[ { "key": "BFEEE7H7", "version": 4, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/BFEEE7H7", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/BFEEE7H7", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/748484/items/EAG9KHVZ", "type": "application/json" } }, "meta": { "createdByUser": { "id": 3055303, "username": "annieyan", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/annieyan", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BFEEE7H7", "version": 4, "parentItem": "EAG9KHVZ", "itemType": "note", "note": "", "tags": [], "relations": {}, "dateAdded": "2016-10-11T17:30:22Z", "dateModified": "2016-10-11T17:30:22Z" } }, { "key": "ZXHV5752", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/ZXHV5752", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/ZXHV5752", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Servilla et al.", "numChildren": 0 }, "data": { "key": "ZXHV5752", "version": 3, "itemType": "journalArticle", "title": "The contribution and reuse of LTER data in the Provenance Aware Synthesis Tracking Architecture (PASTA) data repository", "creators": [ { "creatorType": "author", "firstName": "Mark", "lastName": "Servilla" }, { "creatorType": "author", "firstName": "James", "lastName": "Brunt" }, { "creatorType": "author", "firstName": "Duane", "lastName": "Costa" }, { "creatorType": "author", "firstName": "Jeanine", "lastName": "McGann" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Waide" } ], "abstractNote": "Sites in the Long Term Ecological Research (LTER) Network have now contributed greater than 5000 data packages into the LTER Network Information System (NIS). This corpus of data and metadata allows us to analyze characteristics of data from the LTER program, including temporal coverage, data format, rate of submission, volume of data, and ecological characteristics of the data (e.g., ecosystems, processes, organisms). In addition, data/metadata congruence checks included in the Provenance Aware Synthesis Tracking Architecture (PASTA) underlying the NIS allow us to examine the quality of metadata submitted. Initial records of data use and citation provide the means to evaluate the efficacy of this repository in disseminating data throughout a broader community – 89 citations of data packages found in 52 articles have been documented to date.", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.ecoinf.2016.07.003", "citationKey": "", "url": "http://www.sciencedirect.com/science/article/pii/S1574954116300875", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1574-9541", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "LTER Network" }, { "tag": "Network Information System" }, { "tag": "PASTA" }, { "tag": "information management" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "V29PKBKQ", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/V29PKBKQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/V29PKBKQ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Missier", "parsedDate": "2016-09-29", "numChildren": 0 }, "data": { "key": "V29PKBKQ", "version": 3, "itemType": "journalArticle", "title": "Data trajectories: tracking reuse of published data for transitive credit attribution", "creators": [ { "creatorType": "author", "firstName": "Paolo", "lastName": "Missier" } ], "abstractNote": "The ability to measure the use and impact of published data sets is key to the success of the open data/open science paradigm. A direct measure of impact would require tracking data (re)use in the wild, which is difficult to achieve. This is therefore commonly replaced by simpler metrics based on data download and citation counts. In this paper we describe a scenario where it is possible to track the trajectory of a dataset after its publication, and show how this enables the design of accurate models for ascribing credit to data originators. A Data Trajectory (DT) is a graph that encodes knowledge of how, by whom, and in which context data has been re-used, possibly after several generations. We provide a theoretical model of DTs that is grounded in the W3C PROV data model for provenance, and we show how DTs can be used to automatically propagate a fraction of the credit associated with transitively derived datasets, back to original data contributors. We also show this model of transitive credit in action by means of a Data Reuse Simulator. In the longer term, our ultimate hope is that credit models based on direct measures of data reuse will provide further incentives to data publication. We conclude by outlining a research agenda to address the hard questions of creating, collecting, and using DTs systematically across a large number of data reuse instances in the wild.", "publicationTitle": "", "publisher": "", "place": "", "date": "2016-09-29", "volume": "11", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "1–16", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.2218/ijdc.v11i1.425", "citationKey": "", "url": "http://www.ijdc.net/index.php/ijdc/article/view/11.1.1", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1746-8256", "archive": "", "archiveLocation": "", "shortTitle": "Data trajectories", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "EUQWXNB2", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/EUQWXNB2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/EUQWXNB2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Ghavimi et al.", "parsedDate": "2016-03-05", "numChildren": 0 }, "data": { "key": "EUQWXNB2", "version": 3, "itemType": "journalArticle", "title": "Identifying and Improving Dataset References in Social Sciences Full Texts", "creators": [ { "creatorType": "author", "firstName": "Behnam", "lastName": "Ghavimi" }, { "creatorType": "author", "firstName": "Philipp", "lastName": "Mayr" }, { "creatorType": "author", "firstName": "Sahar", "lastName": "Vahdati" }, { "creatorType": "author", "firstName": "Christoph", "lastName": "Lange" } ], "abstractNote": "Scientific