Search results

Graphic-based tag clouds aim to visually represent tag content and tag structure, and then to better represent tagged information for later search. However, few studies have clarified the features among varied visualization approaches involved in graphic-based tag clouds and compared them for the purpose of information search.

After reviewing four kinds of graphic-based tag clouds, an experimental demonstration was conducted in our study to verify how user performs in information search for a general seeking task by using them. Precision ratio, recall ratio, clicks on search and time for search were four variables tested in the experiment. Also, two supplementary tests were respectively carried out to manifest how graphic-based tag clouds contributed to the identification of target tags and tag clusters.

The experimental results showed that compared to tag content visual tag structure was more important to find related tags from tag clouds for information search. In addition, tag clouds that visually represented the semantic relationships within tags could make user more confident about their search result and carry out a shorter learning process during searching, which signified a tag-based information search path when visual elements were applied.

This research is one of the first to illustrate systematically the graphic-based tag clouds and their impacts on information search. The research findings could suggest on how to build up more effective and interactive tag clouds and make proposition for the design of search user interface by using graphic-based tag clouds.

This paper proposes a recommendation method that mines the semantic relationship between resources and combine it with collaborative filtering (CF) algorithm for crowdsourcing knowledge-sharing communities.

First, structured tag trees are constructed based on tag co-occurrence to overcome the tags' lack of semantic structure. Then, the semantic similarity between tags is determined based on tag co-occurrence and the tag-tree structure, and the semantic similarity between resources is calculated based on the semantic similarity of the tags. Finally, the user-resource evaluation matrix is filled based on the resource semantic similarity, and the user-based CF is used to predict the user's evaluation of the resources.

Folksonomy is a knowledge classification method that is suitable for crowdsourcing knowledge-sharing communities. The semantic similarity between resources can be obtained according to the tags in the folksonomy system, which can be used to alleviate the data sparsity and cold-start problems of CF. Experimental results show that compared with other algorithms, the algorithm in this paper performs better in mean absolute error (MAE) and F1, which indicates that the proposed algorithm yields better performance.

The proposed folksonomy-based CF method can help users in crowdsourcing knowledge-sharing communities to better find the resources they need.

This paper aims to explore the characteristics of the co-occurrence network of online tags and propose new approaches of applying social network analysis by utilising social tagging in order to organise data.

The authors collected online resources labelled “tag” from 7 November 2004 to 31 October 2011 from the CiteULike website, comprising 684 papers and their URLs, titles and data on tagging (users, times, and tags). They examined the co-occurrence network of online tags by using the analyses of social networks, including the analysis of coherence, the analysis of centricity and core to periphery categorical analysis.

Some features of the co-occurrence of online tags are as follows: the internet is subject to the “small world” phenomenon, as well as being “scale-free”. The structure of the internet reflects stable areas of core knowledge. In addition to five possible applications of social network analysis, social tagging has the greatest significance in organising online resources.

This research finds that co-occurrence of tags online is an effective way to organise and index data. Some suggestions are provided on the organisation of online resources.

With the continuous increase of users, resources and tags, social tagging systems gradually present the characteristics of “big data” such as large number, fast growth, complexity and unreliable quality, which greatly increases the complexity of recommendation. The contradiction between the efficiency and effectiveness of recommendation service in social tagging is increasingly becoming prominent. The purpose of this study is to incorporate topic optimization into collaborative filtering to enhance both the effectiveness and the efficiency of personalized recommendations for social tagging.

Combining the idea of optimization before service, this paper presents an approach that incorporates topic optimization into collaborative recommendations for social tagging. In the proposed approach, the recommendation process is divided into two phases of offline topic optimization and online recommendation service to achieve high-quality and efficient personalized recommendation services. In the offline phase, the tags' topic model is constructed and then used to optimize the latent preference of users and the latent affiliation of resources on topics.

Experimental evaluation shows that the proposed approach improves both precision and recall of recommendations, as well as enhances the efficiency of online recommendations compared with the three baseline approaches. The proposed topic optimization–incorporated collaborative recommendation approach can achieve the improvement of both effectiveness and efficiency for the recommendation in social tagging.

With the support of the proposed approach, personalized recommendation in social tagging with high quality and efficiency can be achieved.

Visual Distinctive Language (VDL)-based iconic tags are structured visual information annotation. They explicate the content and organization of tagged information by graphical and symbolic features in order to improve the vocabulary problems of textual tags. The purpose of this paper is to investigate how these special icons help in tagged-based user information searching.

A two-stage experiment was designed and conducted so as to follow and quantify the searching process in specific searching target case and no specific searching target case when using VDL-based iconic tags.

The experimental results manifested that VDL-based iconic tags enhanced the role of tag in information searching. They could make user better understand tag clusters, which, in turn, provide global structure of involved topics. Also, VDL-based iconic tags helped user to find out searching target more quickly with higher accuracy by taking advantages of visual representation of tag categories and symbolic signification of tag content.

This study is one of the first to verify how structured icons work in information searching and how user’s graphical cognition impacts on tag-based information searching process. The research findings are dedicated to the theory of VDL-based iconic tags, as well as to a new visualization method for search user interface design.

The purpose of this study was to compare the ease of use and the effectiveness of several interfaces for retrieving tagged images.

A number of participants were randomly assigned to one of four retrieval interfaces: tag search in a search box; faceted tag search in a search box; selecting terms from the tag cloud of all the tags in the database; and selecting concepts from an ontology created from the tags assigned to the images. Each interface was tested by 21 users.

The results show that the highest recall on average was achieved by users of the ontology interface, for seven out of the ten tasks, however, users were more satisfied with the textbox‐based search than the cloud or the ontology.

