BDACA1516s2 - Lecture1

Introducing. . . What is Big Data? Methods The schedule

Big Data and Automated Content AnalysisWeek 1 – Wednesday

»Introduction«

Damian Trilling

[email protected]@damian0604

www.damiantrilling.net

Afdeling CommunicatiewetenschapUniversiteit van Amsterdam

30 March 2016

Big Data and Automated Content Analysis Damian Trilling



Today1 Introducing. . .

. . . the people

2 What is Big Data?DefinitionsAre we doing Big Data research?

3 MethodsWhich techniques?Which tools?Examples from last year

4 The scheduleNext meetingsPreview



. . . the people

Introducing. . .. . . the people



. . . the people

Introducing. . .Damian

dr. Damian TrillingAssistant Professor Political Communication &Journalism

• studied Communication Science in Münsterand at the VU 2003–2009

• PhD candidate @ ASCoR 2009–2012

• interested in political communication andjournalism in a changing media environmentand in innovative (digital, large-scale,computational) research methods

@damian0604 [email protected] 8th floor www.damiantrilling.net




. . . the people

Introducing. . .Theo

dr. Theo AraujoAssistant Professor of Communication ScienceUniversiteit van Amsterdam

• interested in corporate and persuasivecommunication, and on how organisations,consumers and stakeholders use social mediaacross countries and cultures. also interestedin innovative (digital, large-scale,computational) research methods

@theoaraujo [email protected]


www.theoaraujo.com


. . . the people

Introducing. . .You

Your name?Your background?Your reason to follow this course?



Definitions

What is Big Data?



Definitions

What is Big Data?

A simple technical definition could be:Everything that needs so much computational power and/orstorage that you cannot do it on a regular computer.



Definitions

What is Big Data?

Vis, 2013

• “commercial” definition (Gartner): “’Big data’ is high-volume,-velocity and -variety information assets that demandcost-effective, innovative forms of information processing forenhanced insight and decision making”

• boyd & Crawford definition:1 Technology: maximizing computation power and algorithmic

accuracy to gather, analyze, link, and compare large data sets.2 Analysis: drawing on large data sets to identify patterns in

order to make economic, social, technical, and legal claims.3 Mythology: the widespread belief that large data sets offer a

higher form of intelligence and knowledge that can generateinsights that were previously impossible, with the aura of truth,objectivity, and accuracy.



Definitions

What is Big Data?Vis, 2013

• “commercial” definition (Gartner): “’Big data’ is high-volume,-velocity and -variety information assets that demandcost-effective, innovative forms of information processing forenhanced insight and decision making”

• boyd & Crawford definition:1 Technology: maximizing computation power and algorithmic

accuracy to gather, analyze, link, and compare large data sets.2 Analysis: drawing on large data sets to identify patterns in

order to make economic, social, technical, and legal claims.3 Mythology: the widespread belief that large data sets offer a

higher form of intelligence and knowledge that can generateinsights that were previously impossible, with the aura of truth,objectivity, and accuracy.



Definitions

Implications & criticism

boyd & Crawford, 2012

1 Big Data changes the definition of knowledge2 Claims to objectivity and accuracy are misleading3 Bigger data are not always better data4 Taken out of context, Big Data loses its meaning5 Just because it is accessible does not make it ethical6 Limited access to Big Data creates new digital divides



Definitions

APIs, researchers and tools make Big Data

Vis, 2013Inevitable influences of:

• APIs• filtering, search strings, . . .• changing services over time• organizations that provide the data



Definitions

Epistemologies and paradigm shifts

Kitchin, 2014

• (Reborn) empiricism: purely inductive, correlation is enough• Data-driven science: knowledge discovery guided by theory• Computational social science and digital humanities: employBig Data research within existing epistemologies

• DH: descriptive statistics, visualizations• CSS: prediction and simulation



Definitions


Kitchin, 2014

• (Reborn) empiricism: purely inductive, correlation is enough

• Data-driven science: knowledge discovery guided by theory• Computational social science and digital humanities: employBig Data research within existing epistemologies




Definitions


Kitchin, 2014

• (Reborn) empiricism: purely inductive, correlation is enough• Data-driven science: knowledge discovery guided by theory

• Computational social science and digital humanities: employBig Data research within existing epistemologies




Definitions


Kitchin, 2014

• (Reborn) empiricism: purely inductive, correlation is enough• Data-driven science: knowledge discovery guided by theory• Computational social science and digital humanities: employBig Data research within existing epistemologies




Are we doing Big Data research?

Are we doing Big Data research in this course?