full text papers are usually stored in separate places than their underlying research datasets. Authors typically make references to datasets by mentioning them for example by using their titles and the year of publication. However, in most cases explicit links that would provide readers with direct access to referenced datasets are missing. Manually detecting references to datasets in papers is time consuming and requires an expert in the domain of the paper. In order to make explicit all links to datasets in papers that have been published already, we suggest and evaluate a semi-automatic approach for finding references to datasets in social sciences papers. Our approach does not need a corpus of papers (no cold start problem) and it performs well on a small test corpus (gold standard). Our approach achieved an F-measure of 0.84 for identifying references in full texts and an F-measure of 0.83 for finding correct matches of detected references in the da\\textbarra dataset registry.", "publicationTitle": "", "publisher": "", "place": "", "date": "2016-03-05", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://arxiv.org/abs/1603.01774", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "arXiv: 1603.01774", "tags": [ { "tag": "Computer Science - Digital Libraries" }, { "tag": "Computer Science - Information Retrieval" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "2NVU365P", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/2NVU365P", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/2NVU365P", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Roche et al.", "parsedDate": "2015-11-10", "numChildren": 0 }, "data": { "key": "2NVU365P", "version": 3, "itemType": "journalArticle", "title": "Public Data Archiving in Ecology and Evolution: How Well Are We Doing?", "creators": [ { "creatorType": "author", "firstName": "Dominique G.", "lastName": "Roche" }, { "creatorType": "author", "firstName": "Loeske E. B.", "lastName": "Kruuk" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Lanfear" }, { "creatorType": "author", "firstName": "Sandra A.", "lastName": "Binning" } ], "abstractNote": "Careful scrutiny of one hundred studies in journals that mandate data archival reveals that over half do not comply with their journal’s data policy.", "publicationTitle": "", "publisher": "", "place": "", "date": "2015-11-10", "volume": "13", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "e1002295", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1371/journal.pbio.1002295", "citationKey": "", "url": "http://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.1002295", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1545-7885", "archive": "", "archiveLocation": "", "shortTitle": "Public Data Archiving in Ecology and Evolution", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Archives" }, { "tag": "Data processing" }, { "tag": "Evolutionary Biology" }, { "tag": "Evolutionary genetics" }, { "tag": "Public policy" }, { "tag": "data management" }, { "tag": "reproducibility" }, { "tag": "science policy" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "AW362CVN", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/AW362CVN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/AW362CVN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Robinson-García et al.", "parsedDate": "2015-06-01", "numChildren": 0 }, "data": { "key": "AW362CVN", "version": 3, "itemType": "journalArticle", "title": "Analyzing data citation practices using the data citation index", "creators": [ { "creatorType": "author", "firstName": "Nicolas", "lastName": "Robinson-García" }, { "creatorType": "author", "firstName": "Evaristo", "lastName": "Jiménez-Contreras" }, { "creatorType": "author", "firstName": "Daniel", "lastName": "Torres-Salinas" } ], "abstractNote": "We present an analysis of data citation practices based on the Data Citation Index (DCI) (Thomson Reuters). This database launched in 2012 links data sets and data studies with citations received from the other citation indexes. The DCI harvests citations to research data from papers indexed in the Web of Science. It relies on the information provided by the data repository. The findings of this study show that data citation practices are far from common in most research fields. Some differences have been reported on the way researchers cite data: Although in the areas of science and engineering & technology data sets were the most cited, in the social sciences and arts & humanities data studies play a greater role. A total of 88.1% of the records have received no citation, but some repositories show very low uncitedness rates. Although data citation practices are rare in most fields, they have expanded in disciplines such as crystallography and genomics. We conclude by emphasizing the role that the DCI could play in encouraging the consistent, standardized citation of research data—a role that would enhance their value as a means of following the research process from data collection to publication.", "publicationTitle": "", "publisher": "", "place": "", "date": "2015-06-01", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "n/a–n/a", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/asi.23529", "citationKey": "", "url": "http://onlinelibrary.wiley.com/doi/10.1002/asi.23529/abstract", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "2330-1643", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "scientometrics" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "ZAX5457K", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/ZAX5457K", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/ZAX5457K", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Belter", "parsedDate": "2014-03-26", "numChildren": 0 }, "data": { "key": "ZAX5457K", "version": 3, "itemType": "journalArticle", "title": "Measuring