Domain:
Digitalisation; Infocomm Technology & Smart Systems; Partnership and Engagement; Policy & Planning; Our Core Competencies
Audience:
Middle Management; Manager; Senior Officer
Remark:
You should have attended CSC's Data Analytics - Basic Principles and Applications (CRDDA10/CRDDAVL) programme, or are familiar with basic data analytics. After registration, you are required to fill in a pre-programme survey form for us to assess your suitability for the programme.
Who Should Attend:
You are keen to learn about unstructured text analytics and how to apply it to make better decisions.
You should also be comfortable with having discussions and doing hands-on exercises using Python and R programming languages.
Programme Overview
75% of data in the world are in unstructured form, e.g. videos, audio or text. Within our organisations, we may have avoided using unstructured data due to the inherent difficulties in analysing it, as compared to structured data. However, can you imagine making critical policy or organisational decisions based on only some data?
Making sense of sentiments from unstructured text information is key to ensuring data is analysed in totality. In this programme, discover key concepts in unstructured data analytics and explore how you can apply them through in-class discussions and hands-on exercises. Conducted interactively with case studies, this programme will equip you to make better decisions using unstructured text information.
*This programme is suitable for officers who have background in basic data analytics and statistics.
Learning Outcomes
Differentiate the different types of unstructured data
Describe the approach to analyse unstructured data
Perform basic text analysis on transcribed data
Apply text analytics framework in making better business decisions
Present and communicate findings from unstructured data in an easy-to-understand and interesting manner
Last updated: 25 Mar 2025
1. Basics of unstructured text analytics
- Comparative analysis of structured and unstructured data analysis methods
- Concepts and terminologies
- Working with unstructured data
2. Approaches to analyse unstructured text
- Framework and methodology
3. Mechanics of text analytics: Converting unstructured data into structured data
- Corpus and documents
- Phrases and tokenisation
- Stemming and spelling check
- Dictionary and mining
4. Categorisation of themes and sentiments from feedback information
- Applications of cluster analysis in forming text categories
5. Extraction and discovery of patterns and relationship from text information
- Applications of predictive modelling in pattern discovery relationship mining
6. Storytelling and making better sense of unstructured data
- Applications using data visualisation tool
- Case study: Sentiment analysis
7. Text analytics applications
Case studies and use case scenarios for text analytics
Text analytics using GovText - Topic modeling and its application
Group work and hands-on session uing Rapidminer and R programming language