Online Mind Mapping and Brainstorming

Create your own awesome maps

Online Mind Mapping and Brainstorming

Even on the go

with our free apps for iPhone, iPad and Android

Get Started

Already have an account? Log In

Visualising Unstructured Data by Mind Map: Visualising Unstructured
0.0 stars - reviews range from 0 to 5

Visualising Unstructured Data


"Computers can only return results, since they have lots of memory and no imagination." - Gary Lau

Computer Processing

Statistics - Insight Without Understanding, Word Cloud Generator, word frequency, Tree Cloud, word proximity, Word Tree, theme, Leximancer Portal, Company, developed and commercialised by University of Queensland, Brisbane, Offering: SaaS and Desktop/Server, Technology, Project, 4 Input Steps, 1. Load Data, 2. Generate Concept Seeds, 3. Generate Thesaurus, 4. Run Project, Outputs, Concept Maps, Themes, Concepts, Dimension (RED), Data (BLACK), Thesaurus, Pathway, Insight Dashboard Report, Quadrant Report, Ranked Concepts, Ranked Compound Concepts, Supporting Text, Evaluation, Strengths, Understands academic needs very well, Very little training or customisation needed, Web based distribution, Visualisation - don't need experience to interpret results, Weaknesses, Not designed with integration in mind, Does not use Natural Language Processing (NLP)

NLP - Natural Language Processing, Semantics: Meaning, typically contextually dependent and hinted at by symbols, Terminology, Tokenization: Identification of distinct elements, e.g., words, punctuation mark, Stemming: Reducing word variants (conjugation, declension, case, pluralization) to bases., Named entities: people, companies, places, etc., Co-reference: Multiple expressions that describe the same thing., Pattern-based entities: e-mail addresses, phone numbers, etc., Concepts: abstractions of entities, Concrete and abstract attributes (e.g., 10-year, expensive, comfortable), Taxonomy: An exhaustive, hierarchical categorization of entities and concepts, either specified or generated by clustering., Ontology : In practice, a classification of a set of items in a way that represents knowledge., Subjectivity in the forms of opinions, sentiments, and emotions: attitudinal data., Limitations, Ambiguity, Sarcasim, Abbreviations/slang, Data preparation, Refine dictionary, Wordnet (lexical database)., Corpus: body of knowledge around a domain, More processing time


Unstructured Data

What does it look like?, Square, Spider web, Partner, I'm still trying to find meaning in the madness!

Largely Synonymous with "Text Data", Sensations, Thoughts, Feelings, Actions, Sound & Images i.e. videos

Key difference, Dimensionality, 80% of all data

Examples, Flesh Map, Visuwords, Tweeterverse, Anymails


Visual Cognitive Psychology, information overload, natural ability to group, compare, correlate, detect patterns and outliers

Examples, US Debt, Dashboard Madness, Visual Context, Sentiment, Exploration, data, Explanation and Action, infographic or propganda, answer known, tells a story, Data Driven Documents

1+1= Power to Fight Madness

US Supermarket Sentiment

combine with Datamining is 1+1+1


"Text analytics-based searches for information provide non-definitive results. I don't know what to do" - Boss?

Decison makers

Internal, Existing Students, Existing Staff, Research

External, Prospective Students, Alumni

Data Scientists

Qualities, no substitute for verbal communication and good old-fashioned face time, training to reduce "alienation"

Environment, culture that both thrives and acts on customer feedback


Evaluate, Support and Training, Level of accuarcy, Integration into BI Reporting, Integration into Data Mining, Ingestion Capability, Language Support, Visualisation

Market, Academia, Leximancer, NVIVO, Rapid Miner, Industrial, SAS Enterprise Miner, Attivio, IBM Content Analytics, IBM Modeller, Oracle Endeca Information Discovery, Cognito, DiscoverText, API, Open Source, Processing, GATE (General Architecture for Text Engineering), R, Mallet: machine learning toolkit


Seth Grimes, Introducing Text Analytics, “Large companies lack the agility to respond effectively and in a timely manner to the social media challenge. There is lots of room for innovation from small players.”, "Text analytics may move into databases and ETL tools", Published: Text Analytics in 2009, Application, Data Source, Information To Extract, Satisfaction


Early Stages

Leverage internal skills

Tools, Easy to Use, Interpret and Trust, Low start-cost

Sweet spot

Business Champions

Quick wins

No formal project or budget - raise CAPEX 2013

Late Stages

Wall between structured and unstructured data crumbling, Integration into BI and Datamining

Automatic ingestion and reporting

Build domain expertise

Custom build Visualisations


Paper based a small public university that introduced introduced the new teacher and unit evaluation survey in 2009 with the new PDR process

Voice of Customer / Student / Staff

Mahsood Shah is the Principal Advisor Academic Strategy, Planning and Quality with the Office of the Deputy Vice Chancellor (Academic) at RMIT University: "renewal of quality assurance and performance based funding using student satisfaction as a measure of educational quality will result in increased use of student voice to assess learning and teaching outcomes"

Competitive Advantage


Wellness Engine, Student Success and Risk Factors

Virtuous Circle

Government Funding Criteria

2012 plan to introduce performance based funding as part of quality assurance arrangements, shift from voluntary to mandatory use of surveys with the results used to assess and reward academic staff performance, measures, student attainment of generic skills and learning outcomes, student retention and progression, student satisfaction

delay, did not occur due to budgetary constraints, concerns that performance based funding has discouraged diversity, student access and opportunity


Vodafail The Musical, ROI: Reduce Churn

Intuit:accounting software, website 50% increase in user self-service shrank call center support request, ROI: < 1 year

"Insanity: doing the same thing over and over again and expecting different results."

Albert Einsten

"Love: doing disappointing things and having the same feeling" - Gary Lau



Student Survey, First Year Experience Survey (FYES), Course Experience Questionnaire (CEQ), University Experience Survey (UES), Higher Degree Research Students Annual Survey (MUSEQ-R), Collegiate Learning Assessment (CLA), may supplement CEQ, Australian Graduate Survey (AGS), Best Aspects, Needs Improving, Beyond Graduation Survey (BGS), CeQuery Tool: access database last updated in 2005

Staff Personal Development Review (PDR)

Research, Social Sciences, Publications

Content Management Systems

Legal Contracts, When do they expire?, Which are the high value contracts?

Gary Lau

Senior Business Analyst MQ


10+ years dealing with Business Questions

"Mental Models are made to be Broken"

"Bringing Meaning to Madness"


MQ Analytics Journey

"quantitative and qualitative analysis of structured statutory information for management decision making"




Gary's Work in Process


Data Scientist Blog

Guardian Data Blog

Unstructured Data

Semantic Web

Sound To Text

Book: Search User Interfaces


Natural Language Toolkit



Snake Oil

Tools for Visualisation

Standford Visualisation Group

Standford Unversity

Tools for Data Visualisation

Touch Graph

Designing Data Visualizations


R Resource

Flowing Data, American Spending

SBS ABS 2012 Census Visualisation

Financial Markets

Free Visualsiations