User Profile Representation Research Articles

Psychometric investigation of the gamification Hexad user types scale with Brazilian Portuguese adolescents speakers

Gamification has been applied in different fields over the last years, impacting the development of technologies, services, and products towards a more game-like world. Albeit its success, some results indicated personal differences influencing the success of its application, leading to the creation of user models (e.g., Hexad), a way to represent user profiles in gamified environments. Even though a great effort has been made to create and discuss instruments to represent these user models, many of them lack investigation into their psychometric properties. At the same time, although gamification can be particularly interesting in engaging adolescents, few attempts analyzed instruments considering this population. Addressing this lack, in this study, we evaluated the psychometric properties of the gamification Hexad scale in Brazilian Portuguese considering a sample (N = 110) of adolescents aged between 13 and 16 years old. Through a quantitative study (i.e., confirmatory factor analysis and correlation), we analyzed the psychometric properties of the scale and the correlations between user types when using data collected from adolescents. Results demonstrated that the current version of the scale needs improvements to better assess the user types of the Brazilian adolescent population, especially regarding the Disruptor user type. Also, the user types presented fewer correlations when compared with the adult sample. At the same time that the results of this study can be used in the academy and industry as a source of measurement of user types from Brazilian adolescents, it also opens several possibilities for new studies in personalized gamification considering this population.

CupMar: A deep learning model for personalized news recommendation based on contextual user-profile and multi-aspect article representation

In modern days, making recommendation for news articles poses a great challenge due to vast amount of online information. However, providing personalized recommendations from news articles, which are the sources of condense textual information is not a trivial task. A recommendation system needs to understand both the textual information of a news article, and the user contexts in terms of long-term and temporary preferences via the user’s historic records. Unfortunately, many existing methods do not possess the capability to meet such need. In this work, we propose a neural deep news recommendation model called CupMar, that not only is able to learn the user-profile representation in different contexts, but also is able to leverage the multi-aspects properties of a news article to provide accurate, personalized news recommendations to users. The main components of our CupMar approach include the News Encoder and the User-Profile Encoder. Specifically, the News Encoder uses multiple properties such as news category, knowledge entity, title and body content with advanced neural network layers to derive informative news representation, while the User-Profile Encoder looks through a user’s browsed news, infers both of her long-term and recent preference contexts to encode a user representation, and finds the most relevant candidate news for her. We evaluate our CupMar model with extensive experiments on the popular Microsoft News Dataset (MIND), and demonstrate the strong performance of our approach.

Personality Analysis Using Classification on Turkish Tweets

According to the psychology literature, there is a strong correlation between the personality traits and the linguistic behavior of people. Due to increase in computer based communication, individuals express their personalities in written forms on social media. Hence, social media became a convenient resource to analyze the relationship between the personality traits and the lingusitic behaviour. Although there is a vast amount of studies on social media, only a small number of them focus on personality prediction. In this work, we aim to model the relationship between the social media messages of individuals and Big Five Personality Traits as a supervised learning problem. We use Twitter posts and user statistics for analysis. We investigated various approaches for user profile representation, explored several supervised learning techniques, and presented comparative analysis results. Our results confirm the findings of psychology literature, and we show that computational analysis of tweets using supervised learning methods can be used to determine the personality of individuals.

User Identity Linkage Across Social Networks by Heterogeneous Graph Attention Network Modeling

Today, social networks are becoming increasingly popular and indispensable, where users usually have multiple accounts. It is of considerable significance to conduct user identity linkage across social networks. We can comprehensively depict diversified characteristics of user behaviors, accurately model user profiles, conduct recommendations across social networks, and track cross social network user behaviors by user identity linkage. Existing works mainly focus on a specific type of user profile, user-generated content, and structural information. They have problems of weak data expression ability and ignored potential relationships, resulting in unsatisfactory performances of user identity linkage. Recently, graph neural networks have achieved excellent results in graph embedding, graph representation, and graph classification. As a graph has strong relationship expression ability, we propose a user identity linkage method based on a heterogeneous graph attention network mechanism (UIL-HGAN). Firstly, we represent user profiles, user-generated content, structural information, and their features in a heterogeneous graph. Secondly, we use multiple attention layers to aggregate user information. Finally, we use a multi-layer perceptron to predict user identity linkage. We conduct experiments on two real-world datasets: OSCHINA-Gitee and Facebook-Twitter. The results validate the effectiveness and advancement of UIL-HGAN by comparing different feature combinations and methods.

