Postgraduate Course: Text Mining for Social Research (fusion online) (EFIE11005)
|School||Edinburgh Futures Institute
||College||College of Arts, Humanities and Social Sciences
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
|Course type||Online Distance Learning
||Availability||Available to all students
|Summary||During this course you will learn from scratch the theory and practice of analysing text documents with code. The course is suitable for participants who have no prior experience of text analysis or programming in Python as well as those with some Python knowledge who want to learn how to apply their skills to social research topics. At the end of this course students will know the basics of the theory behind text mining and will have skills to prepare, search, analyse and create visualisations from text documents at scale. The contexts and examples we will use will be relevant to social research.
The Edinburgh Futures Institute will teach this course in a way that enables online and on-campus students to study together. This approach (our 'fusion' teaching model) offers students flexible and inclusive ways to study, and the ability to choose whether to be on-campus or online at the level of the individual course. It also opens up ways for diverse groups of students to study together regardless of geographical location. To enable this, the course will use technologies to record and live-stream student and staff participation during their teaching and learning activities. Students should note that their interactions may be recorded and live-streamed. There will, however, be options to control whether or not your video and audio are enabled.
This course is taught over an intensive 2-day block, with some structured activity before and after the intensive.
The practical parts of this course are taught in the programming language Python. Initially, the core basic Python skills are introduced and the students are taught how to set up their virtual programming environment. In the 2-day intensive part, participants will then learn how to read in textual files and carry out the initial processing required for text manipulation.
The course will also cover concordances, frequency distributions, lexical dispersions, collocations, part-of-speech tagging, named entity recognition, and network creation and draw on sample datasets relevant to social and political research. The course will also introduce the more complex analysis and visualisation techniques required to extract information from large text datasets.
The delivery will be a combination of short recorded lectures on the theory and motivation for the different ways of preparing, analysing and visualising text and coding exercises that will take students from acquiring content, through to practical skills and collaborating in manipulating data in group work between students in the classroom and online. Through worked examples, group exercises and a final project, learners will produce original pieces of work involving the practical skills they acquired.
As part of your course, you will need access to a personal computing device. Unless otherwise stated activities will be web browser based and as a minimum we recommend a device with a physical keyboard and screen that can access the internet.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2021/22, Available to all students (SV1)
|Course Start Date
|Learning and Teaching activities (Further Info)
Lecture Hours 5,
Seminar/Tutorial Hours 5,
Supervised Practical/Workshop/Studio Hours 5,
Formative Assessment Hours 1,
Summative Assessment Hours 1,
Other Study Hours 3,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
|Additional Information (Learning and Teaching)
3 hours scheduled group work
|Assessment (Further Info)
|Additional Information (Assessment)
Project + report (blog of 600 words and 2 visualisations, including a data analysis, providing a testable hypothesis and results)
||The course will have two formative assessments:
- Python fundamentals pre-course work
- Project idea proposal (1 min video). Students will receive feedback on this from peers and academic staff
In addition, students will receive the following feedback:
- Solutions to programming tasks will be provided
- In person coding feedback and at drop-in times (online or physical)
- Feedback by academic staff on the final submission
|No Exam Information
On completion of this course, the student will be able to:
- Demonstrate a critical understanding of the main areas of study linked to the use of technology in text and data mining.
- Explain and use key technologies and formats used in data analysis.
- Develop original and creative responses to data driven problems.
- Demonstrate their ability to deliver - in verbal and written form - coherent, balanced arguments surrounding the use of data.
- Work in a peer relationship and make an identifiable contribution to change and development and/or new thinking.
Ignatow, Gabe, and Rada Mihalcea. Text mining: A guidebook for the social sciences. Sage Publications, 2016. https://dx.doi.org/10.4135/9781483399782.n1
- Chapter 1: Social Science and the Digital Text Revolution (essential reading)
- Chapter 2: Research Design Strategies, Levels of Analysis, p. 18 (recommended reading)
- Chapter 5: Basic Text Processing (recommended reading)
- Chapter 7: Text Analysis Methods from the Humanities and Social Sciences, Visualisations Tools, pp. 83-86 (recommended reading)
- Chapter 12: Information Extraction, Entity Extraction, p. 130 (recommended reading)
Lacey, Nichola. Python by Example: Learning to Program in 150 Challenges. Cambridge University Press, 2019. https://doi-org.ezproxy.is.ed.ac.uk/10.1017/9781108591942 (further reading)
Bird, Steven, Ewan Klein, and Edward Loper. Natural language processing with Python: analyzing text with the natural language toolkit. "O'Reilly Media, Inc.", 2009. https://www.nltk.org/book (further reading)
SpaCy API documentation, https://spacy.io/api (further reading)
|Graduate Attributes and Skills
||1. Students will develop key text and data mining knowledge and understanding through presentations, hands-on coding lessons and the production of research material via their project
2. Students will practice the use of computational methods to analyse text collections as a technique to answer scholarly research questions
3. Students will gain cognitive skills by conducting original research using text-driven analysis and making their own interpretations of the results in the context of world knowledge
4. Students will develop communication, ICT and numeracy skills by interacting with academic staff and their peers in different settings (physical and online), by learning to use different computational tools to support their course work and collaboration and by acquiring fundamental programming skills
5. Students will gain autonomy, accountability and learn to work with others by collaborating in small groups on the practical elements of the course and during the preparation stage of their project, developing their communication skills, and gaining valuable skills in working with others
|Keywords||text and data mining,natural language processing,social research,programming
|Course organiser||Dr Beatrice Alex
Tel: (0131 6)50 2684
|Course secretary||Miss Katie Murray