ContentMine is visiting Virginia Tech during their Open Data week for a 3 days stay. We will present our work in different formats and do a full-day workshop at the end.
- Date: 11th - 13th April 2017
- Location: Virginia Tech @ Blacksburg, Virginia, USA
- Facilitator:
- Stefan Kasberger (@stefankasberger)
- Tom Arrow
- Hashtag: #vtodw (Virginia Tech Open Data Week)
- Website
This work is licensed, unless otherwise stated, under a Creative Commons Attribution 4.0 International License.
| Timetable | Agenda |
|---|---|
| 11th April | Tuesday |
| 9:30 - 10:45 | Introduction to ContentMine Tools for Mining Scholarly & Research Literature 1 |
| 12:30 - 13:45 | Ed Fox Class 1 |
| 15:30 - 16:45 | Ed Fox Class 2 |
| 12th April | Wednesday |
| 9:00 - 9:55 | Introduction to ContentMine Tools for Mining Scholarly & Research Literature 2 |
| 11:15 - 12:05 | Introduction to ContentMine Tools for Life Sciences Research |
| 12:30 - 13:30 | Lunch with ContentMine guest speakers and program participants |
| 14:30 - 15:45 | Text and Data Mining Forum |
| 16:00 - 17:15 | Introduction to ContentMine Tools for Mining Scholarly & Research Literature 3 |
| 13th April | Thursday |
| 9:00 - 16:00 | ContentMine Tools to Explore Scholarly & Research Literature - Full Day, Hands-On Workshop |
In this approximately one hour long session, we will give an introduction into text and data mining and the ContentMine project. This includes the basic concept of TDM, legal issues, TDM with scholarly literature, use-cases and short demos about how we do it with our ContentMine toolchain. There will also be time for questions.
Occasions
- 11th of April - 9:30-10:45h
- 12th of April - 9:00-9:55h
- 12th of April - 16:00-17:15h
Resources
This introduction will focus a bit more on the technical aspects than the general introductory session. It is not publicly accessible, cause it is art of a course programm.
Occasions
- 11th of April - 12:30-13:45h
- 11th of April - 15:30-16:45h
This will be similiar to the Introduction to ContentMine Tools for Mining Scholarly & Research Literature session, but will focus on life sciences and the practical parts.
Occasion
- 12th of April - 11:15-12:05h
A discussion with researchers and Tom Arrow from ContentMine about opportunities and challenges related to text and data mining, with a focus on information access.
Participants
- Tom Arrow (ContentMine)
- Tom Ewing (College of Liberal Arts and Human Sciences, Virginia Tech)
- Weiguo (Patrick) Fan (Pampling College of Business, Virginia Tech)
- Ed Fox (Computer Science, Virginia Tech)
- Leanna House (Statistics, Virginia Tech)
- Bert Huang (Computer Science, Virginia Tech)
Occasion
- 12th of April - 14:30-15:45h
13th of April - 9-16h
The full-day workshop will be the final event, where the shown practices are finally applied. The first part will be a general introduction into text and data mining and our software. The second part will be hands-on, where every participant is able apply the ContentMine software for their own research and/or interest.
Requirements
To be able to participate during the workshop, you need a running installation of our ContentMine software. To reduce the risks of bandwith problems during download or installation errors, we recommend to install the software in advance and test it, if it is running.
- Install the needed ContentMine software. You have two options (we recommend the virtual machine image):
- install the Virtual Machine Image 2017/04, where all software is included. You can find more information how to setup the virtual machine here.
- install the software locally
- bring your laptop with power supply
Preparation
The following actions are not required but may help you to get the most out of the workshop. We especially recommend you to install the software in advance, so you can directly start or ask questions if you have issues with the installation process.
- pyCProject: if you want to analyse the mined facts in Python, you should install our Python wrapper for the CProject.
- do our software tutorials (optional): this helps you to get used to our tools and to get the most out of the workshop. The relevant ones are:
- getpapers
- norma
- ami
- Zika virus: this is our most recent tutorial, which focuses on TDM techniques around the Zika virus. It uses a Jupyter notebook for the analysis part.