Logo image
Back
Quick Understanding Our Engineering Faculty Research Needs Using Topic Modeling
Conference proceeding   Open access

Quick Understanding Our Engineering Faculty Research Needs Using Topic Modeling

Qianjin Zhang and Kari Kozak
2019 ASEE Annual Conference & Exposition
ASEE Annual Conference & Exposition (Tampa, Florida, 06/15/2019–06/19/2019)
06/15/2019
DOI: 10.18260/1-2--33223
url
https://doi.org/10.18260/1-2--33223View
Published (Version of record) Open Access

Abstract

As engineering librarians, we recognize that understanding our faculty research needs is an ongoing endeavor. It that is a repeated continuing learning process throughout our time serving engineering faculty with diverse research interests. However, the time-intensive learning process may not efficiently help engineering librarians quickly develop an overall view of the changing and evolving various departments. It’s also challenging for early-career librarians who are new to engineering librarianship or do not have relevant subject background. In order to tackle the problem, we the authors explored research topics of our faculty’s work using a topic modeling technique called Latent Dirichlet Allocation (LDA) which is a type of statistical topic model and a machine learning algorithm for discovering the research topics from text data. We retrieved thousands of bibliographic records of faculty publications as the text data, especially for the title, abstract and keywords, from Web of Science, removed duplicates and cleaned up the data. Next, we fed the data into the machine, built LDA models and generated research topics from the data. As a result, we determined the optimal research topic number of 25 and interpreted the research topics based on the visualization of the LDA results. In conclusion, our experiment with the LDA approach not only helped us quickly develop an understanding of faculty research needs,, but also would would provide good evidence from which to make decisions on collection management, reference and library instruction,. and showed the possibility of academic libraries to make use of data and data science techniques in the era of big data.
 Engineering Algorithms Machine Learning Data Mining Learning User training Collection management Dirichlet problem Libraries Modelling Librarians

Details

Metrics

98 Record Views
Logo image