Computational text data analysis using R, quanteda and tidytext

New Zealand eScience Infrastructure(NeSI) designs, builds, and operates a shared national platform of advanced computing resources and data services. All researchers in Aotearoa New Zealand have access to NeSI’s platforms. Through NeSI, researchers can access high-capacity CPUs, GPUs and high memory nodes; tailored software environments; expertise in research software and data science engineering; and skills training in computational  tools and approaches. NeSI enables researchers to investigate large, unique, or complex projects more easily, quickly, and accurately.  To learn more, get in touch: info@nesi.org.nz.

New Zealand eScience Infrastructure (NeSI)

<P><STRONG>2019 Science Coding Conference - Pre-conference Workshop </STRONG></P>
<P><BR></P>
<P><EM>Speaker / Session Lead:</EM> <BR>Arindam Basu, Senior Lecturer, College of Education, Health &amp; Human Development<BR>University of Canterbury</P>
<P><BR></P>
<DIV STYLE="font-family: -webkit-standard;">
<DIV STYLE="caret-color: #000000; font-family: -webkit-standard; text-size-adjust: auto;"><HR> </DIV>
<SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">Computational text data analysis is an exciting field of research not </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">only for digital humanities, but also for social and health scientists </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">in unraveling and articulating meanings embedded in written text either </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">in native text format or transcribed from audio and video interviews.</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">The free and open-source software R and associated packages tidytext and </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">quanteda make it possible to conduct this complex task based on a corpus </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">of text; however, many researchers find the task daunting as to how to </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">analyse a corpus of text to generate insights applying computational </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">thinking to the process.</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">The goal of this workshop will be to develop </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">computational thinking and enable researchers to use R and packages </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">tidytext and quanteda to conduct computational text analysis.</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"><BR></DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">We will use a specified corpus of text obtained from Project Gutenberg </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">texts, and we will use quanteda and tidytext packages to analyse the </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">corpus of the text. We will use a data carpentry approach and enable </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">practitioners (students, social scientists, and anyone interested in the </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">process) to conduct text data analysis.</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">We will use a hosted Jupyter </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">notebook instance and cover the following steps: </SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">(1) reading a corpus of </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">text </SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">(2) tokenise the text corpus</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">(3) applying dictionaries to </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">conduct sentiment analysis in the text </SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">(4) identify hidden </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">constructs using topic modelling.  </SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">In the workshop, we will use a data </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">carpentry approach using a modular approach to design the lessons, </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">sharing resources over the web, and in the session live coding each </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">step, obtaining frequent feedbacks from the participants using formative </SPAN><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">assessments in the session. </SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">In order to get the most out of this training, it is strongly recommended that you bring your own laptop to use during the session that can get connected to the Internet and has a modern web browser installed (eg. Chrome/Firefox/Safari).</SPAN></DIV>
<DIV STYLE="font-family: -webkit-standard;"> </DIV>
<DIV STYLE="font-family: -webkit-standard;"><SPAN STYLE="font-family: arial, helvetica, sans-serif; font-size: small;">This workshop is being hosted as a free event in the lead up to <A HREF="http://sciencecodingconference.nz/" TARGET="_blank" DATA-MSYS-CLICKTRACK="0" REL="nofollow noopener noreferrer">NeSI's Science Coding Conference</A>. If you are not sure if this workshop is for you or if you have any further questions, feel free to email Nooriyah at <A HREF="mailto:nooriyah.lohani@nesi.org.nz" REL="nofollow noopener noreferrer">nooriyah.lohani@nesi.org.nz</A>.  </SPAN></DIV>

Bentley room at UCSA Events Centre

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Computational text data analysis using R, quanteda and tidytext

More events from New Zealand eScience Infrastructure (NeSI)

Discover more events from New Zealand eScience Infrastructure (NeSI), from Science & Tech to other experiences you might love.

Computational text data analysis using R, quanteda and tidytext

More events from New Zealand eScience Infrastructure (NeSI)

Discover more events from New Zealand eScience Infrastructure (NeSI), from Science & Tech to other experiences you might love.

More Science & Tech events

Browse more Science & Tech events with different dates, prices, and formats to find your next great experience.