Automatic Metadata Generation Research Articles

FAIR+R: Making Clinical Data Reliable Through Qualitative Metadata.

Metadata are often the first access to data repositories for researchers within secondary use. Through automatic metadata generation and metadata harvesting the amount of data about data has been growing ever since. In order to make data not only FAIR but also reliable, the aspect of metadata quality has to be considered. But as earlier assessments of metadata of different repositories showed, metadata quality still lacks behind its capability. Providing an extensive literature review the authors conclude nine measures to assess metadata in relation to clinical care repositories, such as Medical Data Integration Centers (MeDICs). Proceeding from these measures the authors propose an addition of the FAIR Guiding Principles by adding a fifth block for Reliability including three principles, that resulted from the measures presented. The results form the basis for the future work of an assessment of metadata, that is stored in a MeDIC.

Development and implementation of automatic metadata generation framework for SDI using OSS: a case study of Indian NSDI

Development and implementation of automatic metadata generation framework for SDI using OSS: a case study of Indian NSDI

Modelling the Microphone-Related Timbral Brightness of Recorded Signals

Brightness is one of the most common timbral descriptors used for searching audio databases, and is also the timbral attribute of recorded sound that is most affected by microphone choice, making a brightness prediction model desirable for automatic metadata generation. A model, sensitive to microphone-related as well as source-related brightness, was developed based on a novel combination of the spectral centroid and the ratio of the total magnitude of the signal above 500 Hz to that of the full signal. This model performed well on training data (r = 0.922). Validating it on new data showed a slight gradient error but good linear correlation across source types and overall (r = 0.955). On both training and validation data, the new model out-performed metrics previously used for brightness prediction.

Stanza Type Identification using Systematization of Versification System of Hindi Poetry

Poetry covers a vast part of the literature of any language. Similarly, Hindi poetry is also having a massive portion in Hindi literature. In Hindi poetry construction, it is necessary to take care of various verse writing rules. This paper focuses on the automatic metadata generation from such poems by computational linguistics integrated advance and systematic, prosody rule-based modeling and detection procedures specially designed for Hindi poetry. The paper covers various challenges and the best possible solutions for those challenges, describing the methodology to generate automatic metadata for “Chhand” based on the poems’ stanzas. It also provides some advanced information and techniques for metadata generation for “Muktak Chhands”. Rules of the “Chhands” incorporated in this research were identified, verified, and modeled as per the computational linguistics perspective the very first time, which required a lot of effort and time. In this research work, 111 different “Chhand” rules were found. This paper presents rule-based modeling of all of the “Chhands”. Out of the all modeled “Chhands” the research work covers 53 “Chhands” for which at least 20 to 277 examples were found and used for automatic processing of the data for metadata generation. For this research work, the automatic metadata generator processed 3120 UTF-8 based inputs of 53 Hindi “Chhand” types, achieved 95.02% overall accuracy, and the overall failure rate was 4.98%. The minimum time taken for the processing of “Chhand” for metadata generation was 1.12 seconds, and the maximum was 91.79 seconds.

Modelling Timbral Hardness

Hardness is the most commonly searched timbral attribute within freesound.org, a commonly used online sound effect repository. A perceptual model of hardness was developed to enable the automatic generation of metadata to facilitate hardness-based filtering or sorting of search results. A training dataset was collected of 202 stimuli with 32 sound source types, and perceived hardness was assessed by a panel of listeners. A multilinear regression model was developed on six features: maximum bandwidth, attack centroid, midband level, percussive-to-harmonic ratio, onset strength, and log attack time. This model predicted the hardness of the training data with R 2 = 0.76. It predicted hardness within a new dataset with R 2 = 0.57, and predicted the rank order of individual sources perfectly, after accounting for the subjective variance of the ratings. Its performance exceeded that of human listeners.

Framework for Knowledge Discovery in Educational Video Repositories

The ease of creating digital content coupled with technological advancements allows institutions and organizations to further embrace distance learning. Teaching materials also receive attention, because it is difficult for the student to obtain adequate didactic material, being necessary a high effort and knowledge about the material and the repository. This work presents a framework that enables the automatic metadata generation for materials available in educational video repositories. Each module of the framework works autonomously and can be used in isolation, complemented by another technique or replaced by a more appropriate approach to the field of use, such as repositories with other types of media or other content.

Advancing Professional Learning in Libraries: An Exploratory Study of Cataloging and Metadata Professionals' Experiences and Perspectives on Continuing Education Issues

ABSTRACTBased on a set of web survey data, this study examines cataloging and metadata professionals' perspectives on issues surrounding continuing education. The results show that emerging data standards such as the Semantic Web and BIBFRAME, as well as metadata and digital library-related topics, are subject areas currently central to their professional concerns, in addition to RDA, for professional development. Topics such as ontologies, social tagging, and automatic metadata generation were rarely reported. Meaningful interactions were often found to be lacking in online education. The results provide evidence of the need to expand the pool of shared expertise to meet our collective needs for continuing education in the cataloging and metadata community.

