Collaborative Tagging

The importance of proteomics science is rapidly growing across all areas of biomedical research for the measurement of cellular function. However, the most advanced proteomics technologies, knowledge and datasets have been widely unavailable to the biomedical research communities. These limits make it harder to support the disease and drug related research progress. Moreover, developing common data standards and the validation of deposition is difficult, slow, and an arduous task for any single group. Therefore, proteomics domain necessitates collaboration with diverse researchers for meaningful research progress. The lack of effective collaboration and sharing facilities among researchers with necessary biological expertise is another hurdle for properly designing studies, or developing data standards. The social network centric collaborative research framework could bridge that gap by bringing together expertise in different areas of proteomics, and providing a shared workspace fo...

Self-organizing structure and availability of almost unlimited resource capacities make the peer-to-peer architecture very attractive for large-scale sharing of annotated data in Web 2.0 scenarios. This paper addresses the problem of information aggregation and utilization in a decentralized tagging environment. We introduce the vector space model for characterization of users, resources, and tags. We analyze the problem of constructing a reliable approximation for feature vectors in a fully decentralized setting and introduce possible solutions. The results of large-scale systematic evaluation with realistic data sets witness the viability of our approach.

Self-organizing structure and availability of almost unlimited resource capacities make the peer-to-peer architecture very attractive for large-scale sharing of annotated data in Web 2.0 scenarios. This paper addresses the problem of information aggregation and utilization in a decentralized tagging environment. We introduce the vector space model for characterization of users, resources, and tags. We analyze the problem of constructing a reliable approximation for feature vectors in a fully decentralized setting and introduce possible solutions. The results of large-scale systematic evaluation with realistic data sets witness the viability of our approach.

Everybody experiences every day the need to manage a huge amount of heterogeneous shared resources, causing information overload and fragmentation problems. Collaborative annotation tools are the most common way to address these issues, but collaboratively tagging resources is usually perceived as a boring and time consuming activity and a possible source of conflicts. To face this challenge, collaborative systems should effectively support users in the resource annotation activity and in the definition of a shared view. The main contribution of this paper is the presentation and the evaluation of a set of mechanisms (personal annotations over shared resources and tag suggestions) that provide users with the mentioned support. The goal of the evaluation was to (1) assess the improvement with respect to the situation without support; (2) evaluate the satisfaction of the users, with respect to both the final choice of annotations and possible conflicts; (3) evaluate the usefulness of ...

Abstract—Suppose you registered to a large scientific congress and you got from the Web site the conference program containing a long list of papers which will be presented. Which presentations do you choose to attend? Usually either you try to guess the most interesting talks from their titles and authors or you are forced to have a quick look at the conference proceedings. A recommender system able to learn your research interests from the latest papers you wrote or read, and use them to provide suggestions, might be of valuable help ...

On the internet, web surfers, in the search of information, always strive for recommendations. The solutions for generating recommendations become more difficult because of exponential increase in information domain day by day. In this paper, we have calculated entropy based similarity between users to achieve solution for scalability problem. Using this concept, we have implemented an online user based collaborative web recommender system. In this model based collaborative system, the user session is divided into two levels. Entropy is calculated at both the levels. It is shown that from the set of valuable recommenders obtained at level I; only those recommenders having lower entropy at level II than entropy at level I, served as trustworthy recommenders. Finally, top N recommendations are generated from such trustworthy recommenders for an online user.

In our daily lives, organizing resources like books or webpages into a set of categories to ease future access is a common task. The usual largeness of these collections requires a vast endeavour and an outrageous expense to organize manually. As an approach to effectively produce an automated classification of resources, consider the immense amounts of annotations provided by users on social tagging systems in the form of bookmarks. This project deal with the utilization of user provided tags to perform a social classification of resources. Those resources are accompanied by categorization data from sound expert-driven taxonomies. We analyse different representations using tags and compare to other data sources by using different settings of SVM classifiers. Finally, we explore combinations of different data sources with tags using classifier committees to best classify the resources.