the Value of Research Data: A Citation Analysis of Oceanographic Data Sets", "creators": [ { "creatorType": "author", "firstName": "Christopher W.", "lastName": "Belter" } ], "abstractNote": "Evaluation of scientific research is becoming increasingly reliant on publication-based bibliometric indicators, which may result in the devaluation of other scientific activities - such as data curation – that do not necessarily result in the production of scientific publications. This issue may undermine the movement to openly share and cite data sets in scientific publications because researchers are unlikely to devote the effort necessary to curate their research data if they are unlikely to receive credit for doing so. This analysis attempts to demonstrate the bibliometric impact of properly curated and openly accessible data sets by attempting to generate citation counts for three data sets archived at the National Oceanographic Data Center. My findings suggest that all three data sets are highly cited, with estimated citation counts in most cases higher than 99% of all the journal articles published in Oceanography during the same years. I also find that methods of citing and referring to these data sets in scientific publications are highly inconsistent, despite the fact that a formal citation format is suggested for each data set. These findings have important implications for developing a data citation format, encouraging researchers to properly curate their research data, and evaluating the bibliometric impact of individuals and institutions.", "publicationTitle": "", "publisher": "", "place": "", "date": "2014-03-26", "volume": "9", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "e92590", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1371/journal.pone.0092590", "citationKey": "", "url": "http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0092590", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1932-6203", "archive": "", "archiveLocation": "", "shortTitle": "Measuring the Value of Research Data", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Database searching" }, { "tag": "Earth sciences" }, { "tag": "Marine ecology" }, { "tag": "Ocean temperature" }, { "tag": "Oceanography" }, { "tag": "bibliometrics" }, { "tag": "oceans" }, { "tag": "surface temperature" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "QFN33ZHV", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/QFN33ZHV", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/QFN33ZHV", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Boland et al.", "parsedDate": "2012-09-23", "numChildren": 0 }, "data": { "key": "QFN33ZHV", "version": 3, "itemType": "bookSection", "title": "Identifying References to Datasets in Publications", "creators": [ { "creatorType": "author", "firstName": "Katarina", "lastName": "Boland" }, { "creatorType": "author", "firstName": "Dominique", "lastName": "Ritze" }, { "creatorType": "author", "firstName": "Kai", "lastName": "Eckert" }, { "creatorType": "author", "firstName": "Brigitte", "lastName": "Mathiak" }, { "creatorType": "editor", "firstName": "Panayiotis", "lastName": "Zaphiris" }, { "creatorType": "editor", "firstName": "George", "lastName": "Buchanan" }, { "creatorType": "editor", "firstName": "Edie", "lastName": "Rasmussen" }, { "creatorType": "editor", "firstName": "Fernando", "lastName": "Loizides" } ], "abstractNote": "Research data and publications are usually stored in separate and structurally distinct information systems. Often, links between these resources are not explicitly available which complicates the search for previous research. In this paper, we propose a pattern induction method for the detection of study references in full texts. Since these references are not specified in a standardized way and may occur inside a variety of different contexts – i.e., captions, footnotes, or continuous text – our algorithm is required to induce very flexible patterns. To overcome the sparse distribution of training instances, we induce patterns iteratively using a bootstrapping approach. We show that our method achieves promising results for the automatic identification of data references and is a first step towards building an integrated information system.", "bookTitle": "Theory and Practice of Digital Libraries", "series": "Lecture Notes in Computer Science", "seriesNumber": "7489", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2012-09-23", "publisher": "Springer Berlin Heidelberg", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "150–161", "ISBN": "978-3-642-33289-0 978-3-642-33290-6", "DOI": "", "citationKey": "", "url": "http://link.springer.com/chapter/10.1007/978-3-642-33290-6_17", "accessDate": "2016-10-10", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "DOI: 10.1007/978-3-642-33290-6_17", "tags": [ { "tag": "Bootstrapping" }, { "tag": "Data Mining and Knowledge Discovery" }, { "tag": "Document Preparation and Text Processing" }, { "tag": "Information Systems Applications (incl. Internet)" }, { "tag": "Information storage and retrieval" }, { "tag": "Iterative Pattern Induction" }, { "tag": "Multimedia Information Systems" }, { "tag": "Recognition of Dataset References" }, { "tag": "database management" }, { "tag": "digital libraries" }, { "tag": "information extraction" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "ZJJ7FX27", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/ZJJ7FX27", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/ZJJ7FX27", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Seeber", "parsedDate": "2008-02-21", "numChildren": 0 }, "data": { "key": "ZJJ7FX27", "version": 3, "itemType": "journalArticle", "title": "Citations in supplementary information are invisible", "creators": [ { "creatorType": "author", "firstName": "Frank", "lastName": "Seeber" } ], "abstractNote": "Nature is the international weekly journal of