Quality Of Tags Research Articles

Complementary radial tagging for improved myocardial tagging contrast.

To develop and evaluate complementary radial tagging (CRT) for improved myocardial tagging contrast. We sought to develop and evaluate CRT, which aims to preserve the radial tag contrast throughout the cardiac cycle. Similar to complementary spatial modulation of magnetization, CRT acquires two sets of images with a phase shift in the tag pattern. The combination of a ramped imaging flip angle and image subtraction enhances tag contrast throughout the cardiac cycle. The proposed CRT technique uses a small table shift away from the isocenter to improve the uniformity of the radial tag pattern. We provide a mathematical solution for the optimal table shift and validate the solution in using a retrospective analysis of images from 500 patients in the Cardiac Atlas Project database. CRT simulations, phantom experiments, and in vivo images all demonstrate the improved tag contrast of CRT compared to RT. The retrospective evaluation demonstrated that acceptable CRT images could be acquired in over 98% of the clinical exams. The CRT technique improves radial tag contrast throughout the cardiac cycle and should produce high quality tag patterns in nearly all patients.

Image Tag Recommendation Algorithm Using Tensor Factorization

This paper aims to provide high quality tags for digital images according to users’ interest. As there are three main elements in image tag recommendation problem, tensor factorization technology is utilized in this work. In this paper, the parameters of the tensor factorization model are represented as latent variables, and the key functions of the tensor factorization model can be implemented by integrating three matrices(person matrix, image matrix, and tag matrix) into one tensor. The key problem of image tag recommendation is to obtain the top ranked tags which are suitable not only to image visual contents but also to users’ interest. Afterwards, the top ranked tags are obtained by a predictor utilizing the proposed tensor factorization model. Therefore, the image tag recommendation problem can be converted to calculate the ranking scores by maximizing the ranking statistic AUC. Finally, performance evaluation is conducted on the NUS-WIDE dataset using MRR, S@k, P@k, and NDCG metric. Experimental results show that the proposed image tag recommendation algorithm performs better than other methods

Semantic tagging and linking of software engineering social content

Social online communities and platforms play a significant role in the activities of software developers either as an integral part of the main activities or through complimentary knowledge and information sharing. As such techniques become more prevalent resulting in a wealth of shared information, the need to effectively organize and sift through the information becomes more important. Top-down approaches such as formal hierarchical directories have shown to lack scalability to be applicable to these circumstanes. Light-weight bottom-up techniques such as community tagging have shown promise for better organizing the available content. However, in more focused communities of practice, such as software engineering and development, community tagging can face some challenges such as tag explosion, locality of tags and interpretation differences, to name a few. To address these challenges, we propose a semantic tagging approach that benefits from the information available in Wikipedia to semantically ground the tagging process and provide a methodical approach for tagging social software engineering content. We have shown that our approach is able to provide high quality tags for social software engineering content that can be used not only for organizing such content but also for making meaningful and relevant content recommendation to the users both within a local community and also across multiple social online communities. We have empirically validated our approach through four main research questions. The results of our observations show that the proposed approach is quite effective in organizing social software engineering content and making relevant, helpful and novel content recommendations to software developers and users of social software engineering communities.

Topic ontology-based efficient tag recommendation approach for blogs

Efficient tag recommendation systems are required to help users in the task of searching, indexing and browsing appropriate blog content. Tag generation has become more popular to annotate web content, other blogs, photos, videos and music. Tag recommendation is an action of signifying valuable and informative tags to a budding item based on the content. We propose a novel approach based on topic ontology for tag recommendation. The proposed approach intelligently generates tag suggestions to blogs. In this paper, we effectively construct the technology entitled Ontology based on Wikipedia categories and WordNet semantic relationship to make the ontology more meaningful and reliable. Spreading activation algorithm is applied to assign interest scores to existing blog content and tags. High quality tags are suggested based on the significance of the interest score. Evaluation proves that the applicability of topic ontology with spreading activation algorithm helps tag recommendation more effective when compared to collaborative tag recommendations. Our proposed approach offers several solutions to tag spamming, sentiment analysis and popularity. Finally, we report the results of an experiment which improves the performance of tag recommendation approach.

Social Tagging: Exploring the Image, the Tags, and the Game

KO KNOWLEDGE ORGANIZATION , Seite 57 - 65

A New Approach to Tagging in Indian Languages

In this paper, we present a new approach to automatic tag- ging without requiring any machine learning algorithm or training data. We argue that the critical information required for tagging comes more from word internal structure than from the context and we show how a well designed morphological analyzer can assign correct tags and disam- biguate many cases of tag ambiguities too. The crux of the approach is in the very denition of words. While others simply tokenize a given sen- tence based on spaces and take these tokens to be words, we argue that words need to be motivated from semantic and syntactic considerations, not orthographic conventions. We have worked on Telugu and Kannada languages and in this paper, we take the example of Telugu language and show how high quality tagging can be achieved with a ne grained, hierarchical tag set, carrying not only morpho-syntactic information but also some aspects of lexical and semantic information that is necessary or useful for syntactic parsing. In fact entire corpora can be tagged very fast and with a good degree of guarantee of quality. We give details of our experiments and results obtained. We believe our approach can also be applied to other languages.

