Search Modules > EB5204 > Module Overview

Learning Outcomes

TopAt the end of the course, the participants will be able to:

Identify where sentiment analysis can be applied
Evaluate and analyse the classification techniques for sentiment classification and apply it with open source libraries
Design a sentiment analysis system for customer feedback and reviews
Design a sentiment analysis system for news and social media for applications in finance
Evaluate and assess sentiment analysis at a granular level for entities and aspects

Prerequisites

TopEB5001 Foundations of Business Analytics

Schedule

TopDay 1 October 6 9 am -5pm
Day 2 October 13 9 am -5pm
Day 3 October 20 9 am -5pm
Day 4 October 27 9 am -5pm
Day 5 November 3 9 am -5pm

Syllabus

TopThe following topics will be covered

Introduction to sentiment analysis and its applications in various social domains.
Overview of related tasks of NLP to sentiment analysis
Supervised learning classification algorithms for sentiment analysis
Entity and aspect mining for sentiment analysis
Sentiment visualization tools
Applications of sentiment analysis to customer analytics and financial applications
Sentiment analysis and its psychological basis

TopThe assessment will be 50% in examinations and 50% continual assessment.
Continual Assessment – 50%
•2 individual MCQ quizzes (15%)
The 1st quiz on day 4 of the course will test the material largely in the 1st 2 days of class. The 2nd quiz on day 5 of the course largely covers the materials on the 3rd and 4th days. The quizzes will be MCQ with True/ False questions.
•1 group programming assignment (15%)
Students are expected to form groups of 4-6 to submit a programming assignment of a real-use example.
•1 group presentation topic (10%) and report/ programming (10%)
Students are to present 15 mins on a sentiment-related topic (10%) and submit a final report (10%) .

Late submissions of the CA will result in a penalty of 25% of the marks for each day late.

Final Exam – 50%
•3 sections:
•Section A: 10 marks (by Sam Gu)
─General topics on sentiment analytics
•Section B: 28 marks (by Eric)
─Classification algorithms for sentiment mining & entity mining
─Applications in financial analytics
•Section C: 12 marks (by Dr. Rakesh)
─Applications in customer analytics

The final scores allocation may be subject to minor amendments.

Preclusions

TopNIL

Workload

Top1.5-0.5-0.5-3-2

Workload Components : A-B-C-D-E
A: no. of lecture hours per week
B: no. of tutorial hours per week
C: no. of lab hours per week
D: no. of hours for projects, assignments, fieldwork etc per week
E: no. of hours for preparatory work by a student per week