form a new adapted neighbors set for the users. Finally, new ratings of the unseen items are predicted using the new adapted neighbors set of the users and the $top\_N$ interested items are recommended to the active user. Experimental results on three real-world datasets show that the proposed method significantly outperforms several state-of-the-art recommendation methods.     

A collaborative filtering recommender system using genetic algorithm

This paper presents a novel genetic-based recommender system (BLI_GA) that depends on the semantic information and historical rating data. The main contribution of this research lies in evaluating the possible recommendation lists instead of evaluating items then forming the recommendation list. BLI_GA utilizes the genetic algorithm to find the best list of items to the active user. Thus, each individual represents a candidate recommendation list. BLI_GA hierarchically evaluates the individuals using three fitness functions. The first function uses semantic information about items to estimates the strength of the semantic similarity between items. The second function estimates the similarity in satisfaction level between users. The third function depends on the predicted ratings to select the best recommendation list.BLI_GA results have been compared against recommendation results from alternative collaborative filtering methods. The results demonstrate the superiority of BLI_GA and its capability to achieve more accurate predictions than the alternative methods regardless of the number of K-neighbors.     

Effective top-k computation with term-proximity support

Modern web search engines are expected to return the top-k results efficiently. Although many dynamic index pruning strategies have been proposed for efficient top-k computation, most of them are prone to ignoring some especially important factors in ranking functions, such as term-proximity (the distance relationship between query terms in a document). In our recent work [Zhu, M., Shi, S., Li, M., & Wen, J. (2007). Effective top-k computation in retrieving structured documents with term-proximity support. In Proceedings of 16th CIKM conference (pp. 771–780)], we demonstrated that, when term-proximity is incorporated into ranking functions, most existing index structures and top-k strategies become quite inefficient. To solve this problem, we built the inverted index based on web page structure and proposed the query processing strategies accordingly. The experimental results indicate that the proposed index structures and query processing strategies significantly improve the top-k efficiency. In this paper, we study the possibility of adopting additional techniques to further improve top-k computation efficiency. We propose a Proximity-Probe Heuristic to make our top-k algorithms more efficient. We also test the efficiency of our approaches on various settings (linear or non-linear ranking functions, exact or approximate top-k processing, etc.).     

Personalized hybrid recommendation for group of users: Top-N multimedia recommender

Nowadays, the increasing demand for group recommendations can be observed. In this paper we address the problem of recommendation performance for groups of users (group recommendation). We focus on the performance of very Top-N recommendations, which are important when recommending the long lasting items (only a few such items are consumed per session, e.g. movie). To improve existing group recommenders we propose a mixed hybrid recommender for groups combining content-based and collaborative strategies. The principle of proposed group recommender is to generate content and collaborative recommendations for each user, apply an aggregation strategy to solve the group conflict preferences for the content and collaborative sets separately, and finally reorder the collaborative candidates based on the content-based ones. It is based on an idea that candidates recommended by both recommendation strategies at the same time are presumably more appropriate for the group than the candidates recommended by individual strategies. The evaluation is performed by several experiments in the multimedia domain (as typical representative for group recommendations). Both, online and offline experiments were performed in order to compare real users’ satisfaction to the standard group recommenders and also, to compare performance of proposed approach to the state-of-the-art recommenders based on the MovieLens dataset. Finally, we experimented with the proposed hybrid recommender to generate the recommendation for a group of size one (i.e. single user recommendation). Obtained results, support our hypothesis that proposed mixed hybrid approach improves the precision of the recommendation for groups of users and for the single-user recommendation respectively on very Top-N recommended items.     

Investigating and counteracting popularity bias in group recommendations

Popularity bias is an undesirable phenomenon associated with recommendation algorithms where popular items tend to be suggested over long-tail ones, even if the latter would be of reasonable interest for individuals. Such intrinsic tendencies of the recommenders may lead to producing ranked lists, in which items are not equally covered along the popularity tail. Although some recent studies aim to detect such biases of traditional algorithms and treat their effects on recommendations, the concept of popularity bias remains elusive for group recommender systems. Therefore, in this study, we focus on investigating popularity bias from the view of group recommender systems, which aggregate individual preferences to achieve recommendations for groups of users. We analyze various state-of-the-art aggregation techniques utilized in group recommender systems regarding their bias towards popular items. To counteract possible popularity issues in group recommendations, we adapt a traditional re-ranking approach that weighs items inversely proportional to their popularity within a group. Also, we propose a novel popularity bias mitigation procedure that re-ranks items by incorporating their popularity level and estimated group ratings in two distinct strategies. The first one aims to penalize popular items during the aggregation process highly and avoids bias better, while the second one puts more emphasis on group ratings than popularity and achieves a more balanced performance regarding conflicting goals of mitigating bias and boosting accuracy. Experiments performed on four real-world benchmark datasets demonstrate that both strategies are more efficient than the adapted approach, and empowering aggregation techniques with one of these strategies significantly decreases their bias towards popular items while maintaining reasonable ranking accuracy.     