science: a magazine style journal that publishes full-length research papers in all disciplines of science, as well as News and Views, reviews, news, features, commentaries, web focuses and more, covering all branches of science and how science impacts upon all aspects of society and life.", "publicationTitle": "", "publisher": "", "place": "", "date": "2008-02-21", "volume": "451", "issue": "7181", "section": "", "partNumber": "", "partTitle": "", "pages": "887–887", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1038/451887d", "citationKey": "", "url": "http://www.nature.com/nature/journal/v451/n7181/full/451887d.html", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "0028-0836", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "PU2THKDS", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/PU2THKDS", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/PU2THKDS", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "PU2THKDS", "version": 3, "itemType": "webpage", "title": "Measuring and Anticipating the Impact of Data Reuse.", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "https://deepblue.lib.umich.edu/handle/2027.42/102481", "accessDate": "2016-10-10", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "I8R78DUX", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/I8R78DUX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/I8R78DUX", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "I8R78DUX", "version": 3, "itemType": "webpage", "title": "Measuring and Anticipating the Impact of Data Reuse.", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "https://deepblue.lib.umich.edu/handle/2027.42/102481", "accessDate": "2016-10-10", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "E5R5NCNC", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/E5R5NCNC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/E5R5NCNC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Peters et al.", "parsedDate": "2016-02-15", "numChildren": 0 }, "data": { "key": "E5R5NCNC", "version": 3, "itemType": "journalArticle", "title": "Research data explored: an extended analysis of citations and altmetrics", "creators": [ { "creatorType": "author", "firstName": "Isabella", "lastName": "Peters" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Kraker" }, { "creatorType": "author", "firstName": "Elisabeth", "lastName": "Lex" }, { "creatorType": "author", "firstName": "Christian", "lastName": "Gumpenberger" }, { "creatorType": "author", "firstName": "Juan", "lastName": "Gorraiz" } ], "abstractNote": "In this study, we explore the citedness of research data, its distribution over time and its relation to the availability of a digital object identifier (DOI) in the Thomson Reuters database Data Citation Index (DCI). We investigate if cited research data “impacts” the (social) web, reflected by altmetrics scores, and if there is any relationship between the number of citations and the sum of altmetrics scores from various social media platforms. Three tools are used to collect altmetrics scores, namely PlumX, ImpactStory, and Altmetric.com, and the corresponding results are compared. We found that out of the three altmetrics tools, PlumX has the best coverage. Our experiments revealed that research data remain mostly uncited (about 85 %), although there has been an increase in citing data sets published since 2008. The percentage of the number of cited research data with a DOI in DCI has decreased in the last years. Only nine repositories are responsible for research data with DOIs and two or more citations. The number of cited research data with altmetrics “foot-prints” is even lower (4–9 %) but shows a higher coverage of research data from the last decade. In our study, we also found no correlation between the number of citations and the total number of altmetrics scores. Yet, certain data types (i.e. survey, aggregate data, and sequence data) are more often cited and also receive higher altmetrics scores. Additionally, we performed citation and altmetric analyses of all research data published between 2011 and 2013 in four different disciplines covered by the DCI. In general, these results correspond very well with the ones obtained for research data cited at least twice and also show low numbers in citations and in altmetrics. Finally, we observed that there are disciplinary differences in the availability and extent of altmetrics scores.", "publicationTitle": "", "publisher": "", "place": "", "date": "2016-02-15", "volume": "107", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "723–744", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1007/s11192-016-1887-4", "citationKey": "", "url": "http://link.springer.com/article/10.1007/s11192-016-1887-4", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "0138-9130, 1588-2861", "archive": "", "archiveLocation": "", "shortTitle": "Research data explored", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "U6SRD43I", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/U6SRD43I", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/U6SRD43I", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Gorraiz et al.", "parsedDate": "2016-02", "numChildren": 0 }, "data": { "key": "U6SRD43I", "version": 3, "itemType": "journalArticle", "title": "Availability of digital object identifiers (DOIs) in Web of Science and Scopus", "creators": [ { "creatorType": "author", "firstName": "Juan", "lastName": "Gorraiz" }, { "creatorType": "author", "firstName": "David", "lastName": "Melero-Fuentes" }, { "creatorType": "author", "firstName": "Christian", "lastName": "Gumpenberger" }, { "creatorType": "author", "firstName": "Juan-Carlos", "lastName": "Valderrama-Zurián" } ], "abstractNote": "This study aims to shed light on the implementation of the digital object identifier (DOI) in the two most important multidisciplinary databases, namely Web of Science Core Collection