Evaluation of Semi-Automatic Metadata Generation Tools: A Survey of the Current State of the Art

Assessment of the current landscape of semi-automatic metadata generation tools is particularly important considering the rapid development of digital repositories and the recent explosion of big data. Utilization of (semi)automatic metadata generation is critical in addressing these environmental changes and may be unavoidable in the future considering the costly and complex operation of manual metadata creation. To address such needs, this study examines the range of semi-automatic metadata generation tools (n=39) while providing an analysis of their techniques, features, and functions. The study focuses on open-source tools that can be readily utilized in libraries and other memory institutions. The challenges and current barriers to implementation of these tools were identified. The greatest area of difficulty lies in the fact that the piecemeal development of most semi-automatic generation tools only addresses part of the issue of semi-automatic metadata generation, providing solutions to one or a few metadata elements but not the full range elements. This indicates that significant local efforts will be required to integrate the various tools into a coherent set of a working whole. Suggestions toward such efforts are presented for future developments that may assist information professionals with incorporation of semi-automatic tools within their daily workflows.

Enabling context-aware multimedia annotation by a novel generic semantic problem-solving platform

Automatic generation of metadata, facilitating the retrieval of multimedia items, potentially saves large amounts of manual work. However, the high specialization degree of feature extraction algorithms makes them unaware of the context they operate in, which contains valuable and often necessary information. In this paper, we show how Semantic Web technologies can provide a context that algorithms can interact with. We propose a generic problem-solving platform that uses Web services and various knowledge sources to find solutions to complex requests. The platform employs a reasoner-based composition algorithm, generating an execution plan that combines several algorithms as services. It then supervises the execution of this plan, intervening in case of errors or unexpected behavior. We illustrate our approach by a use case in which we annotate the names of people depicted in a photograph.

Capture of lifecycle information in office applications

Due to the continuously growing number of Learning Resources the automatic generation of metadata has become an important research issue. Lifecycle information like, relations resulting from reuse of Learning Resources can be utilised to support users, for example, in retrieving relevant documents. However, this kind of information is neglected by most systems. We show that lifecycle information can be obtained automatically without user interaction. We describe the challenges that have to be faced when capturing lifecycle information in office applications and present how we met them in the implementation of add-ins for our LIS.KOM framework. The results of first evaluations are promising.

Automatic evaluation of metadata quality in digital repositories

Owing to the recent developments in automatic metadata generation and interoperability between digital repositories, the production of metadata is now vastly surpassing manual quality control capab...

Automatic evaluation of metadata quality in digital repositories

Owing to the recent developments in automatic metadata generation and interoperability between digital repositories, the production of metadata is now vastly surpassing manual quality control capabilities. Abandoning quality control altogether is problematic, because low-quality metadata compromise the effectiveness of services that repositories provide to their users. To address this problem, we present a set of scalable quality metrics for metadata based on the Bruce & Hillman framework for metadata quality control. We perform three experiments to evaluate our metrics: (1) the degree of correlation between the metrics and manual quality reviews, (2) the discriminatory power between metadata sets and (3) the usefulness of the metrics as low-quality filters. Through statistical analysis, we found that several metrics, especially Text Information Content, correlate well with human evaluation and that the average of all the metrics are roughly as effective as people to flag low-quality instances. The implications of this finding are discussed. Finally, we propose possible applications of the metrics to improve tools for the administration of digital repositories.

Application of semi-automatic metadata generation in libraries: Types, tools, and techniques

Analysis of a survey of the types and extent of tools and techniques related to semi-automatic metadata generation applied in real-world library settings indicates that practical applications in libraries seem to be at an incipient stage. More than half ( n = 149, 52.5%) of the survey participants ( n = 285) specify that semi-automatic metadata generation has not been utilized for metadata creation and management in their libraries. This figure becomes even higher when adding the response “don't know,” constituting an additional 13.7%. The results of the survey also show that the semi-automatic metadata generation tools described by participants mostly concern metadata format conversion (38.6%) and metadata templates and forms (27%) for populating certain metadata values. Complex tools and the generation and extraction of metadata directly from the content and context of the digital objects are rarely applied in libraries. This indicates that more research is needed on the development of automatic metadata generation for semantic metadata in usable and practical settings.

Automatic metadata generation using associative networks

In spite of its tremendous value, metadata is generally sparse and incomplete, thereby hampering the effectiveness of digital information services. Many of the existing mechanisms for the automated creation of metadata rely primarily on content analysis which can be costly and inefficient. The automatic metadata generation system proposed in this article leverages resource relationships generated from existing metadata as a medium for propagation from metadata-rich to metadata-poor resources. Because of its independence from content analysis, it can be applied to a wide variety of resource media types and is shown to be computationally inexpensive. The proposed method operates through two distinct phases. Occurrence and cooccurrence algorithms first generate an associative network of repository resources leveraging existing repository metadata. Second, using the associative network as a substrate, metadata associated with metadata-rich resources is propagated to metadata-poor resources by means of a discrete-form spreading activation algorithm. This article discusses the general framework for building associative networks, an algorithm for disseminating metadata through such networks, and the results of an experiment and validation of the proposed method using a standard bibliographic dataset.