A statistical tagger for morphological tagging of Russian language texts

We consider a method of constructing a statistical tagger for automated morphological tagging for Russian language texts. In this method, each word is assigned with a tag that contains information about the part of speech and a full set of the word's morphological characteristics. We employ the set of morphological characteristics used in the SynTagRus corpus whose material has been used to train the tagger. The tagger is based on the SVM (Support Vector Machine) approach. The developed tagger has proven to be efficient and has shown high tagging quality.

Evaluation of Internal Tag Performance in Hatchery‐Reared Juvenile Spotted Seatrout

AbstractStock enhancement programs rely on the ability to recapture and identify stocked fish to evaluate stocking effectiveness. Since 2006, the Seatrout Population Enhancement Cooperative (SPEC) has released almost 600,000 Spotted Seatrout Cynoscion nebulosus, about 100 mm TL, tagged with opercular coded wire tags (CWTs) into coastal Mississippi waters. However, only about 50 fish have been recaptured and initial retention of the opercular CWT has rarely exceeded 75%. This study first evaluated the suitability of visible implant alpha (VIA) and visible implant elastomer (VIE) tags for use in juvenile Spotted Seatrout. The VIA tags performed poorly. Based on those results, the study evaluated the effects of tagging site and fish size on survival, growth, and retention of CWTs and VIE tags and VIE tag fragmentation in juvenile Spotted Seatrout. Three separate growth experiments with juvenile Spotted Seatrout that had mean initial TLs of 93, 138, and 152 mm, respectively, were conducted to assess the effects of tagging. Each growth experiment had nine treatments consisting of a control, fish with either an opercular CWT, a dorsal muscle CWT, a ventral caudal fin VIE tag, or a jaw VIE tag, and four false‐tagged treatments corresponding to each tagged treatment. Dorsal CWTs were retained better than opercular CWTs; VIE tags were equally retained regardless of body location. However, VIE tag quality was affected over the long term by pigmentation overlap and fragmentation. Growth rates and survival were not different within any size‐class experiment or among treatments. This study has shown that CWTs and VIE tags are effective marking methods for juvenile Spotted Seatrout.Received October 11, 2012; accepted May 16, 2013

Comparing student and expert-based tagging of recorded lectures

In this paper we analyse the way students tag recorded lectures. We compare their tagging strategy and the tags that they create with tagging done by an expert. We look at the quality of the tags students add, and we introduce a method of measuring how similar the tags are, using vector space modelling and cosine similarity. We show that the quality of tagging by students is high enough to be useful. We also show that there is no generic vocabulary gap between the expert and the students. Our study shows no statistically significant correlation between the tag similarity and the indicated interest in the course, the perceived importance of the course, the number of lectures attended, the indicated difficulty of the course, the number of recorded lectures viewed, the indicated ease of finding the needed parts of a recorded lecture, or the number of tags used by the student.

Genome-Wide Analysis of Differentially Expressed Genes Relevant to Rhizome Formation in Lotus Root (Nelumbo nucifera Gaertn).

Lotus root is a popular wetland vegetable which produces edible rhizome. At the molecular level, the regulation of rhizome formation is very complex, which has not been sufficiently addressed in research. In this study, to identify differentially expressed genes (DEGs) in lotus root, four libraries (L1 library: stolon stage, L2 library: initial swelling stage, L3 library: middle swelling stage, L4: later swelling stage) were constructed from the rhizome development stages. High-throughput tag-sequencing technique was used which is based on Solexa Genome Analyzer Platform. Approximately 5.0 million tags were sequenced, and 4542104, 4474755, 4777919, and 4750348 clean tags including 151282, 137476, 215872, and 166005 distinct tags were obtained after removal of low quality tags from each library respectively. More than 43% distinct tags were unambiguous tags mapping to the reference genes, and 40% were unambiguous tag-mapped genes. From L1, L2, L3, and L4, total 20471, 18785, 23448, and 21778 genes were annotated, after mapping their functions in existing databases. Profiling of gene expression in L1/L2, L2/L3, and L3/L4 libraries were different among most of the selected 20 DEGs. Most of the DEGs in L1/L2 libraries were relevant to fiber development and stress response, while in L2/L3 and L3/L4 libraries, major of the DEGs were involved in metabolism of energy and storage. All up-regulated transcriptional factors in four libraries and 14 important rhizome formation-related genes in four libraries were also identified. In addition, the expression of 9 genes from identified DEGs was performed by qRT-PCR method. In a summary, this study provides a comprehensive understanding of gene expression during the rhizome formation in lotus root.