and Scopus, within the last decade (2005–2014). The results show a generally increased percentage of items with DOI in all the disciplines in both databases, which provide very similar numbers and trends. While the percentage of citable items with a DOI has already reached 90% in the Sciences and the Social Sciences in 2014, it has remained much lower in the Arts & Humanities, exceeding 50% only since 2013. The observed values for Books and Proceedings are even lower despite the importance of these document types, particularly for the Social Sciences and the Arts & Humanities. The fact that there are still journals with a large number of items still lacking DOIs in 2014 should be alarming for the corresponding editors and should give them reason to enhance the formal quality and visibility of their journals. Finally, scientists are also encouraged to review their publication strategies and to favour publication channels with established DOI assignments.", "publicationTitle": "", "publisher": "", "place": "", "date": "2016-02", "volume": "10", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "98–109", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1016/j.joi.2015.11.008", "citationKey": "", "url": "http://www.sciencedirect.com/science/article/pii/S1751157715301176", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1751-1577", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Altmetrics" }, { "tag": "Citation databases" }, { "tag": "DOI" }, { "tag": "Visibility" }, { "tag": "Web of Science Core Collection" }, { "tag": "scopus" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "EAG9KHVZ", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/EAG9KHVZ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/EAG9KHVZ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Zhang et al.", "parsedDate": "2016", "numChildren": 1 }, "data": { "key": "EAG9KHVZ", "version": 3, "itemType": "journalArticle", "title": "A Bootstrapping-based Method to Automatically Identify Data-usage Statements in Publications", "creators": [ { "creatorType": "author", "firstName": "Qiuzi", "lastName": "Zhang" }, { "creatorType": "author", "firstName": "Qikai", "lastName": "Cheng" }, { "creatorType": "author", "firstName": "Yong", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Wei", "lastName": "Lu" } ], "abstractNote": "", "publicationTitle": "", "publisher": "", "place": "", "date": "2016", "volume": "1", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "69–85", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.20309/jdis.201606", "citationKey": "", "url": "http://dx.doi.org/10.20309/jdis.201606", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1674-3393", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "data-sharing" }, { "tag": "machine-learning" }, { "tag": "natural-language-processing" }, { "tag": "publication" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "6974P2FR", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/6974P2FR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/6974P2FR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Kafkas et al.", "parsedDate": "2013-05-29", "numChildren": 0 }, "data": { "key": "6974P2FR", "version": 3, "itemType": "journalArticle", "title": "Database Citation in Full Text Biomedical Articles", "creators": [ { "creatorType": "author", "firstName": "Şenay", "lastName": "Kafkas" }, { "creatorType": "author", "firstName": "Jee-Hyub", "lastName": "Kim" }, { "creatorType": "author", "firstName": "Johanna R.", "lastName": "McEntyre" } ], "abstractNote": "Molecular biology and literature databases represent essential infrastructure for life science research. Effective integration of these data resources requires that there are structured cross-references at the level of individual articles and biological records. Here, we describe the current patterns of how database entries are cited in research articles, based on analysis of the full text Open Access articles available from Europe PMC. Focusing on citation of entries in the European Nucleotide Archive (ENA), UniProt and Protein Data Bank, Europe (PDBe), we demonstrate that text mining doubles the number of structured annotations of database record citations supplied in journal articles by publishers. Many thousands of new literature-database relationships are found by text mining, since these relationships are also not present in the set of articles cited by database records. We recommend that structured annotation of database records in articles is extended to other databases, such as ArrayExpress and Pfam, entries from which are also cited widely in the literature. The very high precision and high-throughput of this text-mining pipeline makes this activity possible both accurately and at low cost, which will allow the development of new integrated data services.", "publicationTitle": "", "publisher": "", "place": "", "date": "2013-05-29", "volume": "8", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "e63184", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1371/journal.pone.0063184", "citationKey": "", "url": "http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0063184", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1932-6203", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Archives" }, { "tag": "Genomic databases" }, { "tag": "Open access" }, { "tag": "Protein structure databases" }, { "tag": "Proteomic databases" }, { "tag": "Sequence databases" }, { "tag": "biological databases" }, { "tag": "text mining" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "ZHH7ZWJA", "version": 3, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/ZHH7ZWJA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/ZHH7ZWJA", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Névéol et al.", "parsedDate": "2011-12-01", "numChildren": 0 }, "data": { "key": "ZHH7ZWJA", "version": 