The user‐centered design of a non‐specialist metadata tool and interface for the Internet Public Library

AbstractGood quality metadata are key in supporting user interactions with a repository. Poor quality metadata hide resources, produce poor search results, and negatively affect user satisfaction (Barton et al. 2004; Beall 2005; Geisler et al. 2002). Good quality metadata can be resource‐intensive to produce, and as a result there is a ‘metadata generation bottleneck’ between the growing numbers of digital resources requiring description and the limited numbers of metadata specialists who can create such descriptions (Liddy et al., 2001). This can restrict metadata production and reduce the utility of repositories (Wilson, 2007). Approaches to addressing this bottleneck include training more metadata specialists; automatic metadata generation (Liddy et al., 2001; Ochoa & Duval n.d.); and also the solution discussed in this poster, the user‐centered design and development of a tool to support student volunteers and interns to engage in the creation and quality control of Dublin Core metadata records for the Internet Public Library (IPL: http://www.ipl.org/).

Automatic metadata generation by utilising pre-existing metadata of related resources

Manual indexing of digital resources according to metadata standards is a laborious task. Methods and methodologies for automatically producing several parts of a resource's metadata provide valuable assistance to indexers and cataloguers by reducing the burden of their manual work. A methodology, which aims at identifying inference rules for the automatic generation of a resource's metadata, based on pre-existing metadata of its related resources, is introduced in this paper. Furthermore, the application of the methodology to the IEEE LOM standard and an experimental example on a working database of metadata, with a tool developed for this purpose, are demonstrated.

Automatic metadata generation applications: a survey study

This study is a survey of Automatic Metadata Generations Applications (AMeGAs) that are available and free on the Web. The study tested the functions as well as the features of each tool, by using a survey approach and features analysis. The results indicated that Meta Tag Generators (MTGs), which generate meta-information about the Web page, were the most available applications on the Web. Actually, they represented 89.27%. The analysing tools, which check and analyse the existing meta tags in the website, to help Webmasters optimise them, represented 6.34%. The other applications that automatically create metadata from an analysis of the digital resource such as extracting, harvesting and converting tools represented 1.46% for each tool. This study discussed the key results in addition to the future researches.

Can a system make novice users experts? Analysis of metadata created by novices and experts with varying levels of assistance

Accurate description of web resources is one path to the development of the Semantic Web. Two major problems for metadata generation are lack of expertise and the number of web resources. An automated or semi-automated system could encourage creation of metadata for web resources. This work is focused on the design and assessment of a semi-automated Metadata-Generation System (MGS) using four classes of descriptive elements - bibliographic, semantic, keywords and structure. The study tries to assess how the level of knowledge or skill impacts the quality of the metadata generated and, based on the results, it suggests the kind of information automatic metadata generation tools should suggest to users.

Facilitating metadata creation - The MINE metadata wizard for IEEE LOM

One stumbling block to the establishment of distance learning programs is on the time consuming tasks to create high quality digital contents that can be used in instruction. In the literature, reusability of learning objects is addressed as a potential solution toward the sharing of high quality contents. To find suitable contents while one is designing the course material, the IEEE LOM provides a generic and standard mechanism to enable a common representation and vocabulary for the description of learning objects. However, it is unlikely that an individual will fill out the 77 items of metadata defined by the IEEE LOM. Nevertheless, it is possible to compute the relationship among these 77 items, and to provide an automatic metadata generation mechanism to reduce the load of a content creator. This paper proposed such a mechanism, by means of using user profiles, system extracted information, interactive questions, and influence rules. We present the mechanism, as well as a developed system, called the MINE Metadata Wizard, which is integrated with a SCORM-compliant authoring tool that we have developed. Interested readers are welcome to download the tool under http://www.mine. tku.edu.tw/.

Ontology-Based Automatic Annotation of Learning Content

This paper presents an ontology-based approach to automatic annotation of learning objects’ (LOs) content units that we tested in TANGRAM, an integrated learning environment for the domain of Intelligent Information Systems. The approach does not primarily focus on automatic annotation of entire LOs, as other relevant solutions do. Instead, it provides a solution for automatic metadata generation for LOs’ components (i.e., smaller, potentially reusable, content units). Here we mainly report on the content-mining algorithms and heuristics applied for determining values of certain metadata elements used to annotate content units. Specifically, the focus is on the following elements: title, description, unique identifier, subject (based on a domain ontology), and pedagogical role (based on an ontology of pedagogical roles). Additionally, as TANGRAM is grounded on an LO content structure ontology that drives the process of an LO decomposition into its constituent content units, each thus generated content unit is implicitly semantically annotated with its role/position in the LO’s structure. Employing such semantic annotations, TANGRAM allows assembling content units into new LOs personalized to the users’ goals, preferences, and learning styles. In order to provide the evaluation of the proposed solution, we describe our experiences with automatic annotation of slide presentations, one of the most common LO types.