With the emergence and growth of web2.0 paradigm, the theme of e-learning2.0 started to raise. E-learning2.0 is an ideal platform which supports learner centric approach. From the view of learners, the way people learn has changed from passive to active. This paper presents a novel approach to the design of e-learning system using web2.0 tools. The main focus of our approach is to create metadata using folksonomies and Dublin Core metadata standard for e-learning objects. Meanwhile, a learning repository is designed for storing learning objects and metadata. A query interface has been developed to retrieve the search item. To test the usefulness and ease of use of our prototype, we used the Technology Acceptance Model (TAM) to evaluate the system. Results are promising. General Terms Web 2.0, Metadata, Query Interface, Knowledge Management, Statistical Packages for Social Sciences(SPSS).

Grouping resources into set of classes allows easy access to the resources we use in our day-to-day lives. This classification makes the search faster and easier. The process of classifying the resources manually becomes expensive. This cost effectiveness switch to automated classification of resources which depends on the content of the data. This paper deals with the semantic analysis of tags. Collaborative tagging system allows any user to annotate the web resources. The user annotations can be useful to discover the aboutness of resources and also helps to ascertain classification. The social tagging system focuses on using support vector machine (SVM) as a state-of-the-art classification algorithm. We have two large scale social tagging data sets to interpret the characteristics of social classification. This System supports user defined annotations which immensely renovate folksonomies.

If you look at the theses that come out of our group. almost all of them list our advisor. Pattie Maes. first. There's a reason for this: she's absolutely instrumental in making us all successful. She knows just the right questions to ask to push us in the right direction, she knows how to motivate us when demos swamp our schedules (keep those lunches!). and she gives us all the room we need to be individually creative and to work in our own style. I couldn't ask for anything more, and I can truly say that my life has changed 100% since the day I walked into her office and said "I think agents are cool." Likewise the other members of our group:

Nowadays the Web represents a growing collection of an enormous amount of contents where the need for better ways to find and organize the available data is becoming a fundamental issue, in order to deal with information overload. Keyword based Web searches are actually the preferred mean to seek for contents related to a specific topic. Search engines and collaborative tagging systems make possible the search for information thanks to the association of descriptive keywords to Web resources. All of them show problems of inconsistency and consequent reduction of recall and precision of searches, due to polysemy, synonymy and in general all the different lexical forms that can be used to refer to a particular meaning. A possible way to face or at least reduce these problems is represented by the introduction of semantics to characterize the contents of Web resources: each resource is described by one or more concepts instead of simple and often ambiguous keywords. To support these task the availability of a global semantic resource of reference is fundamental. On the basis of our past experience with the semantic tagging of Web resources and the SemKey Project, we are developing Tagpedia, a general-domain "encyclopedia" of tags, semantically structured for generating semantic descriptions of contents over the Web, created by mining Wikipedia. In this paper, starting from an analysis of the weak points of non-semantic keyword based Web searches, we introduce our idea of semantic characterization of Web resources describing the structure and organization of Tagpedia. We introduce our first realization of Tagpedia, suggesting all the possible improvements that can be carried out in order to exploit its full potential.

Collaborative tagging has been quickly gaining ground because of its ability to recruit the activity of web users into effectively organizing and sharing vast amounts of information. Here we collect data from a popular system and investigate the statistical properties of tag cooccurrence. We introduce a stochastic model of user behavior embodying two main aspects of collaborative tagging: (i) a frequency-bias mechanism related to the idea that users are exposed to each other's tagging activity; (ii) a notion of memory, or aging of resources, in the form of a heavy-tailed access to the past state of the system. Remarkably, our simple modeling is able to account quantitatively for the observed experimental features with a surprisingly high accuracy. This points in the direction of a universal behavior of users who, despite the complexity of their own cognitive processes and the uncoordinated and selfish nature of their tagging activity, appear to follow simple activity patterns.

