On Data-Driven AI – and science…

Over the past few weeks I have been interviewed by the New Scientist and the BBC on the nature of modern Artificial Intelligence. This is about the data-driven nature of current intelligent systems, and how science is adopting a similar approach, and what implications this could have for society. Links follow…

New Scientist Article – needs subscription
Same article entirely readable on The Age (Australia)

Patterns in Media Content

Big Data Analysis of News and Social Media Content

Ilias Flaounas, Saatviga Sudhahar, Thomas Lansdall-Welfare, Elena Hensiger, Nello Cristianini (*)

Intelligent Systems Laboratory, University of Bristol

(*) corresponding author

The analysis of media content has been central in social sciences, due to the key role that media plays in shaping public opinion. This kind of analysis typically relies on the preliminary coding of the text being examined, a step that involves reading and annotating it, and that limits the sizes of the corpora that can be analysed. The use of modern technologies from Artificial Intelligence allows researchers to automate the process of applying different codes in the same text. Computational technologies also enable the automation of data collection, preparation, management and visualisation. This provides opportunities for performing massive scale investigations, real time monitoring, and system-level modelling of the global media system. The present article reviews the work performed by the Intelligent Systems Laboratory in Bristol University towards this direction. We describe how the analysis of Twitter content can reveal mood changes in entire populations, how the political relations among US leaders can be extracted from large corpora, how we can determine what news people really want to read, how gender-bias and writing-style in articles change among different outlets, and what EU news outlets can tell us about cultural similarities in Europe. Most importantly, this survey aims to demonstrate some of the steps that can be automated, allowing researchers to access macroscopic patterns that would be otherwise out of reach.

Download the survey article with pointers to the peer reviewed publications

On the Current Paradigm in Artificial Intelligence

Nello Cristianini – (Draft of article prepared for AIComm issue on History of AI)

The field of Artificial Intelligence (AI) has undergone many transformations, most recently the emergence of data-driven approaches centred on machine learning technology. The present article examines that paradigm shift by using the conceptual tools developed by Thomas Kuhn, and by analysing the contents of the longest running conference series in the field. A paradigm shift occurs when a new set of assumptions and values replaces the previous one within a given scientific community. These are often conveyed implicitly, by the choice of success stories that exemplify and define what a given field of research is about, demonstrating what kind of questions and answers are appropriate. The replacement of these exemplar stories corresponds to a shift in goals, methods, and expectations. We discuss the most recent such transition in the field of Artificial Intelligence, as well as commenting on some earlier ones.

Using Twitter to Monitor Collective Mood

Large scale analysis of social media content allows for real time discovery of macro-scale patterns in public opinion and sentiment. In this paper we analyse a collection of 484 million tweets generated by more than 9.8 million users from the United Kingdom over the past 31 months, a period marked by economic downturn and some social tensions. Our findings, besides corroborating our choice of method for the detection of public mood, also present intriguing patterns that can be explained in terms of events and social changes. On the one hand, the time series we obtain show that periodic events such as Christmas and Halloween evoke similar mood patterns every year. On the other hand, we see that a significant increase in negative mood indicators coincide with the announcement of the cuts to public spending by the government, and that this effect is still lasting. We also detect events such as the riots of summer 2011, as well as a possible calming effect coinciding with the run up to the royal wedding.

ANIMATION: http://mediapatterns.enm.bris.ac.uk/mood

REFERENCE: Thomas Lansdall-Welfare, Vasileios Lampos and Nello Cristianini: Effects of the Recession on Public Mood in the UK. Accepted for publication in the International Workshop on Social Media Applications in News and Entertainment (SMANE), 2012.