Identification of differentially expressed genes relevant to corm formation in Sagittaria trifolia.

Sagittaria trifolia is a good model of wetland plants to elucidate the formation of corm. However, few studies have been conducted to uncover the complexity of gene expression involved in corm formation. In this study, high-throughput tag-sequencing based on Solexa Genome Analyzer Platform was applied to monitor the changes in gene expression with three libraries of differentially expressed genes (DEGs) (C1 library: stolon stage, C2 library: initial swelling stage and C3 library: swelling stage) during corm formation in Sagittaria trifolia. Approximately 6.0 million tags were sequenced, and 5854021, 5983454, and 5761079 clean tags including 138319, 116804, and 101739 distinct tags were obtained after removal of low quality tags from each library, respectively. About 46% distinct tags were unambiguous tags mapping to the reference genes, and 33% were unambiguous tag-mapped genes. Totally, 20575, 19807, and 18438 were annotated in C1, C2, and C3 libraries, respectively, after mapping their functions in existing databases. In addition, we found that profiling of gene expression in C1/C2 and C2/C3 libraries were different among most of the selected 20 DEGs. Most DEGs in C1/C2 libraries were relevant to hormone synthesis and response; energy metabolism and stress response, while most of the genes in C2/C3 libraries were involved in carbohydrate metabolism. All up-regulated transcriptional factors and 16 important genes relevant to corm formation in three libraries were also identified. To further analyze the expression of 9 genes, from the results of tag-sequencing, qRT-PCR was applied. In summary, this study provides a comprehensive understanding of gene expression, during the formation of corm in Sagittaria trifolia.

A tangle of tags: The impact of user‐generated tagging in public library catalogs

AbstractWith the increased adoption of catalog packages such as Bibliocommons and Aquabrowser comes a need to investigate the ways in which folksonomic tools impact the amount and quality of user tagging in public library catalogs. This pilot study compares two public library catalogs from library systems in the Midwestern United States. The underlying goals of the investigation were to compare the two catalogs to see whether 1) pronounced differences between the folksonomies of user tags existed in both library catalogs, in number of tags for selected titles and scope/coverage of tags; and 2) how the tags from MPLS compare to the tags presented in Aquabrowser's supplemental tag cloud and RPL and the implications inherent in these comparisons. Using the Book Industry Standard and Communications (BISAC) subject headings, user tags from the two library catalogs were coded and compared for scope and frequency. Results indicate that RPL, which uses Aquabrowser, has significantly more user tags that cover a broader scope than those of MPLS. Findings demonstrate the need for further consideration of user tagging in Web 2.0 catalogs.

Tag Quality Improvement for Social Image Hosting Website

Tag Quality Improvement for Social Image Hosting Website

Tag Quality Improvement for Social Image Hosting Website

Tag Quality Improvement for Social Image Hosting Website

Tag Completion for Image Retrieval

Many social image search engines are based on keyword/tag matching. This is because tag-based image retrieval (TBIR) is not only efficient but also effective. The performance of TBIR is highly dependent on the availability and quality of manual tags. Recent studies have shown that manual tags are often unreliable and inconsistent. In addition, since many users tend to choose general and ambiguous tags in order to minimize their efforts in choosing appropriate words, tags that are specific to the visual content of images tend to be missing or noisy, leading to a limited performance of TBIR. To address this challenge, we study the problem of tag completion, where the goal is to automatically fill in the missing tags as well as correct noisy tags for given images. We represent the image-tag relation by a tag matrix, and search for the optimal tag matrix consistent with both the observed tags and the visual similarity. We propose a new algorithm for solving this optimization problem. Extensive empirical studies show that the proposed algorithm is significantly more effective than the state-of-the-art algorithms. Our studies also verify that the proposed algorithm is computationally efficient and scales well to large databases.

Combining content and relation analysis for recommendation in social tagging systems

Social tagging is one of the most important ways to organize and index online resources. Recommendation in social tagging systems, e.g. tag recommendation, item recommendation and user recommendation, is used to improve the quality of tags and to ease the tagging or searching process. Existing works usually provide recommendations by analyzing relation information in social tagging systems, suffering a lot from the over sparse problem. These approaches ignore information contained in the content of resources, which we believe should be considered to improve recommendation quality and to deal with the over sparse problem. In this paper we propose a recommendation approach for social tagging systems that combines content and relation analysis in a single model. By modeling the generating process of social tagging systems in a latent Dirichlet allocation approach, we build a fully generative model for social tagging, leverage it to estimate the relation between users, tags and resources and achieve tag, item and user recommendation tasks. The model is evaluated using a CiteULike data snapshot, and results show improvements in metrics for various recommendation tasks.