Recommender systems help users to cope with information overload and have become one of the most powerful and popular tools in electronic commerce. In order to provide better recommendations and to be able to use recommender systems in arguably more complex types of applications, most of the typical used approaches need significant extensions. On the video recommendation domain, one of these extensions is based in Segments of Interest (SOI), i.e., video segments that the user liked more or is interested. For this work, our intention is to stress and discuss interaction design issues about SOI based video recommender systems and discuss the relation between SOI and collective intelligence. We present two approaches to marking SOI on a Web social environment and discuss their advantages and disadvantages, and we show why SOI can be seen as a source of collective intelligence and that information and knowledge emerged from a community that had marked SOIs can be used on consensus decision-making and to bring improvements to society.

Recommender systems help users to cope with information overload and have become one of the most powerful and popular tools in electronic commerce. In order to provide better recommendations and to be able to use recommender systems in arguably more complex types of applications, most of the typical used approaches need significant extensions. On the video recommendation domain, one of these extensions is based in Segments of Interest (SOI), i.e., video segments that the user liked more or is interested. For this work, our intention is to stress and discuss interaction design issues about SOI based video recommender systems and discuss the relation between SOI and collective intelligence. We present two approaches to marking SOI on a Web social environment and discuss their advantages and disadvantages, and we show why SOI can be seen as a source of collective intelligence and that information and knowledge emerged from a community that had marked SOIs can be used on consensus decision-making and to bring improvements to society.

In the era of internet access, recommender systems try to alleviate the difficulty consumers face while trying to find items (e.g. services, products, or information) that better match their needs. To do so, a recommender system selects and proposes (possibly unknown) items that may be of interest to some candidate consumer, by predicting her/his preference for this item. Given the diversity of needs between consumers and the enormous variety of items to be recommended, a large set of approaches have been proposed by the research community. This paper provides a review of the approaches proposed in the entire research area of content-based recommender systems, and not only in one part of it. To facilitate understanding, we provide a categorization of each approach based on the tools and techniques employed, which results to the main contribution of this paper, a content-based recommender systems taxonomy. This way, the reader acquires a quick and complete understanding of this research area. Finally, we provide a comparison of content-based recommender systems according to their ability to efficiently handle well-known drawbacks.

Recommendation plays a key role in e-commerce and in the entertainment industry. We propose to consider successive recommendations to users under the form of graphs of recommendations. We give models for this representation. Motivated by the growing interest for algorithmic transparency, we then propose a first application for those graphs, that is the potential detection of introduced recommendation bias by the service provider. This application relies on the analysis of the topology of the extracted graph for a given user; we propose a notion of recommendation coherence with regards to the topological proximity of recommended items (under the measure of items' k-closest neighbors, reminding the "small-world" model by Watts & Stroggatz). We finally illustrate this approach on a model and on Youtube crawls, targeting the prediction of "Recommended for you" links (i.e., biased or not by Youtube).

La recommandation joue un role central dans le e-commerce et dans l'industrie du divertissement. L'interet croissant pour la transparence algorithmique nous motive dans cet article a observer les resultats de recommandations sous la forme d'un graphe capturant les navigations proposees dans l'espace des items. Nous argumentons qu'une telle approche en "boite noire" est utile dans le cas d'une exploration limitee a un utilisateur: nous illustrons une topologie tiree de recommandations a un utilisateur de Youtube, fournissons ses caracteristiques cles, et montrons qu'elle renseigne sur la connaissance de cet utilisateur par le systeme. Nous montrons ensuite que l'analyse de cette topologie d'aborder la question du \text{biais} potentiel dans ces recommandations. Nous postulons que les systemes de recommandation produisent naturellement des topologies coherentes, et qu'une manipulation de ces resultats par l'ajout de liens biaises a...

Combining social network information with collaborative filtering recommendation algorithms has helped to alleviate some drawbacks of collaborative filtering, for example, the cold start problem, and has increased the accuracy of recommendations. However, the user coverage of recommendation for social-based recommendation is low as there is often insufficient data about explicit social relationships among users. In this paper, we fuse recommendation that uses explicit social relations (friends and co-authors) with recommendations that use implicit social relations aiming to increase the user coverage with minimum recommendation accuracy loss. We found that fusing recommendations from friends with recommendations using implicit social networks increases both accuracy and user recommendation coverage while fusing recommendation from co-authors increase the coverage.

This document describes the sample implementation of a very popular classification method in the modern internet web applications-folksonomy. This method forces users to assign a particular keywords to the content that they are uploading. Basing on the assigned keywords it is possible to find a similar content. In this paper, there is described the method of finding similar content basing on the ART-1 neural network. Such solution allows to perform a background clustering of a content and speed up the process of retrieving the related data. In case of a heavy exploitation of an internet application, this might be a big advantage

In the era of Internet where millions of people browsing over millions of websites; searching for web databases such as Product database, Locomotive database etc. have become a routine task. Ranking and returning the most relevant result of a query based on the type of user is important in this aspect. Previous approaches have used values of database frequencies, user profiles and queries. Thus the ranking was done in a userand /or queryindependent manner. A new approach known as User and Query Dependent Ranking for giving ranking to query results can be useful in this context. This ranking framework is based on two fundamental aspects to the problem of ranking query results. They are query similarity and user similarity. These similarities are exploited to make efficient ranking of query results. Keywords—Automated ranking, Recommendation Systems, User similarity, Query similarity, Ranking query results, Data Mining.

The aim of the present paper is to analyze the user's behavior in Web 2.0 through comparing statistical data from a Web 1.0 site and an online community from Web 2.0. In order to emphasize the difference between the two concepts, we have taken into consideration the following: new vs. returning visitors, visitor loyalty, length as well as the depth of the visit to the site. Analyzing the data, one can observe that the visitor loyalty, their lengthy visits to the site and the pages they view are much higher for the site built on the principles of Web 2.0, compared to the classical sites. Likewise, we developed and implemented a collaborative tagging system that allows every registered user to publish, save and label the content with the help of tags. Therefore, this can help in building a model that not only offers customized content but also adapts the site to user needs by providing a recommendation system and aggregate collective intelligence.

The creation of learning resource metadata by instructors is a time consuming and error prone process. This paper outlines a broad research agenda to mitigate these issues.. The first part of this approach is to collect prescriptive metadata from various actors involved using a light weight collaborative tagging approach. This is then augmented with content analysis done directly on learning objects to create concept and summarization metadata. Finally, interaction metadata observed from the environment in which the learning objects ...

Collaborative tagging systems allow users to describe and organize items using labels in a free-shared vocabulary (tags), improving their browsing experience in large collections of items. At present, the most accurate collaborative filtering techniques build user profiles in latent factor spaces that are not interpretable by users. In this paper, we propose a general method to build linear-interpretable user profiles that can be used for user interaction in a recommender system, using the well-known simple additive weighting model (SAW) for multi-attribute decision making. In experiments, two kinds of user profiles where tested: one from free contributed tags and other from keywords automatically extracted from textual item descriptions. We compare them for their ability to predict ratings and their potential for user interaction. As a test bed, we used a subset of the database of the University of Minnesota's movie review system-Movielens, the social tags proposed by Vig et al. (2012) in their work "The Tag Genome", and movie synopses extracted from the Netflix's API. We found that, in "warm" scenarios, the proposed tag and keyword-based user profiles produce equal or better recommendations that those based on latent-factors obtained using matrix factorization. Particularly, the keyword-based approach obtained 5.63% of improvement. In cold-start conditions-movies without rating information, both approaches perform close to average. Moreover, a user profile visualization is proposed arising an accuracy vs. interpretability tradeoff between tag and keywordbased profiles. While keyword-based profiles produce more accurate recommendations, tag-based profiles seems to be more readable, meaningful and convenient for creating profile-based user interfaces.

In this paper we present the first participation of the NLP&IR group at UNED in the Tagging Task (Professional Version): prediction of semantic theme. This categorization task was carried out by an information retrieval approach, together with language models and clustering using only metadata associated with the videos. The results show that language models are useful for enriching the representation of information associated with videos.

Recommender Systems (RS) may behave differently depending on the characteristics of the input data, encouraging the development of Hybrid Filtering (HF). There are few works in the literature that explicitly characterize aspects of the input data and how they can lead to better HF solutions. Such work is limited to the scope of combination of Collaborative Filtering (CF) solutions, using only rating prediction accuracy as an evaluation criterion. However, it is known that RS also need to consider other evaluation criteria, such as novelty and diversity, and that HF involving more than one approach can lead to more effective solutions. In this work, we begin to explore this under-investigated area, by evaluating different HF strategies involving CF and Content-Based (CB) approaches, using a variety of data characteristics as extra input data, as well as different evaluation criteria. We found that the use of data characteristics in HF proved to be useful when considering different evaluation criteria. This occurs in spite of the fact that the experimented methods aim at minimizing only the rating prediction errors, without considering other criteria.

The past few years have seen the rapid rise of all things "social" on the web from the growth of online social networks like Facebook, to user-contributed content sites like Flickr and YouTube, to social bookmarking services like Delicious, among many others. Whereas traditional approaches to organizing and accessing the web's massive amount of information have focused on content-based and link-based approaches, these social systems offer rich opportunities for user-based and community-based exploration and analysis of the web by building on the unprecedented access to the interests and perspectives of millions of users. We focus here on the challenge of modeling and mining social bookmarking systems, in which resources are enriched by large-scale socially generated metadata ("tags") and contextualized by the user communities that are associated with the resources. Our hypothesis is that an underlying social collective intelligence is embedded in the uncoordinated actions of users on social bookmarking services, and that this social collective intelligence can be leveraged for enhanced web-based information discovery and knowledge sharing. Concretely, we posit the existence of underlying implicit communities in these social bookmarking systems that drive the social bookmarking process which can provide a foundation for community-based organization of web resources. To that end, we make three contributions: • First, we propose a pair of novel probabilistic generative models for describing IV Communities, their categories, and the most likely tags per category (in order of ϕ z,t

In this paper, we present an automatic tag suggester, Tess. Our system makes recommendations based only on the textual contents of the resource and is independent of existing tags, thus allowing the emergence of novel tags. Preliminary evaluation experiments show that the system is not only able to suggest many useful tags, but also to discover new and relevant tags, not suggested by any of the users.

The current generation of location-based services (LBSs) does not provide users with personalized recommendations, but only suggests nearby points of interest (POIs) based on their distance from the user current location. To overcome such a limitation, we have realized a social recommender system able to identify user preferences and information needs, thus suggesting personalized recommendations related to possible POIs in the surroundings. The proposed approach allows users to leverage and assign freely chosen keywords (tags) to resources through collaborative tagging services (folksonomies). Our LBS employs a user-based tag model that derives correspondences between personal tag vocabularies (personomies) and folksonomies. Experimental tests performed on 15 real users enabled us to assess the benefits in terms of performance that our approach is able to provide.

The practice and method of collaboratively creating and managing tags to annotate and categorize content has resulted in the creation of folksonomy. Folksonomies provide new opportunities and challenges in the field of recommender systems. Despite the considerable amount of researches done in the context of recommender systems, the specific problem of integrating tags into standard recommender system algorithms is less explored than the problem of recommending tags. Collaborative filtering is one of the popular approaches for providing recommendation. However, despite the popularity of collaborative filtering, to some extent, it could not recognize the preferences of users in cold-start scenarios, where insufficient preferences are associated to certain users or items, which leads to degraded recommendation quality. This study presents a collaborative filtering approach based on the expansion of users' tags. In this case, semantics between tags can be unveiled which subsequently resulted in the identification of semantically similar users. Experiment on real-life dataset shows that our approach outperforms the state-of-the-art tag-aware collaborative filtering approaches in terms of recommendation quality particularly in the cold-start situation.