Matrix Factorization for Personalized Recommendation With Implicit Feedback and Temporal Information in Social Ecommerce Networks

Collaborative filtering with implicit feedback is regarded as one of the most challenging issues in social ecommerce networks. However, the scarcity of negative feedback and the impact of time makes collaborative filtering difficult to use. Most models assign a uniform weight to missing data, but this method is invalid in the real world and leads to a biased representation of user profiles. In social ecommerce networks, the popularity of an item is implicit social information that is dynamic and can affect the preferences of a user. In this paper, we propose a smart model named TimeMF to address the above issues by incorporating implicit feedback and temporal information into social ecommerce recommendation. The weighting scheme is based on the dynamic popularity of an item. Then, we present an objective function and adopt an optimization strategy to enhance the efficiency. The experimental results for a real-world dataset reveal that our model outperforms the baselines on several metrics.

User Profile Analysis Using an Online Social Network Integrated Quiz Game

User interest profiling is important for personalized web search, recommendation and retrieval systems. In order to develop a good personalized application one needs to have accurate representation of user profiles. Most of the personalized systems generate interest profiles from user declarations or inferred from cookies or visited web pages. But to achieve a certain result that satisfies the user needs, explicit definition of the user interests is needed. In this paper we propose to obtain interest profiles from a quiz game played by the user where at each play he/she is asked 10 questions from different categories with different difficulty levels. The developed quiz game is integrated to Facebook online social network. By doing so, we had the chance to extract each user’s both explicit Facebook interest profiles and implicit interest profiles from quiz game answers. These profiles are used to extract different features for each user. Both implicit interest profile and explicit interest profile features are evaluated for clustering and interest ranking tasks separately. The experimental results show that the implicit interest profile features have promising results on personalized systems.

ScholarLens: extracting competences from research publications for the automatic generation of semantic user profiles

Motivation Scientists increasingly rely on intelligent information systems to help them in their daily tasks, in particular for managing research objects, like publications or datasets. The relatively young research field of Semantic Publishing has been addressing the question how scientific applications can be improved through semantically rich representations of research objects, in order to facilitate their discovery and re-use. To complement the efforts in this area, we propose an automatic workflow to construct semantic user profiles of scholars, so that scholarly applications, like digital libraries or data repositories, can better understand their users’ interests, tasks, and competences, by incorporating these user profiles in their design. To make the user profiles sharable across applications, we propose to build them based on standard semantic web technologies, in particular the Resource Description Framework (RDF) for representing user profiles and Linked Open Data (LOD) sources for representing competence topics. To avoid the cold start problem, we suggest to automatically populate these profiles by analyzing the publications (co-)authored by users, which we hypothesize reflect their research competences. Results We developed a novel approach, ScholarLens, which can automatically generate semantic user profiles for authors of scholarly literature. For modeling the competences of scholarly users and groups, we surveyed a number of existing linked open data vocabularies. In accordance with the LOD best practices, we propose an RDF Schema (RDFS) based model for competence records that reuses existing vocabularies where appropriate. To automate the creation of semantic user profiles, we developed a complete, automated workflow that can generate semantic user profiles by analyzing full-text research articles through various natural language processing (NLP) techniques. In our method, we start by processing a set of research articles for a given user. Competences are derived by text mining the articles, including syntactic, semantic, and LOD entity linking steps. We then populate a knowledge base in RDF format with user profiles containing the extracted competences.We implemented our approach as an open source library and evaluated our system through two user studies, resulting in mean average precision (MAP) of up to 95%. As part of the evaluation, we also analyze the impact of semantic zoning of research articles on the accuracy of the resulting profiles. Finally, we demonstrate how these semantic user profiles can be applied in a number of use cases, including article ranking for personalized search and finding scientists competent in a topic —e.g., to find reviewers for a paper. Availability All software and datasets presented in this paper are available under open source licenses in the supplements and documented at http://www.semanticsoftware.info/semantic-user-profiling-peerj-2016-supplements. Additionally, development releases of ScholarLens are available on our GitHub page: https://github.com/SemanticSoftwareLab/ScholarLens.

An Ontology Like Model for gathering Personalized Web Information

In recent days the amount of Information Available on the internet is huge when compared to past few decades. How to gather useful information from the web has become a challenging issue for users. Current web information gathering systems trying to satisfy user requirements by looking at their information needs. For this purpose, user profiles are created for user background knowledge description. User profiles represent the concept models possessed by users when gathering web information. A concept model is implicitly possessed by users and is generated from their background knowledge. While this concept model cannot be proven in laboratories, many web ontologists have observed it in user behaviour. When users read through a document, they can easily determine whether or not it is of their interest or relevance to them, a judgment that arises from their implicit concept models. If a user’s concept model can be simulated, then a superior representation of user profiles can be built. To simulate user concept models, ontology’s—a knowledge description and formalization model—are utilized in personalized web information gathering. Such ontology’s are called ontological user profiles or personalized ontology’s. To represent user profiles, many researchers have attempted to discover user background knowledge through global or local analysis. Keywords: ontology, web information gathering, user profiles.

A Personalized Ontology Model For Web Mining Using Instance Matching

In rapid growth of internet, the amount of web information gathering becomes a challenging point for all users. Many existing retrieval systems have been developed to attempt to satisfy this problem. But still there is no complete solution to the problem. Ontology describes and formalizes standardized representation of knowledge as a set of concepts and the relationship between those concepts. In personalized web information gathering ontology is also used to represent the user profiles. For representing user profiles many existing models have been provided knowledge from either global or local knowledge base. The user background knowledge can be better discovered if we integrate global and local analysis. The proposed system emphasizes the specific semantic relation in one computational model. Ontology contains lots of instances. Automatically instance matching has become the fundamental issue. Instance matching approach is used to present based on discriminative property value. Ontology model in domain specific system with instance

A study of user profile representation for personalized cross-language information retrieval

Purpose– With an increase in the amount of multilingual content on the World Wide Web, users are often striving to access information provided in a language of which they are non-native speakers. The purpose of this paper is to present a comprehensive study of user profile representation techniques and investigate their use in personalized cross-language information retrieval (CLIR) systems through the means of personalized query expansion.Design/methodology/approach– The user profiles consist of weighted terms computed by using frequency-based methods such as tf-idf and BM25, as well as various latent semantic models trained on monolingual documents and cross-lingual comparable documents. This paper also proposes an automatic evaluation method for comparing various user profile generation techniques and query expansion methods.Findings– Experimental results suggest that latent semantic-weighted user profile representation techniques are superior to frequency-based methods, and are particularly suitable for users with a sufficient amount of historical data. The study also confirmed that user profiles represented by latent semantic models trained on a cross-lingual level gained better performance than the models trained on a monolingual level.Originality/value– Previous studies on personalized information retrieval systems have primarily investigated user profiles and personalization strategies on a monolingual level. The effect of utilizing such monolingual profiles for personalized CLIR remains unclear. The current study fills the gap by a comprehensive study of user profile representation for personalized CLIR and a novel personalized CLIR evaluation methodology to ensure repeatable and controlled experiments can be conducted.

ONTOLOGY TECHNIQUES FOR WEB DATA

This paper p r e s e n t s techniques for knowledge description and formalization, ontologies are used to represent user profiles in personalized web data. However, when representing user profiles, many models or techniques have utilized only knowledge from either a global knowledge base or a user local information. In this paper, a personalized ontology model is proposed for knowledge representation and reasoning over user profiles. This model learns ontological user profiles from both a world knowledge base and user local instance repositories. The ontology model is evaluated by comparing it against benchmark models in web information gathering. The results show that this ontology model is successful.

Customized Ontology model for Web Information Gathering using Clustering

The explosion of data leads to the problem on how information should be retrieved accurately and effectively. To address this issue, ontology's are widely used to represent user profiles in personalized web information gathering. As a model for knowledge description and formalization, ontology's are widely used to represent user profiles in personalized web information gathering. When representing user profiles, many models have utilized only knowledge from either a global knowledge base or local knowledge base. Ontology model learns user profiles from both a world knowledge base and local knowledge base. A non-content based customized ontology model is proposed for knowledge representation and reasoning over user profiles. This model generates user Local Instance Repository which includes non-content based descriptors referring to the subjects. This model has improvement over former models in hit/miss ratio, precision and recall parameters.

TOWARDS AN ONTOLOGY-BASED MODEL FOR USER PROFILE REPRESENTATION IN A CLOUD INFRASTRUCTURE

This paper presents an approach for the semantic representation of user profiles through an ontology conducted in the scope of the Cloud4all project. Employing the cloud computing paradigm, Cloud4allaims torealize a global public inclusive infrastructure that will reinforce accessibility of information and communication technologies(ICT). The proposed ontology aims to provide the required representation formalism to sufficiently express personal user needs and preferences based on domain knowledge and the association of interaction-related concepts in order to support automatic reasoning mechanisms for user profile management. To cite this document: Vassilis Koutkias, Evangelos Bekiaris, Nicos Maglaveras and Maria Gkemou, "Towards an ontology-based model for user profile representation in a cloud infrastructure", International Journal of Electronic Commerce Studies, Vol.4, No.2, pp. 349-354, 2013. Permanent link to this document: http://dx.doi.org/10.7903/ijecs.1042

Design and Development of an Ontology based Personal Web Search Engine

As a model for knowledge description and formalization, ontologies are widely used to represent user profiles in personalized web information gathering. However, when representing user profiles, many models have utilized only knowledge from either a global knowledge base or user local information. A personalized search engine which is a hybrid system has been proposed for personalized search and reasoning over user profiles. The hybrid system contains both the global knowledge base and the user local information. User profiles are created for every users to gather their interest and relevance. This system also learns user profiles based on which the user is provided with candidates in Ontology Learning Environment (OLE) tool. The search results are personalized and have topic specificity. The efficiency of a search application is defined by the accuracy by which the search results match the user interests. The efficiency improvement in our application can be defined by the reduction in the number of pages which a particular user who searches for a string. This search engine is evaluated by getting feedback from three kinds of users. The results show that this ontology model is successful.

A reference profile ontology for communities of practice

Communities of Practice (CoP) integrate people in a group in order to learn in a collaborative way. It is necessary to establish in these communities a formal and standardised representation of the knowledge and interests that emerge from CoP. With this scenario in mind, this paper presents a reference ontology for a user profile representation in a CoP Framework (CoPF). The main idea of this framework is to provide virtual CoP for collaborative learning by using semantic web technologies. This work proposes a foundational ontology for a general profile to be used as a guideline to build a computational CoPF, which is semantic web compliant. In this paper we summarise a first proposition of the CoPF ontology development focusing on the ontological user profile. We also present the methodological aspects of the ontological CoPF and also illustrate a case study applying the ontological user profile.

Special issue on fuzzy ontologies and fuzzy markup language applications

Latest research on formal methods for knowledge representation based on semantic web technologies witnessed how ontologies have become a fundamental and critical component for developing applications in different real world scenarios. Indeed, ontologies formally model application domains to enable reuse of knowledge and allow people and software agents to share a common understanding of the structure of information. The body of a knowledge modeled through an ontological approach is based on the conceptualization idea, i.e., an abstract and simplified view of the knowledge related to given application scenario. However, it is widely pointed out that classical ontology model is not sufficient to deal with imprecise and vague knowledge strongly characterizing some real world applications. Soft computing techniques can enhance ontological knowledge representation by providing methods for directly dealing with imprecision and vagueness. Indeed, fuzzy set theory may extend the conventional ontology idea with a collection of fuzzy or vague terms like ‘‘creamy’’, ‘‘hot’’, ‘‘large’’, for which a clear and precise definition is not possible. In this scenario, the fuzzy markup language (FML) represents an important result because it allows fuzzy scientists to express their ‘‘imprecise’’ ideas in abstract and interoperable way by improving their productivity and, at the same time, increasing the average quality of their works. The objective of this special issue is to highlight an ongoing research on fuzzy and FML approaches for knowledge semantic representation based on ontologies, as well as their applications on various domains. This volume contains seven papers that consider different aspects of research on fuzzy ontologies and FML. The first four papers describe the applications exploiting fuzzy theory and ontology. Updating Generalized Association Rules with Evolving Fuzzy Taxonomies by WenYang Lin, Ja-Hwung Su, and Ming-Cheng Tseng proposes an algorithm for mining generalized association rules with fuzzy taxonomic structures where the taxonomy may change as time passes; as shown by their empirical evaluations, the proposed algorithms yield high performances even in high degree of taxonomy evolution. Crowdsourcing techniques to create a fuzzy subset of SNOMED CT for semantic tagging of medical documents by David T. Parry and Tsung-Chun Tsai describes an approach to identifying subsets of medical knowledge contained in the SNOMED CT dictionary via a crowdsourcing technique. The research aims to assist clinicians in coding small freetext documents such as radiology reports. Fuzzy Ontologies-based User Profiles applied to enhance e-Learning Activities by Mateus Ferreira-Satler, Francisco P. Romero, Victor H. Menendez-Dominguez, Alfredo Zapata and Manuel E. Prieto shows how a fuzzy ontology can be used to represent user profiles into a recommender engine and enhances the user’s activities into e-Learning environments. Decision making with a fuzzy ontology by Christer Carlsson, Matteo Brunelli and Jozsef Mezei shows how soft computing techniques, e.g. aggregation functions and interval valued fuzzy numbers, will support effective and practical decision making on the basis of the fuzzy G. Acampora (&) Department of Computer Science, University of Salerno, Salerno, Italy e-mail: gacampora@unisa.it