3, "itemType": "journalArticle", "title": "Extraction of data deposition statements from the literature: a method for automatically tracking research results", "creators": [ { "creatorType": "author", "firstName": "Aurélie", "lastName": "Névéol" }, { "creatorType": "author", "firstName": "W. John", "lastName": "Wilbur" }, { "creatorType": "author", "firstName": "Zhiyong", "lastName": "Lu" } ], "abstractNote": "Motivation: Research in the biomedical domain can have a major impact through open sharing of the data produced. For this reason, it is important to be able to identify instances of data production and deposition for potential re-use. Herein, we report on the automatic identification of data deposition statements in research articles., Results: We apply machine learning algorithms to sentences extracted from full-text articles in PubMed Central in order to automatically determine whether a given article contains a data deposition statement, and retrieve the specific statements. With an Support Vector Machine classifier using conditional random field determined deposition features, articles containing deposition statements are correctly identified with 81% F-measure. An error analysis shows that almost half of the articles classified as containing a deposition statement by our method but not by the gold standard do indeed contain a deposition statement. In addition, our system was used to process articles in PubMed Central, predicting that a total of 52 932 articles report data deposition, many of which are not currently included in the Secondary Source Identifier [si] field for MEDLINE citations., Availability: All annotated datasets described in this study are freely available from the NLM/NCBI website at http://www.ncbi.nlm.nih.gov/CBBresearch/Fellows/Neveol/DepositionDataSets.zip, Contact: aurelie.neveol@nih.gov; john.wilbur@nih.gov; zhiyong.lu@nih.gov, Supplementary Information: Supplementary data are available at Bioinformatics online.", "publicationTitle": "", "publisher": "", "place": "", "date": "2011-12-01", "volume": "27", "issue": "23", "section": "", "partNumber": "", "partTitle": "", "pages": "3306–3312", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1093/bioinformatics/btr573", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3223368/", "accessDate": "2016-10-10", "PMID": "", "PMCID": "", "ISSN": "1367-4803", "archive": "", "archiveLocation": "", "shortTitle": "Extraction of data deposition statements from the literature", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "PMID: 21998156\nPMCID: PMC3223368", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:10:47Z", "dateModified": "2016-10-10T23:10:47Z" } }, { "key": "DAIX7XM9", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/DAIX7XM9", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/DAIX7XM9", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Piwowar and Chapman", "parsedDate": "2008-12", "numChildren": 0 }, "data": { "key": "DAIX7XM9", "version": 2, "itemType": "conferencePaper", "title": "Linking database submissions to primary citations with PubMed Central", "creators": [ { "creatorType": "author", "firstName": "Heather A", "lastName": "Piwowar" }, { "creatorType": "author", "firstName": "Wendy W", "lastName": "Chapman" } ], "abstractNote": "Background: Dataset submissions are growingexponentially. Links between datasetsubmissions and primary literature that describethe data collection are useful for many reasons:rich documentation, proper attribution, improvedinformation retrieval, and enhanced text/dataintegration for analysis. Unfortunately, manydatabase submissions do not include primarycitation links, as database submissions are oftenmade prior to publication. We suggest thatautomated tools can be developed to helpidentify links between dataset submissions andthe primary literature. These tools require fulltext to differentiate cases of data sharing fromdata reuse and other contexts. In this study, weexplore the possibility that deep analysis of fulltext may not be necessary, thereby enabling thequerying of all reports in PubMed Central.Methods: We trained machine learning treeand rule-based classifiers on full-text openaccessarticle unigram vectors, with theexistence of a primary citation link from NCBI'sGene Expression Omnibus (GEO) databasesubmission records as the binary output class.We manually combined and simplified theclassifier trees and rules to create a querycompatible with the interface for PubMedCentral.Results: The query identified 40% of non-OAarticles with dataset submission links from GEO(recall), and 65% of the returned articles withoutdataset submission links were manually judgedto include statements of dataset deposit despitehaving no link from the database (applicableprecision).Conclusion: We hope this work inspires futureenhancements, and highlights the opportunitiesfor simple full-text queries in PubMed Centralgiven the mandated influx of NIH-fundedresearch reports.", "proceedingsTitle": "BioLINK Workshop at ISMB", "conferenceName": "", "publisher": "", "place": "", "date": "December 2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "4", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "B7EHTQM4", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/B7EHTQM4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/B7EHTQM4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Fitzgerald et al.", "numChildren": 0 }, "data": { "key": "B7EHTQM4", "version": 2, "itemType": "journalArticle", "title": "Building the Infrastructure for Data Access and Reuse in Collaborative Research", "creators": [ { "creatorType": "author", "firstName": "Anne", "lastName": "Fitzgerald" }, { "creatorType": "author", "firstName": "Kylie", "lastName": "Pappalardo" }, { "creatorType": "author", "firstName": "Brian F", "lastName": "Fitzgerald" }, { "creatorType": "author", "firstName": "Anthony", "lastName": "Austin" }, { "creatorType": "author", "firstName": "O A K Law", "lastName": "Project" }, { "creatorType": "author", "firstName": "Legal Framework", "lastName": "for E-Research Project" }, { "creatorType": "author", "firstName": "Australia Dept.", "lastName": "of Education" }, { "creatorType": "author", "name": "Science" }, { "creatorType": "author", "firstName": "and", "lastName": "Training" }, { "creatorType": "author", "firstName": "Science Dept.", "lastName": "of Education" }, { "creatorType": "author", "firstName": "Bill", "lastName": "Singleton" } ], "abstractNote": "\"Funded by the Australian Government Department of Education Science and Training (DEST).