Rating prediction for recommendation: Constructing user profiles and item characteristics using backpropagation

Recommender systems play an important role in quickly identifying and recommending most acceptable products to the users. The latent user factors and item characteristics determine the degree of user satisfaction on an item. While many of the methods in the literature have assumed that these factors are linear, there are some other methods that treat these factors as nonlinear; but they do it in a more implicit way. In this paper, we have investigated the effect of true nature (i.e., nonlinearity) of the user factors and item characteristics, and their complex layered relationship on rating prediction. We propose a new deep feedforward network that learns both the factors and their complex relationship concurrently. The aim of our study was to automate the construction of user profiles and item characteristics without using any demographic information and then use these constructed features to predict the degree of acceptability of an item to a user. We constructed the user and item factors by using separate learner weights at the lower layers, and modeled their complex relationship in the upper layers. The construction of the user profiles and the item characteristics, solely based on rating triples (i.e., user id, item id, rating), overcomes the requirement of explicit demographic information be given to the system. We have tested our model on three real world datasets: Jester, Movielens, and Yahoo music. Our model produces better rating predictions than some of the state-of-the-art methods which use demographic information. The root mean squared error incurred by our model on these datasets are 4.0873, 0.8110, and 0.9408 respectively. The errors are smaller than current best existing models’ errors in these datasets. The results show that our system can be integrated to any web store where development of hand engineered features for recommending products is less feasible due to huge traffics and also that there is a lack of demographic information about the users and the items.     

Fuzzy approach for intrusion detection based on user’s commands

The article concerns the problem of detecting masqueraders in computer systems. A masquerader in a computer system is an intruder who pretends to be a legitimate user in order to gain access to protected resources. The article presents an intrusion detection method based on a fuzzy approach. Two types of user’s activity profiles are proposed along with the corresponding data structures. The solution analyzes the activity of the computer user in a relatively short period of time, building a user’s profile. The profile is based on the most recent activity of the user, therefore, it is named the local profile. Further analysis involves creating a more general structure based on a defined number of local profiles of one user, called the fuzzy profile. It represents a generalized behavior of the computer system user. The fuzzy profiles are used directly to detect abnormalities in users’ behavior, and thus possible intrusions. The proposed solution is prepared to be able to create user’s profiles based on any countable features derived from user’s actions in computer system (i.e., used commands, mouse and keyboard data, requested network resources). The presented method was tested using one of the commonly available standard intrusion data sets containing command names executed by users of a Unix system. Therefore, the obtained results can be compared with other approaches. The results of the experiments have shown that the method presented in this article is comparable with the best intrusion detection methods, tested with the same data set, in the matter of the obtained results. The proposed solution is characterized by a very low computational complexity, which has been confirmed by experimental results.     

A Hierarchical Fuzzy Clustering-based System to Create User Profiles

The rapid development of the World Wide Web as a medium of commerce and information dissemination has generated a growing interest of web portal managers in systems able to identify user profiles from the web access logs. The interpretation of these profiles can help re-organize the web portal, e.g., by restructuring the site’s content more efficiently, or even to build adaptive web portals, i.e., portals whose organization and presentation change depending on the specific visitor’s needs. In this paper, we assume that the pages of the web portal have been prearranged in a number of different categories. We introduce a systematic approach to determine a hierarchy of user profiles from the history of users’ accesses to the categories. First, we filter the access log by removing both occasional users and categories of poor interest. Then, we apply an Unsupervised Fuzzy Divisive Hierarchical Clustering (UFDHC) algorithm to cluster the users of the web portal into a hierarchy of fuzzy groups characterized by a set of common interests and each represented by a prototype, which defines the profile of the group typical member. To identify the profile a specific user belongs to, we propose a novel classification method which completely exploits the information contained in the hierarchy. To prove the effectiveness of our approach, we apply the UFDHC algorithm to access log data collected over a period of 15 days and use the classification method to associate a profile with the users defined by access log data collected during subsequent 60 days. Finally, we highlight the good characteristics of our system by comparing our results with the ones obtained by applying a profiling system based on a modified version of the fuzzy C-means.     

Resolving the Topology Mismatch Problem in Unstructured Peer-to-Peer Networks

Prior studies show that more than 70 percent of communication paths in a popular unstructured peer-to-peer (P2P) system (i.e., Gnutella) do not exploit the physical network topology, leading to the topology mismatch problem, and thus, lengthen communication between participating peers. While previous efforts in solving overlay topology matching problems do not guarantee the bounds of performance metrics (e.g., the communication delay between any two overlay peers and the broadcasting scope of any participating peer), in this paper, we present a novel topology matching algorithm that has provable performance qualities. In our proposal, each participating node creates and manages a constant number of overlay connections to other peers in a distributed manner. In rigorous performance analysis, we show that 1) the expected overlay communication delay between any two nodes in our P2P network is a constant; 2) in addition, any joining node has the exponential broadcasting scope in expectation; 3) furthermore, a participating node takes a polylogarithmic overhead to exploit the physical network locality and maintain its flooding scope. Together with extensive simulations, we present our proposal that significantly outperforms two recent solutions, i.e., THANCS and mOverlay, in terms of overlay communication latency and/or broadcasting scope.     

A semantic approach to remove incoherent items from a user profile and improve the accuracy of a recommender system

Recommender systems usually suggest items by exploiting all the previous interactions of the users with a system (e.g., in order to decide the movies to recommend to a user, all the movies she previously purchased are considered). This canonical approach sometimes could lead to wrong results due to several factors, such as a change in user preferences over time, or the use of her account by third parties. This kind of incoherence in the user profiles defines a lower bound on the error the recommender systems may achieve when they generate suggestions for a user, an aspect known in literature as magic barrier. This paper proposes a novel dynamic coherence-based approach to define the user profile used in the recommendation process. The main aim is to identify and remove, from the previously evaluated items, those not semantically adherent to the others, in order to make a user profile as close as possible to the user’s real preferences, solving the aforementioned problems. Moreover, reshaping the user profile in such a way leads to great advantages in terms of computational complexity, since the number of items considered during the recommendation process is highly reduced. The performed experiments show the effectiveness of our approach to remove the incoherent items from a user profile, increasing the recommendation accuracy.     

Students' profiles of ICT use: Identification,determinants, and relations to achievement in a computer and information literacy test

Current debates on students' use of information and communication technology (ICT) have brought to attention profiles and purposes of ICT use in either school-related or recreational contexts. Examining these two contexts at the same time, the present study seeks to identify student profiles of ICT use on the basis of the Norwegian International Computer and Information Literacy Study (ICILS) 2013 data (N = 2426). In order to explore profiles of ICT use in schools and at home for different purposes such as recreation, study purposes, exchanging information, and social communication, we take a person-centered approach and apply latent profile analysis. These analyses revealed two independent user profiles and showed that background characteristics (i.e., gender, immigration status) and motivational constructs (i.e., self-efficacy, interest, and enjoyment in ICT) play a significant role in determining profile membership. Significant differences between the user profiles in students' computer and information literacy test performance did not exist. Given that the coverage of ICT at home and in schools has increased substantially over the last decades, the identification of user profiles informs teachers and parents about whether or not students exploit these opportunities to the same extent. Implications for future research and practice are discussed.     

An optimization model for collaborative recommendation using a covariance-based regularizer

This paper suggests a convex regularized optimization model to produce recommendations, which is adaptable, fast, and scalable—while remaining very competitive to state-of-the-art methods in terms of accuracy. We introduce a regularizer based on the covariance matrix such that the model minimizes two measures ensuring that the recommendations provided to a user are guided by both the preferences of the other users in the system and the known preferences of the user being processed. It is adaptable since (1) it can be viewed from both user and item perspectives (allowing to choose, depending on the task, the formulation with fewer decision variables) and (2) multiple constraints depending on the context (and not only based on the accuracy, but also on the utility of personalized recommendations) can easily be added, as shown in this paper through two examples. Since our regularizer is based on the covariance matrix, this paper also describes how to improve computational and space complexities by using matrix factorization techniques in the optimization model, leading to a fast and scalable model. To illustrate all these concepts, experiments were conducted on four real datasets of different sizes (i.e., FilmTrust, Ciao, MovieLens, and Netflix) and comparisons with state-of-the-art methods are provided, showing that our context-sensitive approach is very competitive in terms of accuracy.     

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.     

EEUPL: Towards effective and efficient user profile linkage across multiple social platforms

Linking user profiles belonging to the same people across multiple social networks underlines a wide range of applications, such as cross-platform prediction, cross-platform recommendation, and advertisement. Most of existing approaches focus on pairwise user profile linkage between two platforms, which can not effectively piece up information from three or more social platforms. Different from the previous work, we investigate scalable user profile linkage across multiple social platforms by proposing an effective and efficient model called EEUPL, which can detect duplicate profiles within one platform that belong to same person and is implemented with Apache Spark for distributed execution. The model contains two key components: 1) To link cross-platform user profiles effectively, we propose an average-link strategy based clustering method. 2) To extend the model EEUPL to large-scale datasets, an Apache Spark based approach is developed. Extensive experiments are conducted on two real-world datasets, and the results demonstrate the superiority of the model EEUPL compared with the state-of-art methods.