A probabilistic music recommender considering user opinions and audio features

A recommender system has an obvious appeal in an environment where the amount of on-line information vastly outstrips any individual’s capability to survey. Music recommendation is considered a popular application area. In order to make personalized recommendations, many collaborative music recommender systems (CMRS) focus on capturing precise similarities among users or items based on user historical ratings. Despite the valuable information from audio features of music itself, however, few studies have investigated how to utilize information extracted directly from music for personalized recommendation in CMRS. In this paper, we describe a CMRS based on our proposed item-based probabilistic model, where items are classified into groups and predictions are made for users considering the Gaussian distribution of user ratings. In addition, this model has been extended for improved recommendation performance by utilizing audio features that help alleviate three well-known problems associated with data sparseness in collaborative recommender systems: user bias, non-association, and cold start problems in capturing accurate similarities among items. Experimental results based on two real-world data sets lead us to believe that content information is crucial in achieving better personalized recommendation beyond user ratings. We further show how primitive audio features can be combined into aggregate features for the proposed CRMS and analyze their influences on recommendation performance. Although this model was developed originally for music collaborative recommendation based on audio features, our experiment with the movie data set demonstrates that it can be applied to other domains.     

A unifying and general account of fairness measurement in recommender systems

Fairness is fundamental to all information access systems, including recommender systems. However, the landscape of fairness definition and measurement is quite scattered with many competing definitions that are partial and often incompatible. There is much work focusing on specific – and different – notions of fairness and there exist dozens of metrics of fairness in the literature, many of them redundant and most of them incompatible. In contrast, to our knowledge, there is no formal framework that covers all possible variants of fairness and allows developers to choose the most appropriate variant depending on the particular scenario. In this paper, we aim to define a general, flexible, and parameterizable framework that covers a whole range of fairness evaluation possibilities. Instead of modeling the metrics based on an abstract definition of fairness, the distinctive feature of this study compared to the current state of the art is that we start from the metrics applied in the literature to obtain a unified model by generalization. The framework is grounded on a general work hypothesis: interpreting the space of users and items as a probabilistic sample space, two fundamental measures in information theory (Kullback–Leibler Divergence and Mutual Information) can capture the majority of possible scenarios for measuring fairness on recommender system outputs. In addition, earlier research on fairness in recommender systems could be viewed as single-sided, trying to optimize some form of equity across either user groups or provider/procurer groups, without considering the user/item space in conjunction, thereby overlooking/disregarding the interplay between user and item groups. Instead, our framework includes the notion of statistical independence between user and item groups. We finally validate our approach experimentally on both synthetic and real data according to a wide range of state-of-the-art recommendation algorithms and real-world data sets, showing that with our framework we can measure fairness in a general, uniform, and meaningful way.     

Dual disentanglement of user–item interaction for recommendation with causal embedding

To achieve personalized recommendations, the recommender system selects the items that users may like by learning the collected user–item interaction data. However, the acquisition and use of data usually form a feedback loop, which leads to recommender systems suffering from popularity bias. To solve this problem, we propose a novel dual disentanglement of user–item interaction for recommendation with causal embedding (DDCE). Different from the existing work, our innovation is we take into account double-end popularity bias from the user-side and the item-side. Firstly, we perform a causal analysis of the reasons for user–item interaction and obtain the causal embedding representation of each part according to the analysis results. Secondly, on the item-side, we consider the influence of item attributes on popularity to improve the reliability of the item popularity. Then, on the user-side, we consider the effect of the time series when obtaining users’ interest. We model the contrastive learning task to disentangle users’ long–short-term interests, which avoids the bias of long–short-term interests overlapping, and use the attention mechanism to realize the dynamic integration of users’ long–short-term interests. Finally, we realize the disentanglement of user–item interaction reasons by decoupling user interest and item popularity. We experiment on two real-world datasets (Douban Movie and KuaiRec) to verify the significance of DDCE, the average improvement of DDCE in three evaluation metrics (NDCG, HR, and Recall) compared to the state-of-the-art model are 5.1106% and 4.1277% (MF as the backbone), 3.8256% and 3.2790% (LightGCN as the backbone), respectively.     

