- Discovering Corruption with Data: Pulitzer Prize-winning Panama Papers
(by Ryan Boyd) This event is cohosted by Data Visualization DC (https://www.meetup.com/data-visualization-dc/) (Data Community DC (http://datacommunitydc.org/)), Graph Database of Baltimore/DC (https://www.meetup.com/graphdb-baltimore/), & Social Data and Analytics DC (https://www.meetup.com/SocialDataDC/events/240275106/) Message from Data Community DC: Interested in being a Mentor or Mentee? Want to be matched on your Full Stack interests? Complete this survey (https://goo.gl/forms/VBq7QRPBzKdr2Si73) and we'll release a list of optimized matches using this Data Community DC open source matching code (https://github.com/datacommunitydc/MentorMenteeMatching). Complete this survey to be matched: https://goo.gl/forms/VBq7QRPBzKdr2Si73 The Talk: Discovering Corruption with Data: Pulitzer Prize-winning Panama Papers The Panama Papers (https://en.wikipedia.org/wiki/Panama_Papers) represent one of the world's largest data leaks in history: 11.5 million records exposing a system that enables crime, corruption, and wrongdoing, hidden by secretive offshore companies. Over 400 journalist members of the International Consortium of Investigative Journalists (ICIJ) worked for a year mining and investigating the data stored in a Neo4j graph database. This resulted in the resignation of the PM of Iceland, Supreme Court hearings for Pakistan's PM, the arrest of people money laundering for Mexican drug cartels, and plenty of more investigations and regulatory reforms. In this talk, Ryan Boyd will demonstrate how Neo4j graph database powered this investigation, showing queries and visualizations highlighting the relationships between offshore companies, corporate officers, law firms and addresses. He'll use the Neo4j Sandbox to show you how you too can dive into the data which has been opened up by the ICIJ for the world to investigate. You'll learn to write basic Cypher queries for finding nodes, relationships, and paths. We'll also provide an intro to how Graph Algorithms in the APOC open source library can help better understand the networks in the Panama Papers data. Agenda 630 - Door Open & Networking 700 - Introductions & Announcements 715 - Ryan Boyd & The Panama Papers 815 - Q&A 830 - Data Drinks @ Highline About Ryan Boyd Ryan is a San Francisco-based software engineer, authNZ geek, data geek and graph geek. He's Director of Developer Relations for Neo4j, an open source graph database which powers connected data analysis in data journalism, cancer resource, and some of the world's top companies. Prior to Neo4j, he was Head of Developer Relations for Google Cloud Platform and worked on over 20+ different APIs and developer products during his 8 years at Google. Ryan is the author of "Getting Started with OAuth 2.0," published by O'Reilly. He no longer skydives now that he has a young daughter, but enjoys the adventures of sailing and cycling.
- Social Data Doing Social Good
This will be ranked as one of the top meetups of the year - we have some outstanding speakers that we are fortunate enough to host. "Using Social Data to Better Understand Emotional Crisis and Suicide" Glen Coppersmith, Qntfy, @GlenCoppersmith (https://twitter.com/glencoppersmith) Glen will talk about what Qntfy is using data outside the healthcare system to detect and better understand emotional crisis and suicide (which claimed more American lives last year than automobile accidents or homicides). He will also share a broader context and vision of how the "digital life" we lead (social media, wearables, devices, etc.) provides for a coming revolution in behavioral health. Glen is the founder & CEO of Qntfy, a company using analytics to empower patients, loved ones, and clinicians. Glen was previously at Johns Hopkins, and considers himself a recovering academic -- still publishing papers, but primarily working to integrate novel technology into complex human systems of care. "Quantifying a community's worldview and detecting the early signs of extremism in Social Data" Jonathon Morgan, Founder/CEO New Knowledge, co-host of @PartiallyD, @JonathonMorgan (https://twitter.com/jonathonmorgan) Using deep learning, we can analyze the context in which online communities use language about politics, hate speech, and extremism. By comparing theses context to mainstream language, it's possible to quantify a community's worldview, measure its partisanship, and detect the early signs of extremism. We'll look at how these techniques reveal rising radicalization on the far right, and even where Clinton and Trump supporters might share common values. Jonathon is the founder and CEO of New Knowledge, a company building technologies to research, explain, and predict human behavior. As part of his ongoing work applying quantitative methods to combating terrorism and violent extremism, he served as an advisor to the White House and State Department, co-authored the ISIS Twitter Census for the Brookings Institution, and develops new technology with DARPA, along with Qntfy. Jonathon's recent research into the online behavior of far-right extremist groups has been featured by the Washington Post, The Atlantic, and the Southern Poverty Law Center. In his spare time, he co-hosts Partially Derivative, the surprisingly popular podcast about data science and drinking.
- Election 2016 - A Social Data Update
For our September Meetup - we will be focussing on the 2016 Presidential Election and the trends and insights that are being uncovered in Social Data. -> Kellan Terry, Brandwatch, Quantifying Political Success with Social Data (LinkedIn (https://www.linkedin.com/in/kellan-terry-8882b240), @ArrowMaker5 (https://twitter.com/ArrowMaker5)) Social media, not polls, is the greatest gauge of the efficacy of a candidate's campaign maneuvers. In 2016, presidential hopefuls can gather real-time feedback from the voters they so desperately try to appeal to by gathering and analyzing social data to discover the insights therein. Within this presentation we'll look at how candidates performed through debates, conventions and controversies as their social discussions address every up and down. Kellan is the Senior PR Data Analyst at social intelligence company, Brandwatch. He has served as the lead analyst around the 2016 US Presidential Election, and has provided data and analysis to media outlets such as the Wall Street Journal, USA Today, Reuters, NPR and more. -> David Troy, CEO 410Labs (http://410labs.com/#about), (LinkedIn (https://www.linkedin.com/in/davidctroy), @davetroy (https://twitter.com/davetroy)), A Networked Theory of Trump Support: The still-emerging field of network science offers perhaps our best shot at understanding the Trump phenomenon. David is a serial technology entrepreneur and community builder. He founded regional ISP and hosting provider ToadNet. He developed Twittervision as well as open source voice-over-IP systems. To help grow the Baltimore creative community he founded Beehive Baltimore, Baltimore Angels and the TEDxMidAtlantic conferences. -> Dr. V.S. Subrahmanian, Professor in the Department of Computer Science, (LinkedIn (https://www.linkedin.com/in/v-s-subrahmanian-8500577), @vssubrah (https://twitter.com/vssubrah)) - Bots, Sentiment, and More in the 2016 US Presidential Election VS is Professor of Computer Science at the University of Maryland and a founder of Sentimetrix. He develops new data-driven algorithms to solve a host of problems ranging from identifying influencers, bots, and bad actors in social networks, forecasting terror attacks and destabilizing terror networks, to increasing airline profits via predictive analytics. His work has been featured by numerous media outlets such as the Washington Post, The Economist, PBS, and more.
- Finding the Hotspots on the Globe through Social Data
This month's social data meetup is focussed on finding the political hotspots in Social Data. Edward Crook, Brandwatch (https://www.brandwatch.com), Senior Research Analyst - "An Analysis of the Syrian Migrant Crisis" - How social is shaping the story and how online data can be worked to reveal insights. Jeff Long, DataMinr (http://www.DataMinr.com), "Social Media as a Global Sensor Network" Jeff Long is the head of Dataminr's state and major city partnerships business. Previously, Jeff worked on Capitol Hill as a policy adviser and held business development roles at start-ups, RevolutionHealth.com (http://revolutionhealth.com/) and DNA Direct. Jeff graduated from Hamilton College with a B.A. and received his M.B.A. from the University of Virginia. Professor Dame Wendy Hall The University of Southampton, (http://www.ecs.soton.ac.uk/people/wh)UK (http://www.ecs.soton.ac.uk/people/wh), "Observatories and Data Analytics for Web Science" is Executive Director of the Web Science Institute at Southampton. She will discuss the role of observatories and data analytics for the development of new methodologies for longitudinal research in Web Science as well as applications for business intelligence and policy making in general.
- Social Good in Government: Leveraging Social Data
Speakers: 6:30 - 7:00 Doors Open 7:00 - 7:05 Introductions 7:05 - 7:30 Topic Title: Social Data in International Development Dr. Craig Jolley (@jolleywithane) (https://twitter.com/jolleywithane) is a AAAS Science & Technology Policy Fellow in the U.S. Global Development Lab at the U.S. Agency for International Development. His work at USAID supports programs to combat global poverty and improve health, security, and economic growth by incorporating data science technologies into development planning, implementation, and monitoring. One particular focus area has been in social media analytics, where he has pursued social data as an information source for improved communications and outreach, as well as information on opinions, trends, and events in the developing world. He received his PhD in Physics from Arizona State University, and has researched biological physics and biomolecular networks at Montana State University and RIKEN. 7:30 - 8:00: Social Data and 300 Global Embassies Christopher Toppe and Mohammed Partovi - Department of State. Problems and Solutions in managing 300 embassy social presences around the world in dozens of languages and character sets. Tools and Strategies in reporting on performance. 8:00 - 8:30: How Analytics Can Illuminate Digital Media Strategies David Bresnahan-McRae is a Manager of Client Strategy at Social Driver who specializes in digital advocacy projects. Before joining Social Driver, David received a Masters of Comparative Politics at the London School of Economics (LSE), and worked in Melbourne, Australia as a specialist in analytics and digital healthcare advocacy.
- The Coming Election in Social Data
This meetup will focus on what we are seeing in Social Data with regards to the great election of 2016. Hosted by iStrategy Labs, we will explore what trends we are seeing to date, applications being built off of various data sources, and trends we are seeing that we have not seen before. Email me ([masked]) with any questions. Brandwatch, Dinah Alobeid A tech PR professional for nearly 8 years, and is currently the Head of PR, North America at social listening and analytics firm Brandwatch in New York City. Presentation Overview: Through the lens of social data, I'll examine the role social has played in recent elections (i.e. UK's General Election 2015), the pivotal moments that have already happened a year out from the 2016 U.S. election, and how candidates are leveraging social whether they want to or not. Twitter, Sean Evins As Partnerships Manager for the Government and Elections team at Twitter, Sean Evins is part of a team driving creative use of the Twitter platform by government officials, agencies, and political campaigns to help them communicate effectively, educate and inform citizens, increase responsiveness, and collect actionable feedback on public opinion. Presentation Overview: Data and content around the debates this year Chris Williams first used the Twitter API in 2009 to find out who the most popular bands were at SXSW, and has been playing with the API in his free time ever since. He started building quoted.news (originally Qwotd) in 2014 as a class project while working on his masters in journalism at Northwestern. He's continued to update it when he can, but often gets sidetracked by an interesting article with a good quote. An alpha version is available at http://alpha.quoted.news/ Presentation Overview: Measuring article popularity based on article quotes on Twitter
- The Science Behind Influencer Analysis in Social Media
For this September meetup - we'll be focused on Influencer Analysis. Klout.com - Tyler Singletary (@harmophone (https://twitter.com/@harmophone)), is Director of Platform at Klout. Tyler will be speaking about Klout Scores, Klout Topics, and Klout’s Influence Graph. Kirk Borne "The Data Science of Social Influence Analysis -- fun, failures, and fans". Dr. Kirk Borne (@KirkDBorne) is the Principal Data Scientist for the NextGen Analytics and Data Science (https://www.boozallen.com/consulting/strategic-innovation/nextgen-analytics-data-science) workstream within the Strategic Innovation Group atBooz Allen Hamilton. He previously spent 12 years as Professor at George Mason University in the Computational and Data Sciences program. Before that, he worked 18 years on various NASA contracts, as research scientist and manager on large data systems. He has a PhD in Astrophysics from Caltech. He has applied his expertise in science and data systems as a consultant and advisor to numerous agencies and firms, focusing on the use of data for discovery, decision support, and innovation across many different domains and industries. He is an active contributor of data science and analytics information on social media, where he has been named consistently among the top worldwide influencers in big data and data science. Follow him on Twitter at @KirkDBorne and read his blog at http://rocketdatascience.org/ NodeXL - Marc Smith (@marc_smith) - Sociologist of computer-mediated collective action @ Connected Action http://www.connectedaction.net Director: Social Media Research Foundation Smrfoundation.org (http://smrfoundation.org)
- Predicting Topics and Sharing in Social Media
For June's Social Data Analytics- DC, we're very happy to partner with our friends at Data Science DC (http://www.meetup.com/Data-Science-DC/events/222556386/) to present two speakers from the University of Maryland working at the cutting edge of the analysis of behavior in social media. Hadi Amiri will talk about predicting interactions between brands and consumers, while Bill Rand will talk about fitting agent-based and other models to Twitter data. You can sign up for this event either here or at DSDC's Meetup page, but please don't register in both places. Agenda: • 6:30pm -- Networking, Empanadas, and Refreshments • 7:00pm -- Introduction, Announcements, Give-aways • 7:15pm -- Presentations and Discussion • 8:30pm -- Data Drinks (Tonic, 2036 G St NW) Presentations: Brandtology in Social Media User generated contents in social media platforms provide important and timely indicators on the spontaneous and often genuine views of users, fans, and customers on a wide range of topics. It is thus invaluable to obtain actionable insights from such live streaming contents. In this talk, I introduce Brandtology in social media: the science of studying brands, customers, and the interaction between the two in the context of social