iDM Online Workshop Series FY2022 #3
Text and Data Mining: Frontier and Tools
On October 18, iCeMS On-site laboratory, the Center for Integrated Data-Material Sciences (iDM) hosted its third online workshop. This workshop was held in response to the first two which were used as information gathering sessions soliciting diverse perspectives on how data science could be applied to materials science and also provided insight into knowledge and skill gaps. The workshop drew many students from New Zealand and outside of iCeMS. Dr Daniel Packwood, who co-directs the iDM with Prof Aiko Fukazawa, was excited to have so many young students in attendance and invited contact from those interested in exchange studies.
Previous workshops had illuminated how research groups were relying on laborious handwork to extract relevant information from the available literature. iDM brought in Axton Pitt, CEO and Co-founder of the New Zealand-based company Litmaps, for the day’s workshop to begin to answer the group’s questions around automation of these tasks. Litmaps is an online visual literature mapping tool designed to “accelerate the research process and improve the accessibility of knowledge.”
Pitt, in addition to presenting an introduction to Litmaps capabilities, explained his experience of the data-mining pipeline. He provided sources for massive, digitized research databases, and tools that can be used for data extraction. He discussed some of the current issues surrounding automated extraction of data from scientific literature and some of the barriers to being able to use the available tools. iDM organizers aim to address some of these barriers in future workshops by, for example, introducing Python programming which would enable researchers to customize some of the available tools.