Addressing ontology-based question answering with collections of user queries

This paper presents QACID an ontology-based Question Answering system applied to the CInema Domain. This system allows users to retrieve information from formal ontologies by using as input queries formulated in natural language. The original characteristic of QACID is the strategy used to fill the gap between users’ expressiveness and formal knowledge representation. This approach is based on collections of user queries and offers a simple adaptability to deal with multilingual capabilities, inter-domain portability and changes in user information requirements. All these capabilities permit developing Question Answering applications for actual users. This system has been developed and tested on the Spanish language and using an ontology modelling the cinema domain. The performance level achieved enables the use of the system in real environments.     

A deep recommendation model of cross-grained sentiments of user reviews and ratings

The matrix factorization model based on user-item rating data has been widely studied and applied in recommender systems. However, data sparsity, the cold-start problem, and poor explainability have restricted its performance. Textual reviews usually contain rich information about items’ features and users’ sentiments and preferences, which can solve the problem of insufficient information from only user ratings. However, most recommendation algorithms that take sentiment analysis of review texts into account are either fine- or coarse-grained, but not both, leading to uncertain accuracy and comprehensiveness regarding user preference. This study proposes a deep learning recommendation model (i.e., DeepCGSR) that integrates textual review sentiments and the rating matrix. DeepCGSR uses the review sets of users and items as a corpus to perform cross-grained sentiment analysis by combining fine- and coarse-grained levels to extract sentiment feature vectors for users and items. Deep learning technology is used to map between the extracted feature vector and latent factor through the rating-based matrix factorization model and obtain deep, nonlinear features to predict the user's rating of an item. Iterative experiments on e-commerce datasets from Amazon show that DeepCGSR consistently outperforms the recommendation models LFM, SVD++, DeepCoNN, TOPICMF, and NARRE. Overall, comparing with other recommendation models, the DeepCGSR model demonstrated improved evaluation results by 14.113% over LFM, 13.786% over SVD++, 9.920% over TOPICMF, 5.122% over DeepCoNN, and 2.765% over NARRE. Meanwhile, the DeepCGSR has great potential in fixing the overfitting and cold-start problems. Built upon previous studies and findings, the DeepCGSR is the state of the art, moving the design and development of the recommendation algorithms forward with improved recommendation accuracy.     

A social-semantic recommender system for advertisements

Social applications foster the involvement of end users in Web content creation, as a result of which a new source of vast amounts of data about users and their likes and dislikes has become available. Having access to users’ contributions to social sites and gaining insights into the consumers’ needs is of the utmost importance for marketing decision making in general, and to advertisement recommendation in particular. By analyzing this information, advertisement recommendation systems can attain a better understanding of the users’ interests and preferences, thus allowing these solutions to provide more precise ad suggestions. However, in addition to the already complex challenges that hamper the performance of recommender systems (i.e., data sparsity, cold-start, diversity, accuracy and scalability), new issues that should be considered have also emerged from the need to deal with heterogeneous data gathered from disparate sources. The technologies surrounding Linked Data and the Semantic Web have proved effective for knowledge management and data integration. In this work, an ontology-based advertisement recommendation system that leverages the data produced by users in social networking sites is proposed, and this approach is substantiated by a shared ontology model with which to represent both users’ profiles and the content of advertisements. Both users and advertisement are represented by means of vectors generated using natural language processing techniques, which collect ontological entities from textual content. The ad recommender framework has been extensively validated in a simulated environment, obtaining an aggregated f-measure of 79.2% and a Mean Average Precision at 3 (MAP@3) of 85.6%.     