     

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.     

An assessment of operational coverage as both an adequacy and a selection criterion for operational profile based testing

While the relation between code coverage measures and fault detection is actively studied, only few works have investigated the correlation between measures of coverage and of reliability. In this work, we introduce a novel approach to measuring code coverage, called the operational coverage, that takes into account how much the program’s entities are exercised so to reflect the profile of usage into the measure of coverage. Operational coverage is proposed as (i) an adequacy criterion, i.e., to assess the thoroughness of a black box test suite derived from the operational profile, and as (ii) a selection criterion, i.e., to select test cases for operational profile-based testing. Our empirical evaluation showed that operational coverage is better correlated than traditional coverage with the probability that the next test case derived according to the user’s profile will not fail. This result suggests that our approach could provide a good stopping rule for operational profile-based testing. With respect to test case selection, our investigations revealed that operational coverage outperformed the traditional one in terms of test suite size and fault detection capability when we look at the average results.     

Query representation and management in a multiparadigmatic visual query environment

We propose a framework for database querying providing the user with several interaction paradigms based on different (i.e., form-based, diagrammatic, iconic, and hybrid) visual representations of the database. A unified model, namely the Graph Model, is used as the common underlying model, in terms of which databases expressed in the most common data models can be easily converted. Graph Model databases can be queried by means of the multiparadigmatic interface. The semantics of the query operations is formally defined in terms of the Graphical Primitives. Such a formal approach enables the query manager to maintain the same query consistently in any representation. In the proposed multiparadigmatic environment, the user can switch from one interaction paradigm to another during query formulation, so that the most suitable query representation can be found.     

Community-Aware Resource Profiling for Personalized Search in Folksonomy

In recent years,there is a fast proliferation of collaborative tagging(a.k.a.folksonomy) systems in Web 2.0 communities.With the increasingly large amount of data,how to assist users in searching their interested resources by utilizing these semantic tags becomes a crucial problem.Collaborative tagging systems provide an environment for users to annotate resources,and most users give annotations according to their perspectives or feelings.However,users may have different perspectives or feelings on resources,e.g.,some of them may share similar perspectives yet have a conflict with others.Thus,modeling the profile of a resource based on tags given by all users who have annotated the resource is neither suitable nor reasonable.We propose,to tackle this problem in this paper,a community-aware approach to constructing resource profiles via social filtering.In order to discover user communities,three different strategies are devised and discussed.Moreover,we present a personalized search approach by combining a switching fusion method and a revised needs-relevance function,to optimize personalized resources ranking based on user preferences and user issued query.We conduct experiments on a collected real life dataset by comparing the performance of our proposed approach and baseline methods.The experimental results verify our observations and effectiveness of proposed method.     

Finding Diachronic Like‐Minded Users

User communities in social networks are usually identified by considering explicit structural social connections between users. While such communities can reveal important information about their members such as family or friendship ties and geographical proximity, just to name a few, they do not necessarily succeed at pulling like‐minded users that share the same interests together. Therefore, researchers have explored the topical similarity of social content to build like‐minded communities of users. In this article, following the topic‐based approaches, we are interested in identifying communities of users that share similar topical interests with similar temporal behavior. More specifically, we tackle the problem of identifying temporal (diachronic) topic‐based communities, i.e., communities of users who have a similar temporal inclination toward emerging topics. To do so, we utilize multivariate time series analysis to model the contributions of each user toward emerging topics. Further, our modeling is completely agnostic to the underlying topic detection method. We extract topics of interest by employing seminal topic detection methods; one graph‐based and two latent Dirichlet allocation‐based methods. Through our experiments on Twitter data, we demonstrate the effectiveness of our proposed temporal topic‐based community detection method in the context of news recommendation, user prediction, and document timestamp prediction applications, compared with the nontemporal as well as the state‐of‐the‐art temporal approaches.     

The impact of data obfuscation on the accuracy of collaborative filtering

Collaborative filtering (CF) is a widely-used technique for generating personalized recommendations. CF systems are typically based on a central storage of user profiles, i.e., the ratings given by users to items. Such centralized storage introduces potential privacy breach, since all the user profiles may be accessible by untrusted parties when breaking the access control of the centralized system. Hence, recent studies have focused on enhancing the privacy of CF users by distributing their user profiles across multiple repositories and obfuscating the user profiles to partially hide the actual user ratings. This work combines these two techniques and investigates the unavoidable side effect of data obfuscation: the reduction of the accuracy of the generated CF predictions. The evaluation, which was conducted using three different datasets, shows that considerable parts of the user profiles can be modified without observing a substantial decrease of the CF prediction accuracy. The evaluation also indicates what parts of the user profiles are required for generating accurate CF predictions. In addition, we conducted an exploratory user study that reveals positive attitude of users towards the data obfuscation.     