Combining Relation and Content Analysis for Social Tagging Recommendation

标签是Web 2.0 时代信息分类与索引的重要方式.为解决标签系统所面临的不一致性、冗余性以及完备性等问题,标签推荐通过提供备选标签的方法来提高标签的质量.为了进一步提升标签推荐的质量,提出了一种基于标签系统中对象间关系与资源内容融合分析的标签推荐方法,给出了基于LDA(latent Dirichlet allocation)的融合表示对象间关系与资源内容的标签系统生成模型TSM/Forc,提出了一种基于概率的标签推荐方法,并给出了基于吉布斯(Gibbs)抽样的参数估计方法.实验结果表明,该方法可以提供比当前主流与最新方法更加准确的推荐结果.;Tagging is one of the most important ways to categorize or indexing information at the age of Web 2.0. To handle the disadvantages of tagging systems such as inconsistentcies, redundancy and incompleteness, tag recommendation methods improve the quality of tags by providing candidate tags. In order to further improve the quality of tag recommendations, a tag recommendation method is proposed which bases on a combined analysis of the relations of objects in a tagging system and the content of resources. An LDA based generative tagging system model TSM/Forc that models object relation and resource content in a combined way is introduced, together with a probabilistic based tag recommendation method and a Gibbs sampling based model parameter estimation approach. Experiment results show that the proposed method could provide more accurate recommendations than the latest methods.

The use of a ‘bleach‐etch‐seal’ deproteinization technique on MIH affected enamel

To ascertain whether deproteinization pretreatment of molar-incisor hypomineralization (MIH) enamel affects resin sealant infiltration. Thirty one extracted MIH teeth were divided into three sections and randomly allocated into the Control (etch and FS), Treatment 1 (5% NaOCl, etched and fissure sealed), and Treatment 2 (5% NaOCl and fissure sealed with no etch) groups. Two hundred seventy nine sealant tag/enamel grade observations were recorded by scanning electron microscopy. Control and Treatment 1 were similar in their outcomes, and Treatment 2 was markedly different. There was no statistical evidence to suggest that there was any difference between Treatment 1 and the Control Treatment (95% CI, 0.52, 1.51; P = 0.6). There was a marked difference between Treatment 2 and the Control Treatment (95% CI, 0.07, 0.25; P < 0.001). All treatments also demonstrated a high-predicted probability of obtaining 'poor' sealant tags (Control = 47%, Treatment 1 = 49%, and Treatment 2 = 40%). The findings suggest that there was no significant difference in the tag quality between the conventional technique (Control) and the 'bleach-etch-seal' technique (Treatment 1). There was no benefit in pre-treating with NaOCl alone (without etch) before sealing. This research also showed that there was a high-predicted probability of obtaining 'poor' sealant tags in MIH enamel, regardless of which of the three treatments was used.

Content Classification by folksonomies: Framework of Social Bookmarking System

Social bookmarking is a recent phenomenon which has the potential to give us a great deal of data about pages on the web. In this paper, we present an improved framework to web content classification based on Folksonomy. Since Folksonomy is keyword-based, it is associated with semantic problems. Various academicians have constructed ontologies to solve semantic problems. However, ontology depends on expert knowledge of the problem domain, and the process of constructing knowledge depends on the participation of knowledge engineers. This study presents an improved weighting mechanism to solve the semantic problems and the problematic effects of poor classification. An experimental prototype called FSBS (Folksonomy Social Bookmarking System) was developed. Testing indicates that the FSBS can effectively reduce the number of classification results by more than 30% significantly improved the quality of tagging, and increased user satisfaction. We believed that our works have provided a feasible framework for an intelligent social bookmarking system.

Perceptions, quality and motivational needs in image tagging human computation games

Human computation games (HCGs) are applications that use games to harness human intelligence to perform various computational tasks. That is, users perform computations as a byproduct of being entertained while playing a game. Such games are increasing in popularity and it is critical to examine how different types of HCG affect players’ perceptions and performance. In addition, understanding their motivational appeal to different players is also important to good HCG design. In the present research, we focus on image tagging HCGs, where users play games to generate keywords for images. Three versions were created: a collaborative HCG which required players to cooperate, a competitive HCG where players worked against each other, and a control non-game manual tagging application. The applications were evaluated to uncover the quality of the tags, users’ perceptions of these variants, and the influence of motivational needs on usage intention. Results suggest that, while participants reported liking the collaborative and competitive HCGs over the control application, those using the latter seemed to generate better quality tags. Further, using the trichotomy of needs theory, we found that an individual’s need for achievement and power influenced intention to use the various applications.