Dynamic intent-aware iterative denoising network for session-based recommendation

Session-based recommendation aims to predict items that a user will interact with based on historical behaviors in anonymous sessions. It has long faced two challenges: (1) the dynamic change of user intents which makes user preferences towards items change over time; (2) the uncertainty of user behaviors which adds noise to hinder precise preference learning. They jointly preclude recommender system from capturing real intents of users. Existing methods have not properly solved these problems since they either ignore many useful factors like the temporal information when building item embeddings, or do not explicitly filter out noisy clicks in sessions. To tackle above issues, we propose a novel Dynamic Intent-aware Iterative Denoising Network (DIDN) for session-based recommendation. Specifically, to model the dynamic intents of users, we present a dynamic intent-aware module that incorporates item-aware, user-aware and temporal-aware information to learn dynamic item embeddings. A novel iterative denoising module is then devised to explicitly filter out noisy clicks within a session. In addition, we mine collaborative information to further enrich the session semantics. Extensive experimental results on three real-world datasets demonstrate the effectiveness of the proposed DIDN. Specifically, DIDN obtains improvements over the best baselines by 1.66%, 1.75%, and 7.76% in terms of P@20 and 1.70%, 2.20%, and 10.48% in terms of MRR@20 on all datasets.     

Evaluating collaborative filtering recommendations inside large learning object repositories

Collaborative filtering (CF) algorithms are techniques used by recommender systems to predict the utility of items for users based on the similarity among their preferences and the preferences of other users. The enormous growth of learning objects on the internet and the availability of preferences of usage by the community of users in the existing learning object repositories (LORs) have opened the possibility of testing the efficiency of CF algorithms on recommending learning materials to the users of these communities. In this paper we evaluated recommendations of learning resources generated by different well known memory-based CF algorithms using two databases (with implicit and explicit ratings) gathered from the popular MERLOT repository. We have also contrasted the results of the generated recommendations with several existing endorsement mechanisms of the repository to explore possible relations among them. Finally, the recommendations generated by the different algorithms were compared in order to evaluate whether or not they were overlapping. The results found here can be used as a starting point for future studies that account for the specific context of learning object repositories and the different aspects of preference in learning resource selection.     

Incorporating group recommendations to recommender systems: Alternatives and performance

In collaborative filtering recommender systems recommendations can be made to groups of users. There are four basic stages in the collaborative filtering algorithms where the group’s users’ data can be aggregated to the data of the group of users: similarity metric, establishing the neighborhood, prediction phase, determination of recommended items. In this paper we perform aggregation experiments in each of the four stages and two fundamental conclusions are reached: (1) the system accuracy does not vary significantly according to the stage where the aggregation is performed, (2) the system performance improves notably when the aggregation is performed in an earlier stage of the collaborative filtering process. This paper provides a group recommendation similarity metric and demonstrates the convenience of tackling the aggregation of the group’s users in the actual similarity metric of the collaborative filtering process.     

An extensive study on the evolution of context-aware personalized travel recommender systems

Ever since the beginning of civilization, travel for various causes exists as an essential part of human life so as travel recommendations, though the early form of recommendations were the accrued experiences shared by the community. Modern recommender systems evolved along with the growth of Information Technology and are contributing to all industry and service segments inclusive of travel and tourism. The journey started with generic recommender engines which gave way to personalized recommender systems and further advanced to contextualized personalization with advent of artificial intelligence. Current era is also witnessing a boom in social media usage and the social media big data is acting as a critical input for various analytics with no exception for recommender systems. This paper details about the study conducted on the evolution of travel recommender systems, their features and current set of limitations. We also discuss on the key algorithms being used for classification and recommendation processes and metrics that can be used to evaluate the performance of the algorithms and thereby the recommenders.     

An impact of time and item influencer in collaborative filtering recommendations using graph-based model

Recommender Systems deal with the issue of overloading information by retrieving the most relevant sources in the wide range of web services. They help users by predicting their interests in many domains like e-government, social networks, e-commerce and entertainment. Collaborative Filtering (CF) is the most promising technique used in recommender systems to give suggestions based on liked-mind users’ preferences. Despite the widespread use of CF in providing personalized recommendation, this technique has problems including cold start, data sparsity and gray sheep. Eventually, these problems lead to the deterioration of the efficiency of CF. Most existing recommendation methods have been proposed to overcome the problems of CF. However, they fail to suggest the top-n recommendations based on the sequencing of the users’ priorities. In this research, to overcome the shortcomings of CF and current recommendation methods in ranking preference dataset, we have used a new graph-based structure to model the users’ priorities and capture the association between users and items. Users’ profiles are created based on their past and current interest. This is done because their interest can change with time. Our proposed algorithm keeps the preferred items of active user at the beginning of the recommendation list. This means these items come under top-n recommendations, which results in satisfaction among users. The experimental results demonstrate that our algorithm archives the significant improvement in comparison with CF and other proposed recommendation methods in terms of recall, precision, f-measure and MAP metrics using two benchmark datasets including MovieLens and Superstore.