Introduction

• Introduction (JR)
• Nuts and bolts (GDF)
• Analysis (both)

Introdution

• Social media has exploded in recent years.

• Social media defined:

• Incredible numbers, incredible potential…
• We are the University of Reading Big Social Data Research Group.
  • Formed Summer 2014 covering multiple disciplines across the university.

Form and Function

• Social media are of interest to social scientists:
• Social (and other) networks influence decision making.
  • Favouritism, discrimination, bias, loyalty, etc. all influence allocations of resources and outcomes.
  • Social media are social networks quantified.
• Social networks publicise and propagate information:
  • Information availability crucial in decision making.
  • More information = better forecasting, better policy making?
• Social media present huge opportunities:
  • But huge challenges: Collection, processing, understanding the data.
  • Cross-disciplinary collaboration essential.
• Our group consists of:
  • Computer scientists (Di Fatta, Stahl):
    • Collection and processing of data.
  • Mathematicians (Vukadinović Greetham):
    • Complex analysis of network dynamics.
  • Applied Linguists (Jaworska):
    • Extracting meaning from qualitative data.
  • Social scientists:
    • What can we learn about social (and other types of) interaction and outcomes?

Reading and the General Election

• XX days ago we began collecting Tweets via Twitter’s streaming API.
  • General election related tweets: #GE2015, #Tories, #Labour, etc.
• During the Leaders’ Debate on April 2:

• During the Opposition Leaders’ Debate on April 16:

• A debate notable for the absentees…

• We’ve collected XX tweets since the end of March, with XX during the debates alone.
• But what to do with this information?

Sentiment Analysis?

• Simple volume of tweets may be interesting, but is it useful?
• Increasing focus on sentiment, or mood: What do people think?
  • Does mood/sentiment yield predictive power?
  • Academic papers have considered stock markets and sports events.
  • During election time, sentiment hugely interesting…
    • Who is ahead? Do big shifts occur?
    • What messages stick? Persistence in sentiment?
• Perhaps however, we have jumped a step:
  • Sentiment is a latent concept: We never observe its true value.
  • We can try to estimate it but we have no true value to compare against.

Methodology

Results

• Opposition leaders’ debate:

• What about the extreme events?
  • Early Ukip peak at about 20:10.
  • Subsequent Labour moment around 20:30.
  • Big Lib-Dem surge after 20:45.
  • Tory nosedive just before 9pm…
  • … Tory surge just before 21:30.
• Using Twitter and sentiment analysis we have potential to identify topics and their salience.
  • Further analysis can enable us to determine proximity of parties and individuals to particular issues of interest.