Advanced Social Data Science II

Course content

The wealth of new data in the digital society is characterized by high frequency observations in a high granularity setting, allowing for both comprehensive and detailed analysis of social and individual behaviour. Text data such as comments and conversations on social media have the potential to provide thick descriptions of social interactions and individual values in large-scale, sometimes population level, settings. Digitalization of large corpuses of legal, administrative and political texts allows for dynamic analysis of evolving social ideas and issues. Most digital data do not arrive in simple accessible, quantifiable and comparable forms, but as text, sound and pictures. Advanced Social Data Science II focuses on unstructured data and methods for processing, transforming and dealing with complex and high dimensional text data. The course presents classic text data methods for characterizing and developing typologies and categories of individual and social behaviour, networks and ideas. Furthermore, it introduces stateof-the-art methods for classifying complex unstructured text data, and relates such data-driven methods to existing theoretical methods and models in the social sciences. Coding in the course is in Python, and the course requires familiarity with Python.

Education

Full-degree students enrolled at the Faculty of Social Science, UCPH 

  • MSc in Security Risk Management
  • Master Programme in Social Data Science
  • Master Programmes in Sociology
  • Master programme in Political Science and Social Science
  • Master Programmes in Economics

 

Mandatory course on MSc programme in Social Data Science at University of Copenhagen. 

Learning outcome

After completing the course, the student is expected to be able to:

 

Knowledge:

  •  Understand key concepts in traditional bag-of-words approaches to text data and how they relate to embeddings- and transformer-based approaches.
  • Explain the differences between and capabilities of neural network architectures such as RNN, LSTM and attentions-based models.
  • Account for various learning strategies, algorithms as well as approaches: clustering and unsupervised learning, supervised learning, semi-supervised learning, and transfer learning.
  • Account for the potential of different representations, encodings and transformations of text, structured and unstructured.

 

Skills:

  • Apply and justify preprocessing methods for text data.
  • Extract reliable informations from text data using supervised and unsupervised learning and techniques from natural language processing.
  • Use scikit-learn and PyTorch to apply basic and advanced machine learning models.
  • Apply state-of-the-art deep transfer learning to classify unstructured data.

 

Competences:

  • Integrate theoretical and applied knowledge within the field of Social Data Science and formulate compelling research questions given an unstructured dataset.
  • Construct data sets from unstructured text and media data that are validated and well documented.
  • Independently carry out a problem-driven end-to-end analysis given an unstructured dataset of text, including exploratory analysis and discovery using unsupervised methods and supervised learning for measurement, and assessment of model-based biases.
  • Critically evaluate the implications of results, considering model limitations and biases, and systematic noise introduced by data collection and sampling methods.

This class will be taught using a combination of lectures and hands-on lab exercises working with problem sets.

Examples of course readings:

 

  • Bishop, Christopher: *Pattern Recognition and Machine Learning*. Spring Publishing, 2006.
  • Cantu, Francisco & Michelle Torres: "Learning to See: Visual Analysis for Social Science Data".
  • Gentzkow, M., Kelly, B. T., & Taddy, M. Text as Data. *Journal of Economic Literature*.
  • Grimmer, J., & Stew art, B. M. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. *Political Analysis*, 21(3), 267-297.
  • Hastie, T., & Tibshirani, R. & Friedman, J.(2008). *The Elements of Statistical Learning; Data Mining, Inference and Prediction*.
  • Hovy, D. *Text Analysis in Python for Social Scientists.*
  • Jurafsky, Dan, and James H. Martin. *Speech and language processing*. Vol. 3. London: Pearson, 2014.
  • Krippendorff, Klaus. Content analysis: An introduction to its methodology. Sage publications, 2018.
Oral
Peer feedback (Students give each other feedback)
ECTS
7,5 ECTS
Type of assessment
Home assignment, 72 hours
Type of assessment details
72-hour written take home exam. The exam can be written individually or in groups of 2-4 students.
Aid
All aids allowed

ChatGPT and other large language model tools are permitted as a dedicated source, meaning text copied verbatim needs to be quoted, the tool cited, and generally the specific use made of them needs to be described in the submitted exam.

Marking scale
7-point grading scale
Censorship form
No external censorship
Exam period

Exam information:

The examination date can be found in the exam schedule    here

The exact time and place will be available in Digital Exam from the middle of the semester. 

Re-exam

An essay, written either in a group, or individually, on a subject pertaining to the course content and prescribed literature. The subject must be pre-approved by the course lecturer(s)

 

Reexam info:

The reexamination date/period can be found in the reexam schedule    here

Criteria for exam assessment

Students are assessed on the extent to which they master the learning outcome for the course.

 

To obtain the top grade “12”, the student must with no or only a few minor weaknesses be able to demonstrate an excellent performance displaying a high level of command of all aspects of the relevant material and can make use of the knowledge, skills and competencies listed in the learning outcomes.

 

To obtain the passing grade “02”, the student must in a satisfactory way be able to demonstrate a minimal acceptable level of the knowledge, skills and competencies listed in the learning outcomes.

  • Category
  • Hours
  • Lectures
  • 28
  • Class Instruction
  • 42
  • Preparation
  • 112
  • Exam
  • 24
  • English
  • 206

Kursusinformation

Language
English
Course number
ASDK20006U
ECTS
7,5 ECTS
Programme level
Full Degree Master
Duration

1 block

Placement
Block 4
Studyboard
Social Data Science
Contracting department
  • Social Data Science
  • Department of Political Science
  • Department of Sociology
  • Department of Economics
Contracting faculty
  • Faculty of Social Sciences
Course Coordinators
  • Frederik Georg Hjorth   (2-74764e7774813c79833c7279)
  • Clara Johan E Vandeweerdt   (17-6d766b7c6b38806b786e6f816f6f7c6e7e4a73707d38757f386e75)
Saved on the 01-05-2025

Are you BA- or KA-student?

Are you bachelor- or kandidat-student, then find the course in the course catalog for students:

Courseinformation of students