Algorithmic recommendations shape music consumption at scale, and understanding the impact of various algorithmic models on how content is consumed is a central question for music streaming platforms. The ability to shift consumption towards less popular content and towards content different from user's typical historic tastes not only affords the platform ways of handling issues such as filter bubbles and popularity bias, but also contributes to maintaining a healthy and sustainable consumption patterns necessary for overall platform success. In this work, we view diversity as an enabler for shifting consumption and consider two notions of music diversity, based on taste similarity and popularity, and investigate how four different recommendation approaches optimized for user satisfaction, fare on diversity metrics. To investigate how the ranker complexity influences diversity, we use two well-known rankers and propose two new models of increased complexity: a feedback aware neural ranker and a reinforcement learning (RL) based ranker. We demonstrate that our models lead to gains in satisfaction, but at the cost of diversity. Such trade-off between model complexity and diversity necessitates the need for explicitly encoding diversity in the modeling process, for which we consider four types of approaches: interleaving based, submodularity based, interpolation, and RL reward modeling based. We find that our reward modeling based RL approach achieves the best trade-off between optimizing the satisfaction metric and surfacing diverse content, thereby enabling consumption shifting at scale. Our findings have implications for the design and deployment of practical approaches for music diversification, which we discuss at length.

Grouping resources into set of classes allows easy access to the resources we use in our day-to-day lives. This classification makes the search faster and easier. The process of classifying the resources manually becomes expensive. This cost effectiveness switch to automated classification of resources which depends on the content of the data. This paper deals with the semantic analysis of tags. Collaborative tagging system allows any user to annotate the web resources. The user annotations can be useful to discover the aboutness of resources and also helps to ascertain classification. The social tagging system focuses on using support vector machine (SVM) as a state-of-the-art classification algorithm. We have two large scale social tagging data sets to interpret the characteristics of social classification. This System supports user defined annotations which immensely renovate folksonomies.

Semiotics is a field where research on Computer Science methodologies has focused, mainly concerning Syntax and Semantics. These methodologies, however, are lacking of some flexibility for the continuously evolving web community, in which the knowledge is classified with tags rather than with ontologies. In this paper we propose a multi-agent system for the recommendation of tagged pictures obtained from mainstream Web applications. The agents in this system execute a hybrid reasoning based on WordNet ...

Facetag is a working prototype of a semantic collaborative tagging tool conceived for bookmarking information architecture resources. It aims to show how the widespread homogeneous and flat keywords' space of tags can be effectively mixed with a richer faceted classification scheme to improve the "information scent" and "berrypicking" capabilities of the system. The additional semantic structure is aggregated both implicitly observing user behaviour and explicitly introducing a compelling user experience to facilitate the creation of relationships between tags directly by end-users. Facetag current implementation is written in PHP / SQL and includes an open API which allows querying and integration from other applications.

The objective of our group was to exploit state-of-the-art Information Retrieval methods for finding associations and dependencies between tags, capturing and representing differences in tagging behavior and vocabulary of various folksonomies, with the overall aim to better understand the semantics of tags and the tagging process. Therefore we analyze the semantic content of tags in the Flickr and Delicious folksonomies. We find that: tag context similarity leads to meaningful results in Flickr, despite its narrow folksonomy character; the comparison of tags across Flickr and Delicious shows little semantic overlap, being tags in Flickr associated more to visual aspects rather than technological as it seems to be in Delicious; there are regions in the tag-tag space, provided with the cosine similarity metric, that are characterized by high density; the order of tags inside a post has a semantic relevance.

We present the first personalized peer-to-peer top-k search protocol for a collaborative tagging system. Each peer maintains relevant personalized information about its tagging behavior as well as that of its social neighbors, and uses those to locally process its queries. Extensive experiments based on a real-world dataset crawled from del.icio.us shows that very little storage at each peer suffices to get almost the same results as a hypothetical centralized solution with infinite storage.