\"", "publicationTitle": "", "publisher": "", "place": "", "date": "", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://books.google.com/books?id=t57xHgAACAAJ", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "data-citation" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "UN5NNWCT", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/UN5NNWCT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/UN5NNWCT", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Anwar and Hunt", "parsedDate": "2009-01", "numChildren": 0 }, "data": { "key": "UN5NNWCT", "version": 2, "itemType": "journalArticle", "title": "Improved data retrieval from TreeBASE via taxonomic and linguistic data enrichment.", "creators": [ { "creatorType": "author", "firstName": "Nadia", "lastName": "Anwar" }, { "creatorType": "author", "firstName": "Ela", "lastName": "Hunt" } ], "abstractNote": "BACKGROUND: TreeBASE, the only data repository for phylogenetic studies, is not being used effectively since it does not meet the taxonomic data retrieval requirements of the systematics community. We show, through an examination of the queries performed on TreeBASE, that data retrieval using taxon names is unsatisfactory. RESULTS: We report on a new wrapper supporting taxon queries on TreeBASE by utilising a Taxonomy and Classification Database (TCl-Db) we created. TCl-Db holds merged and consolidated taxonomic names from multiple data sources and can be used to translate hierarchical, vernacular and synonym queries into specific query terms in TreeBASE. The query expansion supported by TCl-Db shows very significant information retrieval quality improvement. The wrapper can be accessed at the URL http://spira.zoology.gla.ac.uk/app/tbasewrapper.phpThe methodology we developed is scalable and can be applied to new data, as those become available in the future. CONCLUSION: Significantly improved data retrieval quality is shown for all queries, and additional flexibility is achieved via user-driven taxonomy selection.", "publicationTitle": "BMC evolutionary biology", "publisher": "", "place": "", "date": "January 2009", "volume": "9", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "93", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.ncbi.nlm.nih.gov/pubmed/19426482", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "4K4DEFR2", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/4K4DEFR2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/4K4DEFR2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Bollier", "parsedDate": "2009-12", "numChildren": 0 }, "data": { "key": "4K4DEFR2", "version": 2, "itemType": "journalArticle", "title": "The Promise and Peril of Big Data", "creators": [ { "creatorType": "author", "firstName": "David", "lastName": "Bollier" } ], "abstractNote": "", "publicationTitle": "", "publisher": "", "place": "", "date": "December 2009", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "1–66", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "JSPK42ZD", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/JSPK42ZD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/JSPK42ZD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Bradley et al.", "parsedDate": "2009", "numChildren": 0 }, "data": { "key": "JSPK42ZD", "version": 2, "itemType": "journalArticle", "title": "The Spectral Game: leveraging Open Data and crowdsourcing for education", "creators": [ { "creatorType": "author", "firstName": "Jean-Claude", "lastName": "Bradley" }, { "creatorType": "author", "firstName": "Robert J", "lastName": "Lancashire" }, { "creatorType": "author", "firstName": "Andrew Sid", "lastName": "Lang" }, { "creatorType": "author", "firstName": "Antony J", "lastName": "Williams" } ], "abstractNote": "We report on the implementation of the Spectral Game, a web-based game where players try to match molecules to various forms of interactive spectra including 1D/2D NMR, Mass Spectrometry and Infrared spectra. Each correct selection earns the player one point and play continues until the player supplies an incorrect answer. The game is usually played using a web browser interface, although a version has been developed in the virtual 3D environment of Second Life. Spectra uploaded as Open Data to ChemSpider in JCAMP-DX format are used for the problem sets together with structures extracted from the website. The spectra are displayed using JSpecView, an Open Source spectrum viewing applet which affords zooming and integration. The application of the game to the teaching of proton NMR spectroscopy in an undergraduate organic chemistry class and a 2D Spectrum Viewer are also presented.", "publicationTitle": "Journal of Cheminformatics", "publisher": "", "place": "", "date": "2009", "volume": "1", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "9", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.jcheminf.com/content/1/1/9", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "DJ4WTTKG", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/DJ4WTTKG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/DJ4WTTKG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Chen et al.", "parsedDate": "2007-10", "numChildren": 0 }, "data": { "key": "DJ4WTTKG", "version": 2, "itemType": "journalArticle", "title": "AILUN: reannotating gene expression data automatically", "creators": [ { "creatorType": "author", "firstName": "Rong", "lastName": "Chen" }, { "creatorType": "author", "firstName": "Li", "lastName": "Li" }, { "creatorType": "author", "firstName": "Atul J", "lastName": "Butte" } ], "abstractNote": "", "publicationTitle": "Nature Methods", "publisher": "", "place": "", "date": "October 2007", "volume": "4", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "879", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.nature.com/doifinder/10.1038/nmeth1107-879", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Algorithms" }, { "tag": "Animals" }, { "tag": "Automatic Data Processing" }, { "tag": "Computational Biology" }, { "tag": "Databases: Genetic" }, { "tag": "Gene Expression Profiling" }, { "tag": "Internet" }, { "tag": "Oligonucleotide Array Sequence Analysis" }, { "tag": "Saccharomyces cerevisiae" }, { "tag": "arabidopsis" }, { "tag": "drosophila" }, { "tag": "humans" }, { "tag": "mice" }, { "tag": "rats" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "MMACRUCQ", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/MMACRUCQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/MMACRUCQ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Downs and Marshall", "parsedDate": "2010", "numChildren": 0 }, "data": { "key": "MMACRUCQ", "version": 2, "itemType": "journalArticle", "title": "A PROPOSAL ON USING REUSE READINESS LEVELS TO MEASURE SOFTWARE REUSABILITY", "creators": [ { "creatorType": "author", "firstName": "Robert R", "lastName": "Downs" }, { "creatorType": "author", "firstName": "James J", "lastName": "Marshall" } ], "abstractNote": "", "publicationTitle": "Earth Science", "publisher": "", "place": "", "date": "2010", "volume": "", "issue": "July", "section": "", "partNumber": "", "partTitle": "", "pages": "1–20", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Scientific data" }, { "tag": "data reuse" }, { "tag": "reuse metrics" }, { "tag": "reuse readiness" }, { "tag": "software reuse" }, { "tag": "use cases" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "DZ4ASS22", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/DZ4ASS22", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/DZ4ASS22", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Piwowar et al.", "parsedDate": "2008-09", "numChildren": 0 }, "data": { "key": "DZ4ASS22", "version": 2, "itemType": "journalArticle", "title": "Towards a data sharing culture: recommendations for leadership from academic health centers", "creators": [ { "creatorType": "author", "firstName": "Heather A", "lastName": "Piwowar" }, { "creatorType": "author", "firstName": "Michael J", "lastName": "Becich" }, { "creatorType": "author", "firstName": "Howard", "lastName": "Bilofsky" }, { "creatorType": "author", "firstName": "Rebecca S", "lastName": "Crowley" } ], "abstractNote": "Recommendations for Academic Health Centers to Encourage Data Sharing 1. Commit to sharing research data as openly as possible, given privacy constraints. Streamline IRB, technology transfer, and information technology policies and procedures accordingly. 2. Recognize data sharing contributions in hiring and promotion decisions, perhaps as a bonus to a publication's impact factor. Use concrete metrics when available. 3. Educate trainees and current investigators on responsible data sharing and reuse practices through class work, mentorship, and professional development. Promote a framework for deciding upon appropriate data sharing mechanisms. 4. Encourage data sharing practices as part of publication policies. Lobby for explicit and enforceable policies in journal and conference instructions, to both authors and peer reviewers. 5. Encourage data sharing plans as part of funding policies. Lobby for appropriate data sharing requirements by funders, and recommend that they assess a proposal's data sharing plan as part of its scientific contribution. 6. Fund the costs of data sharing, support for repositories, adoption of sharing infrastructure and metrics, and research into best practices through federal grants and AHC funds. 7. Publish experiences in data sharing to facilitate the exchange of best practices.", "publicationTitle": "PLoS Medicine", "publisher": "", "place": "", "date": "September 2008", "volume": "5", "issue": "9", "section": "", "partNumber": "", "partTitle": "", "pages": "e183", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://www.plosmedicine.org/article/info:doi/10.1371/journal.pmed.0050183", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Academic Medical Centers" }, { "tag": "Health Planning Guidelines" }, { "tag": "Leadership" }, { "tag": "Research Design" }, { "tag": "humans" } ], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } }, { "key": "777897B3", "version": 2, "library": { "type": "group", "id": 748484, "name": "UW-ReuseAndCitation", "links": { "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/748484/items/777897B3", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/uw-reuseandcitation/items/777897B3", "type": "text/html" } }, "meta": { "createdByUser": { "id": 3105710, "username": "nmweber", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/nmweber", "type": "text/html" } } }, "creatorSummary": "Piwowar", "parsedDate": "2008-12", "numChildren": 0 }, "data": { "key": "777897B3", "version": 2, "itemType": "conferencePaper", "title": "Proposed Foundations for Evaluating Data Sharing and Reuse in the Biomedical Literature", "creators": [ { "creatorType": "author", "firstName": "Heather A", "lastName": "Piwowar" } ], "abstractNote": "", "proceedingsTitle": "JCDL 2008", "conferenceName": "", "publisher": "", "place": "", "date": "December 2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "6", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-10-10T23:06:13Z", "dateModified": "2016-10-10T23:06:13Z" } } ]