Mapping of ETDs in ProQuest Dissertations and Theses (PQDT) Global database (2014-2018)

Authors

  • Manika Lamba Department of Library and Information Science, University of Delhi
  • Margam Madhusudhan Department of Library and Information Science, University of Delhi

DOI:

https://doi.org/10.48798/cadernosbad.2034

Keywords:

Latent Dirichlet Allocation, Machine Learning, Text Analytics, Topic Modeling, Prediction Modeling

Abstract

The information explosion in the form of ETDs poses the challenge of management and extraction of appropriate knowledge for decision making by information practitioners. This study presents a solution to the problem by applying topic mining and prediction modeling to 441 full-text ETDs extracted from the PQDT Global database during 2014-2018 in the field of library science using the RapidMiner platform. This study was divided into three phases. In the first phase, metadata analysis of the ETDs retrieved from the database was performed to identify the association of various entities such as universities, departments, types of degrees, and geographical areas with the ETDs. In the second phase, 8 core topics namelychildren literature; academic library; information retrieval; archival science; user study; digital library; library leadership; and digital communication were determined using latent dirichlet allocation (LDA) and each ETD was then annotated with the modeled topic. Lastly, a prediction model using the Support Vector Machine (SVM) was created to classify the untagged ETDs going to be submitted in the database under the 8 modeled topics ( a to h ).

Downloads

Download data is not yet available.

Author Biographies

Manika Lamba, Department of Library and Information Science, University of Delhi

Manika is a Ph.D. Scholar at the Department of Library and Information Science, University of Delhi, India and did M.Phil .; and M.Li.Sc. from the same department. Further, she has completed M.Sc. Plant Biotechnology and B.Sc. (H) Biochemistry. She is an active reviewer for “Journal of International Medical Research” (Sage), “Information Discovery and Delivery” (Emerald); Hi-Tech Library (Emerald); Journal of Information Science (Sage); and “International Journal of Technology, Knowledge and Society” (Common Ground Research Networks) journals. She was Editor-at-Large for dh + lib for 3 weeks from August to September (an ACRL Digital Humanities Interest Group project).She was featured in “Information Professionals Share Their Top Tips for 2019” blog by Copyright Clearance Center
(http://www.copyright.com/blog/information-professionals-top-tips-2019/). Her research interests include Digital Humanities, Information Visualization, Data Analytics, Data Mining, Prediction Modeling, Marketing of Medical Libraries, Open Access, ETDs, Sentiment and Opinion Analysis. 

Margam Madhusudhan, Department of Library and Information Science, University of Delhi

Margam Madhusudhan is currently working as Associate Professor in the Department of Library and Information Science, University of Delhi. He has been awarded Highly Commended Paper by Emerald Literati Awards 2019, Excellence in Research in 2017, PV Verghese Award in 2013 and achieved status of IAO Certified Faculty Member (USA) in 2014. He has 20 years of teaching, administration and research experience at the University level. He has worked as Deputy Dean Academics (2013-2015) and Member of Academic Council (2012-2014) in the University of Delhi. Under his supervision 7 PhDs, 23 MPhils and 130+ Project reports have been awarded. He has published one book, edited three books, 80+ articles in International and National Journals, and 29 chapters in books. 
Atas do ETD 2019: Fruits of Knowledge

Downloads

Published

2020-03-31

How to Cite

Lamba, M., & Madhusudhan, M. (2020). Mapping of ETDs in ProQuest Dissertations and Theses (PQDT) Global database (2014-2018). Cadernos BAD, (1), 169–182. https://doi.org/10.48798/cadernosbad.2034

Issue

No. 1 (2019): ETD 2019: Fruits of Knowledge

Section

Comunicações

License

Os autores que publicam nos Cadernos BAD:

  1. Concedem à revista o direito de primeira publicação, mantendo os direitos de autor, de acordo com os termos da Creative Commons Attribution, que permite a partilha do texto com menção obrigatória da publicação inicial nos Cadernos BAD;

  2. Mantêm o direito de publicar o texto noutros locais (ex.: repositório institucional, capítulo de livro, outra publicação periódica), com menção da publicação inicial nos Cadernos BAD e uma ligação para o sítio na Internet da revista;
  3. Mantêm a possibilidade e são mesmo incentivados a publicar e distribuir o seu trabalho online (ex.: em repositórios institucionais ou na sua página pessoal) antes ou durante o processo editorial, já que isso pode potenciar interações geradoras de melhoria, bem como aumentar o impacto e a citação do texto publicado (Veja Efeitos do Acesso Livre).