Social networks have become an important venue to express the feelings of their users on a large scale. People are intuitive to use social networks to express their feelings, discuss ideas, and invite folks to take suggestions. Every social media user has a circle of friends. The suggestions of these friends are considered important contributions. Users pay more attention to suggestions provided by their friends or close friends. However, as the content on the Internet increases day by day, user satisfaction decreases at the same rate due to unsatisfactory search results. In this regard, different recommender systems have been developed that recommend friends to add topics and many other things according to the seeker's interests. The existing system provides a solution for personalized retrieval, but its accuracy is still a problem. In this work, we have proposed a personalized query recommendation system that utilizes Friendship Strength (FS) to recommend queries. For FS calculation, we have used the Facebook dataset comprising of more than 22k records taken from four different accounts. We have developed a ranking algorithm that provides ranking based on FS. Compared with existing systems, the proposed system can provide encouraging results. Key research groups and organizations can use this system for personalized information retrieval.

Recent years have seen a significant growth in social tagging systems.[delete period & insert comma], Social tagging systems which allow users to use their own generated tags to organize, categorize, describe and search digital content on social media. The growing popularity of tagging systems is leading to an increasing need for automatic generation of recommended items for users. Much previous research focuses on incorporating recommender systems techniques in social tagging systems to support the suggestion of suitable tags for annotating related items. Collaborative filtering is one of these recommender system such techniques technique. The most critical task in collaborative filtering is finding related users with similar preferences, [insert comma] or i.e., [insert comma] "liked-minded" users. Despite the popularity of collaborative filtering, it still suffers from some certain limitations for example in relation to "cold-start" users, for example, [insert comma] where it is often the case that often there are insufficient preferences to make recommendations. In addition Moreover, there is the data-sparsity [notice inserted hyphen]problem, where there is limited user feedback data to identify similarities in users' interests because there is no intersection between users' transactional data, a situation which also leads to degraded recommendation quality.  Therefore, [delete space between previous letter and comma] inthis paper report we present a new collaborative filtering approach based on users' semantic annotations (tags), which calculates the similarity between users by discovering the semantic spaces in their posted tags. We believe that this approach better reflects the semantic similarity between users according to their tagging perspectives and consequently improves recommendations through the identification of semantically related items for each user. Our experiment on a real-life dataset shows demonstrates that our approach outperforms the traditional user-based collaborative filtering approach in terms of recommendation improving the quality improvement of recommendations. 

The synonym issue is an inherent barrier in human-computer communication, and it is more challenging in a Web 2.0 application, especially in social tagging applications. In an effort to resolve the issue, the goal of this study is to test the feasibility of a Web 2.0 application as a potential source for synonyms. This study investigates a way of identifying similar tags from a popular collaborative tagging application, Delicious. Specifically, we propose an algorithm (FolkSim) for measuring the similarity of social tags from Delicious. We compared FolkSim to a cosine-based similarity method and observed that the top-ranked tags on the similar list generated by FolkSim tend to be among the best possible similar tags in given choices. Also, the lists appear to be relatively better than the ones created by CosSim. We also observed that tag folksonomy and similar list resemble each other to a certain degree so that it possibly serves as an alternative outcome, especially in case the FolkSim-based list is unavailable or infeasible.

Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs and other content. In this paper we analyze the structure of collaborative tagging systems as well as their dynamical aspects. Specifically, we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given url. We also present a dynamical model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.

Collaborative tagging describes the process by which many users add metadata in the form of keywords to shared content. Recently, collaborative tagging has grown in popularity on the web, on sites that allow users to tag bookmarks, photographs and other content. In this paper we analyze the structure of collaborative tagging systems as well as their dynamic aspects. Specifically, we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given URL. We also present a dynamic model of collaborative tagging that predicts these stable patterns and relates them to imitation and shared knowledge.

We analyze the behavior of recommender systems relative to the popularity of the items to recommend. Our findings show that most popular ranking-based recommenders are biased towards popular items, thus affecting the quality of recommendation. Based on these observations, we propose a new deep learning architecture with an improved learning strategy that significantly improves the performance of such recommenders on low-popular items. The proposed technique is based on two main aspects: resampling of negatives and ensembling of multiple instances of the algorithm. Experimental results on traditional benchmark datasets show that the proposed approach substantially improves the recommendation ability by balancing accurate contributions almost independently from the popularity of the items to recommend.