Depends on the definition

• Not if we take a definition that only focuses on computingpower and the amount of data

• But: We are using the same techniques. And they scale well.• Oh, and about that high-performance computing in the cloud:We actually do have access to that, so if someone has a reallygreat idea. . .







• But: We are using the same techniques. And they scale well.

• Oh, and about that high-performance computing in the cloud:We actually do have access to that, so if someone has a reallygreat idea. . .







• But: We are using the same techniques. And they scale well.• Oh, and about that high-performance computing in the cloud:We actually do have access to that, so if someone has a reallygreat idea. . .



Methods



Which techniques?

What we will learn the next weeks

1. How to collect dataAPIs, scrapers and crawlers, feeds, databases, . . .Storage in different file formats

2. How to analyze dataSentiment analysis, automated content analysis, regularexpressions, natural language processing, cluster analysis, machinelearning, network analysis



Which tools?

The methods

The tools we use for thisThe programming language Python (and the huge amount ofPython modules others already wrote).



Which tools?

A language, not a program:Python



Which tools?

Python

What?

• A language, not a specific program• Huge advantage: flexibility, portability• One of the languages for data analysis. (The other one is R.)

But Python is more flexible—the original version of Dropbox was written in Python. I’d say: R fornumbers, Python for text and messy stuff. But that’s just my personal view.

Which version?We use Python 3.http://www.google.com or http://www.stackexchange.com still offer a lotof Python2-code, but that can easily be adapted. Most notable difference: InPython 2, you write print "Hi", this has changed to print ("Hi")


http://www.google.com

http://www.stackexchange.com


Which tools?

If it’s not a program, how do you work with it?

Interactive mode

• Just type python3 on the command line, and you can startentering Python commands (You can leave again by entering quit())

• Great for quick try-outs, but you cannot even save your code

An editor of your choice

• Write your program in any text editor, save it as myprog.py• and run it from the command line with ./myprog.py or

python3 myprog.py



Which tools?

If it’s not a program, how do you start it?

An IDE (Integrated Development Environment)

• Provides an interface• Both quick interactive try-outs and writing larger programs• We use spyder, which looks a bit like RStudio (and to someextent like Stata)



Which tools?

Some considerations regarding the use of software inscience

Assuming that science should be transparent and reproducible

, weshoulduse tools that are

• platform-independent• free (as in beer and as in speech, gratis and libre)• which implies: open source

This ensures it can our research (a) can be reproduced by anyone,and that there is (b) no black box that no one can look inside



Which tools?

Some considerations regarding the use of software inscience

Assuming that science should be transparent and reproducible, weshoulduse tools that are

• platform-independent• free (as in beer and as in speech, gratis and libre)• which implies: open source

This ensures it can our research (a) can be reproduced by anyone,and that there is (b) no black box that no one can look inside



Which tools?

Why program your own tool?

[...] these [commercial] tools are often unsuitablefor academic purposes because of their cost, alongwith the problematic ‘black box’ nature of many ofthese tools. Vis, 2013

[...] we should resist the temptation to let theopportunities and constraints of an application orplatform determine the research question [...] Mahrt &Scharkow, 2013, p. 30



Examples from last year

Some final projects from previous courses

Questions

• Are (popular) apps for children in the Apple App Store framedin terms of education or entertainment?

• How can house prices on funda.nl be predicted?• Where are those who edit Wikipedia-entries about companiesgeographically located, related to the company’s HQ?

• What are the sentiment and topical frames presented inGoogle US search results for the top political news searchterms as indicated by Google Trends?

• How is the tone in newspaper election coverage related to thetone on Twitter?



The schedule



The schedule

Each weekIn general: A lecture (Monday) and a lab session (Wednesday).Each week one method.

ExaminationsA mid-term take-home exam in week 5 and an individual researchproject on which you work during the whole course.

Self-studyPlay around! You really have to do it to learn programming. See itas your weekly assignment ;-)



Next meetings

Next meetings



Next meetings

Week 2: Getting started with Python

Monday, 4–4Introduction lecture (you are encouraged to try it out at the sametime!)

Wednesday, 6–4Data analysis exercise

Preparation: Read chapters 2 and 3!And play around!



Preview

Start playing!Exercises

1. Run a program that greets you.The code for this is

1 print("Hello world")

After that, do some calculations. You can do that in a similar way:1 a=22 print(a*3)

Just play around.

Additional ressourcesCodecademy course on Pythonhttps://www.codecademy.com/learn/python


https://www.codecademy.com/learn/python

BDACA1516s2 - Lecture1

Education

Transcript of BDACA1516s2 - Lecture1