The experiment was rather specific, and more studies are needed in order to generalize the findings.

With the widespread use of tagging on the web it is of importance to examine whether tagging enables resource discovery. This study shows that in addition to the tags, the retrieval interface also influences user satisfaction and retrieval success.

This article describes the third part of a three-stage study investigating the information behaviour of fans and fan communities, the first stage of which is described in the study by Price and Robinson (2017).

Using tag analysis as a method, a comparative case study was undertaken to explore three aspects of fan information behaviour: information gatekeeping; classifying and tagging and entrepreneurship and economic activity. The case studies took place on three sites used by fans–Tumblr, Archive of Our Own (AO3) and Etsy. Supplementary semi-structured interviews with site users were used to augment the findings with qualitative data.

These showed that fans used tags in a variety of ways quite apart from classification purposes. These included tags being used on Tumblr as meta-commentary and a means of dialogue between users, as well as expressors of emotion and affect towards posts. On AO3 in particular, fans had developed a practice called “tag wrangling” to mitigate the inherent “messiness” of tagging. Evidence was also found of a “hybrid market economy” on Etsy fan stores. From the study findings, a taxonomy of fan-related tags was developed.

Findings are limited to the tagging practices on only three sites used by fans during Spring 2016, and further research on other similar sites are recommended. Longitudinal studies of these sites would be beneficial in understanding how or whether tagging practices change over time. Testing of the fan-tag taxonomy developed in this paper is also recommended.

This research develops a method for using tag analysis to describe information behaviour. It also develops a fan-tag taxonomy, which may be used in future research on the tagging practices of fans, which heretofore have been a little-studied section of serious leisure information users.

Generally, the user requires customized information reflecting his/her current needs and interests that are stored in his/her profile. There are many sources which may provide beneficial information to enrich the user’s interests such as his/her social network for recommendation purposes. The proposed approach rests basically on predicting the reliability of the users’ profiles which may contain conflictual interests. The paper aims to discuss this issue.

This approach handles conflicts by detecting the reliability of neighbors’ profiles of a user. The authors consider that these profiles are dependent on one another as they may contain interests that are enriched from non-reliable profiles. The dependency relationship is determined between profiles, each of which contains interests that are structured based on k-means algorithm. This structure takes into consideration not only the evolutionary aspect of interests but also their semantic relationships.

The proposed approach was validated in a social-learning context as evaluations were conducted on learners who are members of Moodle e-learning system and Delicious social network. The quality of the created interest structure is assessed. Then, the result of the profile reliability is evaluated. The obtained results are satisfactory. These results could promote recommendation systems as the selection of interests that are considered of enrichment depends on the reliability of the profiles where they are stored.

Some specific limitations are recorded. As the quality of the created interest structure would evolve in order to improve the profile reliability result. In addition, as Delicious is used as a main data source for the learner’s interest enrichment, it was necessary to obtain interests from other sources, such as e-recruitement systems.

This research is among the pioneer papers to combine the semantic as well as the hierarchical structure of interests and conflict resolution based on a profile reliability approach.

The fabulous results of convolution neural networks in image-related tasks attracted attention of text mining, sentiment analysis and other text analysis researchers. It is, however, difficult to find enough data for feeding such networks, optimize their parameters, and make the right design choices when constructing network architectures. The purpose of this paper is to present the creation steps of two big data sets of song emotions. The authors also explore usage of convolution and max-pooling neural layers on song lyrics, product and movie review text data sets. Three variants of a simple and flexible neural network architecture are also compared.

The intention was to spot any important patterns that can serve as guidelines for parameter optimization of similar models. The authors also wanted to identify architecture design choices which lead to high performing sentiment analysis models. To this end, the authors conducted a series of experiments with neural architectures of various configurations.

The results indicate that parallel convolutions of filter lengths up to 3 are usually enough for capturing relevant text features. Also, max-pooling region size should be adapted to the length of text documents for producing the best feature maps.

Top results the authors got are obtained with feature maps of lengths 6–18. An improvement on future neural network models for sentiment analysis could be generating sentiment polarity prediction of documents using aggregation of predictions on smaller excerpt of the entire text.

The purpose of this paper is to investigate the linking of a folksonomy (user vocabulary) and LCSH (controlled vocabulary) on the basis of word matching, for the potential use of LCSH in bringing order to folksonomies.

A selected sample of a folksonomy from a popular collaborative tagging system, Delicious, was word‐matched with LCSH. LCSH was transformed into a tree structure called an LCSH tree for the matching. A close examination was conducted on the characteristics of folksonomies, the overlap of folksonomies with LCSH, and the distribution of folksonomies over the LCSH tree.

The experimental results showed that the total proportion of tags being matched with LC subject headings constituted approximately two‐thirds of all tags involved, with an additional 10 percent of the remaining tags having potential matches. A number of barriers for the linking as well as two areas in need of improving the matching are identified and described. Three important tag distribution patterns over the LCSH tree were identified and supported: skewedness, multifacet, and Zipfian‐pattern.

The results of the study can be adopted for the development of innovative methods of mapping between folksonomy and LCSH, which directly contributes to effective access and retrieval of tagged web resources and to the integration of multiple information repositories based on the two vocabularies.

The linking of controlled vocabularies can be applicable to enhance information retrieval capability within collaborative tagging systems as well as across various tagging system information depositories and bibliographic databases.

This is among frontier works that examines the potential of linking a folksonomy, extracted from a collaborative tagging system, to an authority‐maintained subject heading system. It provides exploratory data to support further advanced mapping methods for linking the two vocabularies.