Presented By O’Reilly and Cloudera
Make Data Work
21–22 May 2018: Training
22–24 May 2018: Tutorials & Conference
London, UK

Narrative Extraction – Analysing the World’s Narratives through Natural Language Understanding

Naveed Ghaffar (Narrative Economics), Rashed Iqbal (UCLA)
16:3517:15 Wednesday, 23 May 2018
Data science and machine learning
Location: Capital Suite 10/11 Level: Non-technical

Who is this presentation for?

Data scientists and innovators working in the field of Natural Language Processing, Natural Language Generation and Natural Language Understanding. The topic is particularly relevant to those who want to learn about the latest advancements in AI based personal assistants. Social scientists and behavioural economists would also benefit from this presentation.

Prerequisite knowledge

Beginner level understanding of Natural Language Processing and Natural Language Understanding is beneficial but not necessary. An appreciation of Deep Learning techniques would also be useful. We do not expect audience members to have any special or advanced level knowledge to appreciate this presentation.

What you'll learn

The audience will understand the importance of narratives and how they affect our society, politics and the macro-economic conditions of a country. The latest techniques in Natural Language Understanding will be discussed, and the audience will appreciate our approach to narrative extraction and how we model the effects of popular narratives. The audience will also understand the complexities in this area and where further research focus is required.

Description

Nobel Laureate Professor, Robert Shiller, is one of few economists to have predicted the Great Recession of 2007-2009 and the dot-com crash. Throughout his career, Professor Shiller has introduced and supported ground-breaking ideas in economics. In 2017, Professor Shiller presented a paper titled ‘Narrative Economics’ at the National Bureau of Economic Research (NBER). The paper introduced two key concepts:

• Macro-economic fluctuations are not only influenced by economic indicators but also by the origination and spread of popular narratives.

• Narratives spread along a pattern similar to contagious disease epidemics. He proposes using epidemiological disease modelling techniques to understand the impact and dynamics of these narratives.

By narratives, we mean stories, or ideas, particularly those of human interest and emotion that are conveyed in communication. The human brain has always been highly attuned towards narratives, whether factual or not, to justify on-going actions. Stories motivate and connect activities to deeply felt values and needs. When narratives “go viral” they spread far and wide and are often accompanied by deep socio-political and economic change. The 1920-21 Depression, the Great Depression of the 1930s, the so-called “Great Recession” of 2007-9, and the contentious political-economic situation of today, are considered as the results of the popular narratives of their respective times.

The interpretation of narratives is a subjective human phenomenon and is difficult to study scientifically. Narrative Extraction is the first step to this end. We present a framework for extracting narrative using Natural Language Understanding to help us gain a better understanding of how “viral” narratives emerge and their likely impact.

Our high-level approach to narrative extraction involves:

• Automation of Narrative Extraction – identification and extract key concepts around a theme of conversation. We source narratives through data repositories such as GDELT.

• Understanding – generating an ontological framework for concepts and associations. Natural Language Understanding is said to operate at multiple levels. The lowest level being the syntax level followed by semantic and then pragmatic levels. Narrative Extraction lies next to the pragmatic level adding human subjectivity into the mix.

• Categorising narrative types – ideas are conveyed through the delivery mechanism of stories. Through our research, we have developed the key categories for these narratives types. Each category adds rich context to an idea, and it enables us to model the likely propagation effect or “stickiness” of the narrative itself.

• Identification and search of narratives – of the tens of millions of popular narratives flowing across the world at any moment. Narrative Extraction enables search of these narratives specific to a geo-location, around a concept, or a product. In addition, we can search across the popularity of narratives or their predicted impact to influence types of human action.

The topic of Narrative Extraction is particularly relevant in this time where “fake news” and the manipulation of social media may have aided in the propagation of stories that have motivated human action, for example, during the 2016 US Election or the Brexit referendum. Beyond these not so trivial matters, research in this area will assist corporations to understand brand value dynamics; “virality” of products, and it will enable improved modelling of a product’s Diffusion of Innovation curve. Spreading narratives have been creating cultural change long before the Internet or the advent of social media. However, the dynamics of this phenomena have both accelerated and become more decentralised. Narratives traverse the ‘Dunbar’s Number’ threshold far more frequently than ever before and appear to influence a greater multiplicity of social groups. It is our hope that this address will raise awareness of the latest techniques involving Natural Language Understanding and will help stimulate interest and further research in this area.

- Narrative Economics paper by Robert Shiller: https://cowles.yale.edu/sites/default/files/files/pub/d20/d2069.pdf

Photo of Naveed Ghaffar

Naveed Ghaffar

Narrative Economics

Naveed Ghaffar is a serial entrepreneur and innovator in data management and data science technologies. He has founded 3 start-ups in this domain over the past 6 years, and he continues to coach and mentor a number of London based start-ups.

Naveed is the co-founder of Narrative Economics, a start-up company that is leading research and development in the emerging field of Natural Language Understanding as it pertains to the spread of popular narratives across the world.

More recently, Naveed has served as Chief Engineer for KPMG McLaren between January 2016 to September 2017, where he was responsible for overall product management for the company’s suite of data analytics and simulation solutions.

Naveed has a background in data analytics and data governance. He is recognised as a thought leader on Privacy by Design, Design Thinking and the policy and technical effects of the EU GDPR regulations.

Naveed holds a degree in Law (LLB Honors) and a Masters in Computer Science (MSc) from the University of Birmingham. He is a Certified Scrum Master, Design Thinking Coach, and Jobs-to-be-Done Innovator.

Photo of Rashed  Iqbal

Rashed Iqbal

UCLA

Rashed Iqbal, Ph. D is a Program Manager, Data Solutions at Teledyne Technologies in California. He has two areas of interest and expertise: Data Science and Machine Learning, and Transitioning Traditional Organisation to Agile and Lean Methods. He practices, consults, and teaches in these domains.

He is an Adjunct Professor in Economics Department at UCLA where he teaches graduate courses in Data Science. Rashed also teaches Deep learning and Natural Language Processing / Understanding at UC Irvine.

Rashed undertook multiple entrepreneurial ventures in these areas. His current area of research is Narrative Economics that studies impact of the popular narratives and stories on economic fluctuations. He is using Natural Language Processing/Understanding and Deep Learning to extract narratives in human communication. He believes narrative extraction will revolutionize process of human communication to which Narrative Economics is just one of the applications.

Rashed has a Ph.D. in Systems Engineering with focus on Stochastic and Predictive Systems and holds current CSM, CSP, PMI-ACP, and PMP certifications. He is also a Senior Member of the IEEE.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)