COMP47600 Text Analytics

Academic Year 2022/2023

This course aims is to cover how text analytics is currently used to find important regularities and discover meaning in big data. As such, the course will cover the fundamental techniques and some sample application areas where text analytics is deployed. Initially, the course will cover how raw textual data is pre-processed, the natural language techniques (NLP) used to prepare data for subsequent analysis and the paradigms used for system evaluation. The key techniques used in text analytics will be reviewed; including techniques for computing similarity, classification and clustering of texts, sentiment analysis, and discovering temporal regularities. Classic examples of text analytics from social media, polling, predictive analytics and news media will be discussed as examples of the application of these techniques. The course will be run using online-blended delivery; that is, lectures and practical briefings will be pre-recorded and available asynchronously online (with associated materials, eg slides) and practicals will be delivered as a timetabled hour each week, synchronously delivered online (via zoom). So, students will be expected to work offline on the lecture and practical materials but are expected to be present online for practical hours each week (via zoom).

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

At the end of the course students should have a thorough knowledge of the main techniques used in text analytics, some familiarity with the software used to implement these techniques and a knowledge of some of the main application areas. Students should have developed a knowledge of the main application areas in which these techniques prove useful and know how to evaluate new text-analytics systems.

Indicative Module Content:

The course aims to provide students with a firm understanding of the key areas of Text Analytics research, and give a flavour of the application domains in which it has been applied.

Student Effort Hours: 
Student Effort Type Hours
Lectures

24

Practical

12

Specified Learning Activities

144

Total

180

Approaches to Teaching and Learning:
Very practical course, with hands-on practicals each week that accompany the lecture. The aim is that you should be able to do text analytics at the end of the course. 
Requirements, Exclusions and Recommendations
Learning Requirements:

This course is designed to be taken by students with no prior programming experience.

Learning Recommendations:

This course is designed to be taken by students with no prior programming experience (though it will involve coursework using Python and R). Having said this, prior experience of, at least, one programming language will clearly be a boon. Neither does the course assume a previous qualification in Computer Science. It is very much a from-scratch introduction to text analytics.


Module Requisites and Incompatibles
Incompatibles:
COMP30810 - Introduction to Text Analytics

Additional Information:
None


 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Continuous Assessment: Practicals Throughout the Trimester n/a Graded No

50

Examination: Written essay-question(s) type of exam. 2 hour End of Trimester Exam No Graded Yes

50


Carry forward of passed components
No
 
Resit In Terminal Exam
Spring No
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment

How will my Feedback be Delivered?

Students are given feedback on practicals.