Tags and keywords, freely chosen by users for annotating resources, offer a new way for organizing and retrieving web resources that closely reflect the users' interests and preferences, as well as automatically generate folksonomies. Social tagging systems have gained increasing popularity as a method for annotating and categorizing a wide range of different web resources. They also attract researchers in social sciences because they offer a huge quantity of user-generated annotations that reveal the interests of millions of people. To date, the study using digital trace data methods continues to lack a theoretical framework, particularly in social science research. This paper presents a methodology to use big data from Web 2.0 in social research. At the same time, it applies a method to extract data from a particular social bookmarking site (Delicious) and shows the sort of results that this type of analysis can offer to social scientists. The illustration is made around the topic of globalization of agriculture. Using data crawled from a large social tagging system can have an important impact in the discovering of latent patterns, which is needed to provide effective recommendations to different actors. In this paper, a sample of 851 users, 526 URLs and 1,700 tags from the Delicious classification system on the subject of globalization were retrieved and analyzed. Through the analysis, main users and websites around globalization issues in Delicious emerged, along with discovering the most important tags that were applied by users to describe the globalization of agriculture. The implications of these methodology and findings for further research are discussed.

Recommender Systems (RSs) are among the solutions in addressing the information overload problems. One of the RS main problem is cold start users where RSs do not have enough information to identify the user's preferences and thus unable to recommend relevant items. One of the approaches to overcome such problem is through social relationship which can be extracted from social networks. Existing studies used friendship relation to find nearest neighbors combined with implicit data such as tweet content, posts, like or tags to identify user's preference. This study proposed friendship strength through user's interaction and item rating values to identify users' preferences. User-based collaborative filtering methods are used in developing the system. Two datasets are synthetically obtained from MovieLens database for user's rating information. Meanwhile Twitter users' interactions data, was retrieved from Higgs Boson topic available from the Standford University. There are four phases of development namely user profile phase, friendship strength phase, user's preference phase and items recommendation phase. The findings of the study show that there is an improvement in the proposed method compared to the baseline based on the recall (R), precision (P) and F score measures.

When a new customer enters the spectrum of the E-Commerce system, the informative records and dataset, such as about the new user, purchasing history and other browsing data become insufficient, resulting in the emergence of one serious issue such as a Cold start problem (CSP). Furthermore, when the interaction among the product items becomes limited, a new problem such as Sparsity arises to handle such problems in E-Commerce system, we have designed an extensive and hybridized methodological approach known as Cold start and sparsity aware hybridized recommendation system (CSSHRS), to reduce the Sparsity of dataset as well as to overcome the cold start problem in the recommendation framework. The proposed CSSHRS technique has been predicted by using the dataset of Last. FM, and Book-Crossing resulted in Mean absolute percentage error (MAPE) of 37%, recalls 0.07, precision 0.18, Normalized Discounted Cumulative Gain (NDCD) 0.61, and F-measure 0.1. This article proves the proposed CSSHRS technique as an effective and efficient hybrid of RS against the issue of data sparsity as well as CSP. INDEX TERMS Data clustering, cold start problem, recommender system, sparsity.

Social tagging system are web-based sites that store user’s keywords called tags, continue to receive significant consideration in academic environment it became an interesting research topic, give good support for users to tag resources, communicate with friends as well as friend recommendation, due to increasingly acceptance of Web2.0. There is a constant growth in the number of users using social tagging. Friend recommendation is one of the most important aspects for overcoming information overloading problem and helps users to make choice. In this work we proposed improving friend recommendation using, to address the difficulty of tag ambiguities. The technique is consisted of the following stages: Apply FP-Growth algorithm to discovery the frequent events sets among the users, construct the combine trust graph, and then apply ant colony optimization Algorithm to joint trust graph to compute the optimal friend recommended through repetition. The results of our experiments on a De...