Fuzzy ontologies-based user profiles applied to enhance e-learning activities

Nowadays, the impact of technological developments on improving human activities is becoming more evident. In e-learning, this situation is no different. There are common to use systems that assist the daily activities of students and teachers. Typically, e-learning recommender systems are focused on students; however, teachers can also benefit from these type of tools. A recommender system can propose actions and resources that facilitate teaching activities like structuring learning strategies. In any case, a complete user’s representation is required. This paper shows how a fuzzy ontology can be used to represent user profiles into a recommender engine and enhances the user’s activities into e-learning environments. A fuzzy ontology is an extension of domain ontologies for solving the problems of uncertainty in sharing and reusing knowledge on the Semantic Web. The user profile is built from learning objects published by the user himself into a learning object repository. The initial experiment confirms that the automatically obtained fuzzy ontology is a good representation of the user’s preferences. The experiment results also indicate that the presented approach is useful and warrants further research in recommending and retrieval information.

Engaging Families in Lifestyle Changes Through Social Networking

Previous research has shown that providing family engagement and social support play important roles in weight management success, helping to achieve long-term lifestyle changes. Traditionally, the support provided by online health communities is primarily targeted at individuals and does not involve their families. SOFA (SOcial FAmilies), a novel approach for engaging, motivating, and persuading families to adopt a healthy lifestyle, is proposed. SOFA is an online social network for families coupled with a repository of health-related educational content. This article reports the results of a live user study aimed at investigating how user profile representation and system-assigned tasks influence users engagement with the system and change their attitude toward a healthy lifestyle. The results show that representing family members as individuals increases the number of active members per family as well as their retention, contribution to, and engagement with the network. The results also show that family-based social networks positively change the attitude of family members toward a healthy lifestyle.

A Personalized Ontology Model for Web Information Gathering

As a model for knowledge description and formalization, ontologies are widely used to represent user profiles in personalized web information gathering. However, when representing user profiles, many models have utilized only knowledge from either a global knowledge base or a user local information. In this paper, a personalized ontology model is proposed for knowledge representation and reasoning over user profiles. This model learns ontological user profiles from both a world knowledge base and user local instance repositories. The ontology model is evaluated by comparing it against benchmark models in web information gathering. The results show that this ontology model is successful.

Interest based selection of user generated content for rich communication services

The last few years, we have witnessed an exponential growth in available content, much of which is user generated (e.g. pictures, videos, blogs, reviews, etc.). The downside of this overwhelming amount of content is that it becomes increasingly difficult for users to identify the content they really need, resulting into considerable research efforts concerning personalized search and content retrieval. On the other hand, this enormous amount of content raises new possibilities: existing services can be enriched using this content, provided that the content items used match the user's personal interests. Ideally, these interests should be obtained in an automatic, transparent way for an optimal user experience. In this paper two models representing user profiles are presented, both based on keywords and with the goal to enrich real-time communication services. The first model consists of a light-weight keyword tree which is very fast, while the second approach is based on a keyword ontology containing extra temporal relationships to capture more details of the user's behavior, however exhibiting lower performance. The profile models are supplemented with a set of algorithms, allowing to learn user interests and retrieving content from personal content repositories. In order to evaluate the performance, an enhanced instant messaging communication service was designed. Through simulations the two models are assessed in terms of real-time behavior and extensibility. User evaluations allow to estimate the added value of the approach taken. The experiments conducted indicate that the algorithms succeed in retrieving content matching the user's interests and both models exhibit a linear scaling behavior. The algorithms perform clearly better in finding content matching several user interests when benefiting from the extra temporal information in the ontology based model.