Skip to main content

Study information

Machine learning for social data science

Module titleMachine learning for social data science
Module codeSSIM916
Academic year2023/4
Credits15
Module staff

Dr Travis Coan (Lecturer)

Duration: Term123
Duration: Weeks

11

Number students taking module (anticipated)

25

Module description

Effective analytics in the era of “big data” requires researchers to have a wide range of tools at their disposal. This module focuses a set of tools that are essential for applied and academic social data scientists: machine learning methods for structured and unstructured data. This module provides a practical introduction to the ways in which machine learning methods are applied regression problems, classification tasks, and unsupervised clustering of large datasets.

 

Although there are no formal pre-requisites for taking the module, some (even limited) programming experience will be helpful. You will use the Python programming language to implement most of the tools introduced throughout the term. No prior knowledge of Python is assumed. You are encouraged to reach out to module convener with questions regarding Python or programming more generally.

Module aims - intentions of the module

There are two primary aims of the module. First, the module will provide an applied introduction to the use of machine learning methods to help answer social science questions. You are introduced to how these tools are used to generate predictions for continuous outcomes (i.e., regression), classify categorical outcomes, and cluster information. We will compare machine learning-based solutions to these problems to more standard statistical approaches to identify the strengths and weaknesses of each approach. Second, the module introduces you to the Python programming language. Python is a popular language for scientific computing and knowledge of Python will place you at a competitive advantage in industry, government, or when pursing further education.

Intended Learning Outcomes (ILOs)

ILO: Module-specific skills

On successfully completing the module you will be able to...

  • 1. Understand and apply a variety of machine learning methods to answer questions in social science and public policy
  • 2. Critically evaluate the strengths and weaknesses of specific machine learning methods for answering research questions in the social sciences.

ILO: Discipline-specific skills

On successfully completing the module you will be able to...

  • 3. Employ text analytic methods to empirically evaluate theories and hypotheses in the social sciences.
  • 4. Demonstrate a strong command of research design and analysis through written assessments.

ILO: Personal and key skills

On successfully completing the module you will be able to...

  • 5. Gain a solid foundation in the Python programming language.
  • 6. Work independently and within a limited period to complete a specified task.

Syllabus plan

Although the module’s precise content may vary from year to year, it is envisaged that the syllabus will cover the following topics:

  • Machine learning methods for regression tasks
  • Supervised learning methods for classification
  • Performance metrics for regression and classification tasks
  • Unsupervised learning and clustering
  • An introduction to neural networks
  • An introduction to transfer learning
  • Bayesian approaches to solving machine learning problems

Learning activities and teaching methods (given in hours of study time)

Scheduled Learning and Teaching ActivitiesGuided independent studyPlacement / study abroad
22128

Details of learning activities and teaching methods

CategoryHours of study timeDescription
Scheduled Learning & Teaching activities22Weekly 2-hour lectures / seminars or 1 hour lecture + 1 hour seminar
Guided Independent Study40Completing assigned readings
Guided Independent Study58Preparation for and completion of practical assignments
Guided Independent Study30Practicing techniques used in computer tutorials

Formative assessment

Form of assessmentSize of the assessment (eg length / duration)ILOs assessedFeedback method
2 short practical exercisesBetween 2-4 tables, graphs, etc. with short descriptions1-6Written

Summative assessment (% of credit)

CourseworkWritten examsPractical exams
10000

Details of summative assessment

Form of assessment% of creditSize of the assessment (eg length / duration)ILOs assessedFeedback method
Assessment 1. Problem set covering several of the methods discussed in the module.501500 words with tables, figures, charts from analysis1-6Written
Assessment 2. Problem set covering several of the methods discussed in the module.501500 words with tables, figures, charts from analysis1-6Written
0
0
0
0

Details of re-assessment (where required by referral or deferral)

Original form of assessmentForm of re-assessmentILOs re-assessedTimescale for re-assessment
Assessment 1Problem set covering several of the methods discussed in the module. 1500 words with tables, figures, charts from analysis1-6August/September re-assessment period
Assessment 2Problem set covering several of the methods discussed in the module. 1500 words with tables, figures, charts from analysis1-6August/September re-assessment period

Indicative learning resources - Basic reading

  • Guido, S. and A. C. Mueller (2016). Introduction to Machine Learning with Python: A Guide for Data Scientists. O’Reilly.
  • Swaroop C H, A Byte of Python. https://python.swaroopch.com.

Indicative learning resources - Web based and electronic resources

Indicative learning resources - Other resources

Key words search

machine learning, computational social science, data analysis

Credit value15
Module ECTS

7.5

Module pre-requisites

none

Module co-requisites

SSIM Programming for Social Data Science

NQF level (module)

7

Available as distance learning?

No

Origin date

08/03/2022