Predicting the level of cooperation in a Peer-to-Peer live streaming application

The Peer-to-Peer (P2P) architecture has been successfully used to reduce costs and increase the scalability of Internet live streaming systems. However, the effectiveness of these applications depends largely on user (peer) cooperation. In this article we use data collected from SopCast, a popular P2P live application, to show that there is high correlation between peer centrality—out-degree, out-closeness, and betweenness—in the P2P overlay graph and peer cooperation. We use this finding to propose a new regression-based model to predict peer cooperation from its past centrality. Our model takes only peer out-degrees as input, as out-degree has the strongest correlation with peer cooperation. Our evaluation shows that our model has good accuracy and does not need to be trained too often (e.g., once each 16 min). We also use our model to sketch a mechanism to detect malicious peers that report artificially inflated cooperation aiming at, for example, receiving better quality of service.     

Evolutionary design of user interfaces for workflow information systems

In this paper we argue that user interface design should evolve from iterative to evolutionary in order to support the user interface development life cycle in a more flexible way. Evolutionary design consists of taking any input that informs to the lifecycle at any level of abstraction and its propagation through inferior and superior levels (vertical engineering) as well as the same level (horizontal engineering). This lifecycle is particularly appropriate when requirements are incomplete, partially unknown or to be discovered progressively. We exemplify this lifecycle by a methodology for developing user interfaces of workflow information systems. The methodology involves several models (i.e., task, process, workflow, domain, context of use) and steps. The methodology applies model-driven engineering to derive concrete user interfaces from a workflow model imported into a workflow management system in order to run the workflow. Instead of completing each model step by step, any model element is either derived from early requirements or collected in the appropriate model before being propagated in the subsequent steps. When more requirements are elicited, any new element is added at the appropriate level, consolidated with the already existing elements, and propagated to the subsequent levels. A workflow editor has been developed to support the methodology.     

Recommendations based on a heterogeneous spatio-temporal social network

Recommender systems in location-based social networks (LBSNs), such as Facebook Places and Foursquare, have focused on recommending friends or locations to registered users by combining information derived from explicit (i.e. friendship network) and implicit (i.e. user-item rating network, user-location network, etc.) sub-networks. However, previous models were static and failed to adequately capture user time-varying preferences. In this paper, we provide a novel recommendation method based on the time dimension as well. We construct a hybrid tripartite (i.e., user, location, session) graph, which incorporates 7 different unipartite and bipartite graphs. Then, we test it with an extended version of the Random Walk with Restart (RWR) algorithm, which randomly walks through the network by using paths of 7 differently weighted edge types (i.e., user-location, user-session, user-user, etc.). We evaluate experimentally our method and compare it against three state-of-the-art algorithms on two real-life datasets; we show a significant prevalence of our method over its competitors.     

Ontology driven semantic profiling and retrieval in medical information systems

We propose the application of a novel sub-ontology extraction methodology for achieving interoperability and improving the semantic validity of information retrieval in the medical information systems (MIS) domain. The system offers advanced profiling of a user’s field of specialization by exploiting the concept of sub-ontology extraction, i.e., each sub-ontology may subsequently represent a particular user profile. Semantic profiling of a user’s field of specialization or interest is necessary functionality in any medical domain information retrieval system; this is because the (structural and semantic) extent of information sources is massive and individual users are only likely to be interested in specific parts of the overall knowledge documents on the basis of their area of specialization. The prototypical system, OntoMOVE, has been specifically designed for application in the medical information systems domain. OntoMOVE utilizes semantic web standards like RDF(S) and OWL in addition to medical domain standards and vocabularies encompassed by the UMLS knowledge sources.     

Evolutionary approach for semantic-based query sampling in large-scale information sources

Metadata about information sources (e.g., databases and repositories) can be collected by Query Sampling (QS). Such metadata can include topics and statistics (e.g., term frequencies) about the information sources. This provides important evidence for determining which sources in the distributed information space should be selected for a given user query. The aim of this paper is to find out the semantic relationships between the information sources in order to distribute user queries to a large number of sources. Thereby, we propose an evolutionary approach for automatically conducting QS using multiple crawlers and obtaining the optimized semantic network from the sources. The aim of combining QS and evolutionary methods is to collaboratively extract metadata about target sources and optimally integrate the metadata, respectively. For evaluating the performance of contextualized QS on 122 information sources, we have compared the ranking lists recommended by the proposed method with user feedback (i.e., ideal ranks), and also computed the precision of the discovered subsumptions in terms of the semantic relationships between the target sources.