pollysfreedomblog

Home » Data and Text mining

Category Archives: Data and Text mining

Open Access and Research Data management: Horizon 2020 and Beyond in Ireland

In April of this year University College Cork (UCC) hosted a 2-day training event focusing on Open Access Data in Horizon 2020. The event was sponsored by FOSTER and organized jointly by UCC Boole Library and Repository Network Ireland.

Day one was aimed at researchers and others who were interested in developing Horizon 2020 proposals.

The two day event was a great success, introducing some people to the concept of Open Access and Open Data while also providing plenty of food for thought for those of us involved in the support of researchers and management of services and infrastructure.

All presentations can be found on the FOSTER website on the event page.

Read more…

Advertisements

Libraries and Digital Humanities

Librarians will be familiar with some of the challenges facing digital humanities researchers. The metadata within the datasets is often incomplete and inconsistent. Rough OCR and non-standard spelling make analyzing datasets difficult. And, humanists are not traditionally trained in computer programming so they have a lot to learn when undertaking a digital project.

Libraries are taking on the challenge of digital humanities along with scholars. Librarians are filling new roles as data librarians. Libraries are offering a variety of services including storage and preservation of data, tools for creating digital projects, and expertise in analytical research methods. As digital humanities continues to emerge we are sure to see libraries developing more innovative services for students and researchers. This active engagement ensures librarians will have an important role in supporting digital humanities.

Read more…

Text & Data Mining

According to Maurizio Borghi, on the site, Copyright User.com gives the following explanation for what is text & data mining.

“The electronic analysis of large amounts of copyright works allows researchers to discover patterns, trends and other useful information that cannot be detected through usual ‘human’ reading. This process, known as ‘text and data mining’, may lead to knowledge which can be found in the works being mined but not yet explicitly formulated. For example, the processing of data contained in a large collection of scientific papers in a particular medical field could suggest a possible association between a gene and a disease, or between a drug and an adverse event, without this connection being explicitly identified or mentioned in any of the papers.” Read more…

The Carnegie Mellon University Libraries on TDM – Read more…

Elsevier on what is TDM –  Read more…

CrossRef has pre-recorded webinars on TDM – Read more…

LIBER Europe on TDM – Read more…

Hague Declaration on TDM – Read more…

Wiley Online Library on TDM – Read more…

A Recent Webinar hosted by the Center for Research Libraries

Title: Text and Data Mining in the Humanities and Social Sciences: Strategies and Tools, presented by Peter Leonard and Lindsay King of Yale.

In the webinar Leonard and King discussed reasons for the current interest in TDM, what makes a good project, and the implications for libraries of this growing research trend. They also demonstrated Yale’s Robots Reading Vogue platform, showing various projects based on the ProQuest database. They responded to significant questions and observations from webinar participants, including how to get good quality OCR from non-western alphabets or earlier fonts, the relative quality of OCR from various news databases, and what tools to use for topic modeling.

The webinar is now available via the CRL’s YouTube channel.

%d bloggers like this: