Please do not cite or circulate the printed version of this HTML document. Please refer instead to the original online version of this document, which is available online at , or contact the author(s).

Research Master's Thesis

The Making of Predictions

Social Media-Based Prediction and Its Resources, Techniques, and Applications

Fernando N. van der Vlist

(Graduate School of Humanities,) University of Amsterdam, the Netherlands
(Dept. of Media Studies,) University of Amsterdam, the Netherlands

Submitted to the Department of Media Studies at the University of Amsterdam, Faculty of Humanities, in partial fulfillment of the requirements for the degree of Master of Arts (MA).

Published in: Scripties Online. Digital Academic Repository, University of Amsterdam, 2015. Web. <http://dare.uva.nl/en/scriptie/569838>.

Submitted: 26 June 2015; Accepted: 17 July 2015; Published: July 2015

Abstract

This thesis investigates prediction and the stuff of which it is made. Over the recent years social media have attracted both an academic and public interest in its “predictive power” but when it comes to making predictions researchers generally agree that this is “hard”, “difficult”, or “tough”, especially when it involves uncertainty with regards to the future. Predictions are accomplishments and come into being with a purpose, considerable social and intellectual investment from sponsors or advocates, and mobilisation of existing conceptual and material resources. Rather than a specialist reading of concrete cases of prediction, the objective of this thesis is to develop a framework for conceptualising and analysing the stuff of prediction in at least some of the many ways that it exists, and in which it is imagined, accomplished, experienced, and thought through. More specifically, it investigates this stuff both empirically and conceptually (and historically), with a particular focus on the specificity of its techniques as they find applications in concrete settings. Two emblematic practical goals or purposes for social media-based prediction are investigated: forecasting the pulse of social media streams and the surveillance of influenza-like illness using Web search data. How to analyse the relation between the stuff of prediction and the social circumstances and practicalities with which it is inevitably entangled? What are techniques of prediction using their resources for? At the same time it also does a methodological contribution by making the exploration of what it means to take prediction as an object of study an integral part of the project itself, as opposed to committing to such a view from the outset. What does it mean to take prediction as an object of study; how to conceive of it intellectually? Responding to a growing public and academic interest in the predictive power of social media, and in prediction as a way of dealing with challenges characterised by uncertainty and risk more generally, the proposed framework enables a critical analysis of the production of prediction with a particular sensitivity towards its techniques, the resources they mobilise in light of a certain specific practical goal, and the social and cultural significance of their applications in diverse concrete settings.

Keywords

prediction, calculation, techniques, quantification, social media, big data, uncertainty

prediction
calculation
techniques
quantification
social media
big data
uncertainty
Info
Title: The Making of Predictions
Subtitle: Social Media-Based Prediction and Its Resources, Techniques, and Applications
Type: Research Master's thesis; Abstract
Supervisor.name: Dr. B. (Bernhard) Rieder
Supervisor.affiliation: Dept. of Media Studies, Faculty of Humanities, University of Amsterdam
Second-reader.name: Dr. C. (Carolin) Gerlitz
Second-reader.affiliation: Dept. of Media Studies, Faculty of Humanities, University of Amsterdam
Third-reader.name: Dr. N. A. J. M. (Niels) van Doorn
Third-reader.affiliation: Dept. of Media Studies, Faculty of Humanities, University of Amsterdam
Committee.name: Dr. M. E. (Menno) Spiering (chair); Dr. I. C. (Ingrid) van Alphen; Dr. J. A. (Jan) Teurlings; Dr. B. (Barbara) Titus; Dr. H. Y. M. (Yolande) Jansen; C. (Charlotte) Faber; M. (Melanie) Vrauwdeunt
Committee.affiliation: Faculty of Humanities, University of Amsterdam
Description.note: Submitted to the Department of Media Studies at the University of Amsterdam, Faculty of Humanities, in partial fulfillment of the requirements for the degree of Master of Arts (MA).
Description.note: A preliminary version of this thesis was presented at the 2nd Thesis Conference Research Master Media Studies: Human | Non-Human | Post-Human in a panel on “Dealing with Data”, hosted at the University of Amsterdam.
Description.note: This thesis was published in Scripties Online. Digital Academic Repository, University of Amsterdam, 2015. Web. <http://dare.uva.nl/en/scriptie/569838>.
Abstract: This thesis investigates prediction and the stuff of which it is made. Over the recent years social media have attracted both an academic and public interest in its “predictive power” but when it comes to making predictions researchers generally agree that this is “hard”, “difficult”, or “tough”, especially when it involves uncertainty with regards to the future. Predictions are accomplishments and come into being with a purpose, considerable social and intellectual investment from sponsors or advocates, and mobilisation of existing conceptual and material resources. Rather than a specialist reading of concrete cases of prediction, the objective of this thesis is to develop a framework for conceptualising and analysing the stuff of prediction in at least some of the many ways that it exists, and in which it is imagined, accomplished, experienced, and thought through. More specifically, it investigates this stuff both empirically and conceptually (and historically), with a particular focus on the specificity of its techniques as they find applications in concrete settings. Two emblematic practical goals or purposes for social media-based prediction are investigated: forecasting the pulse of social media streams and the surveillance of influenza-like illness using Web search data. How to analyse the relation between the stuff of prediction and the social circumstances and practicalities with which it is inevitably entangled? What are techniques of prediction using their resources for? At the same time it also does a methodological contribution by making the exploration of what it means to take prediction as an object of study an integral part of the project itself, as opposed to committing to such a view from the outset. What does it mean to take prediction as an object of study; how to conceive of it intellectually? Responding to a growing public and academic interest in the predictive power of social media, and in prediction as a way of dealing with challenges characterised by uncertainty and risk more generally, the proposed framework enables a critical analysis of the production of prediction with a particular sensitivity towards its techniques, the resources they mobilise in light of a certain specific practical goal, and the social and cultural significance of their applications in diverse concrete settings.
Keywords: prediction, calculation, techniques, quantification, social media, big data, uncertainty
Length.words: 23,071
Length.reading: 2 hours, 9 mins
Sections: Acknowledgements; Abstract; Keywords; Contents; List of Tables; Introduction, the Stuff of Prediction; Prediction and Uncertainty; Archaeology and Cultural Techniques; Expertise, Calculation, and Judgement; Part I, Resources; Chapter 1, the Artificial as Cultural Mediator; Quantification and Measurement; Evidence and (Media) Empiricism; The Quantification of Uncertainty; Chapter 2, the Art and Science of Prediction; Routine Predictability and Prediction; Two Cultures of Statistical Modelling; The Predictive Power of Social Media; Data Collection and Modelling; Application Areas; Detection and Prediction; Part II, Techniques and Applications; Chapter 3, Forecasting the Pulse of Social Media Streams; Event-Based Information Organisation; Forecasting as an Information Retrieval Concern; New Event Detection as a Document Classification Problem; Chapter 4, Surveilling Influenza-Like Illness Using Web Search Queries; Query-Based Syndromic Surveillance; “Big Data Hubris” and Algorithm Dynamics; Disease Control and Prevention as a Machine Intelligence Problem; Inductive Inference and Mechanical Reasoning; Social Media Companies and Their Tangled Positions; Conclusion; Works Cited; Appendix: A Survey of Social Media-Based Prediction
Element.table: Table 1; Table 2; Table 3; Table 4; Table A–1; Table A–2; Table A–3; Table A–4; Table A–5
Publisher: Scripties Online, Digital Academic Repository, University of Amsterdam
Publisher.place: Amsterdam, the Netherlands
Document.pages: 1–119 (i–x, 1–79, A1–A30)
Date.submitted: 26 June 2015
Date.evaluated: 17 July 2015
Date.accepted: 17 July 2015
Date.published: July 2015
Language: English (United Kingdom)
Documentation.style: Modern Language Association (7th ed.)
Export.citation: BibTEX
Export.print: javascript:window.print()
2012– fernandovandervlist.nl
v1.2.28