networks. I will talk about two the issues of predictability in Brandtology namely churn prediction and emerging topic detection. Hadi Amiri (http://www.umiacs.umd.edu/~hadi/index.html) is currently a Postdoc at the University of Maryland, Institute for Advanced Computer Studies (UMIACS). He is affiliated with the Computational Linguistics & Information Processing (CLIP) lab. His primary research interests are in the areas of Social Media Analysis and Natural Language Processing, and his current work centers on understanding exposition in the context of social networks. He received his PhD from the National University of Singapore in 2013 and worked as Research Scientist at the Institute for Infocomm Research (I2R) from[masked]. Follow Hadi on Twitter @amirieb (https://twitter.com/amirieb). Using Big Data and Agent-Based Modeling to Understand and Predict Social Media Diffusion With the increasing abundance of `digital footprints' left by human interactions in online environments, e.g., social media and app use, the ability to model such behavior has become increasingly possible. Many approaches have been proposed, however, most previous model frameworks are fairly restrictive, and often the models are not directly compared on a diverse collection of human behavior. We will explore a new modeling approach that enables the creation of models directly from data with no previous restrictions on the data. We will examine this modeling framework in the context of predictive and descriptive abilities on a heterogeneous catalog of human behavior collected from fifteen thousand users on Twitter. We find that despite the popularity of exogenous drive-type models, for explaining digitally-mediated human behavior, most users are better modeled using self- or socially-driven models. Our work highlights the importance of a flexible modeling approach when attempting to explain and predict human behavior in digital environments. William Rand (http://www.rhsmith.umd.edu/directory/william-rand) examines the use of computational modeling techniques, like agent-based modeling, geographic information systems, social network analysis, and machine learning, to help understand and analyze complex systems, such as the diffusion of innovation, organizational learning, and economic markets. He serves as the Director of the Center for Complexity in Business, the first academic research center focused solely on the application of complex systems techniques to business applications and management science. Over the course of his research experience, he has used computer models to help understand a large variety of complex systems, such as the evolution of cooperation, suburban sprawl, traffic patterns, financial systems, land-use and land-change in urban systems, and many other phenomena. He has recently received research awards from DARPA, Google, WPP, the National Science Foundation and the Marketing Science Institute. Follow Bill on Twitter @billrand (https://twitter.com/billrand). Sponsors: This event is sponsored by the GWU Department of Decision Sciences (http://business.gwu.edu/about-us/departments/decision-sciences/), Statistics.com (http://bit.ly/12YljkP), Elder Research (http://datamininglab.com/), Booz Allen Hamilton (https://www.boozallen.com/consulting/strategic-innovation/nextgen-analytics-data-science), Twitter (http://www.twitter.com), the Big Boulder Initiative (http://www.bbi.org), and Pearson/InformIT (http://www.informit.com/). (Would your organization like to sponsor too? Please get in touch!)
- Social Sentiment Analysis in Social Data
The State of Sentiment Analysis - March 11th at George Washington University - Funger Hall (https://registrar.gwu.edu/sites/registrar.gwu.edu/files/downloads/scheduling/Funger/FNGR103.pdf). For this meetup we will be discussing Social Sentiment Analysis in Social Data Seth Grimes (http://www.altaplana.com/sethgrimes.html) - President of Alta Plana. (@SethGrimes (http://twitter.com/SethGrimes)) Seth is the leading industry analyst covering text analytics, sentiment analysis, and analysis on the confluence of structured and unstructured data sources. Seth will give the state of the industry in Sentiment Analysis. Clarabridge (http://www.clarabridge.com) - Shane Axtell (linkedin (https://www.linkedin.com/pub/shane-axtell/4/492/932)/@shaxtall (https://twitter.com/shaxtell)) - Lead computational linguist at Clarabridge. The differences and interactions between NPS, Sentiment, and Emotions and show how they can be used in parallel to obtain a holistic view of customers Mapr (https://www.mapr.com) - William Peterson - William “Bill” Peterson is the Director of Product Marketing for MapR. Brandwatch (http://www.brandwatch.com) - Nate Walton - (LinkedIn (https://www.linkedin.com/in/natewalton)) Director of Professional Services- "Using what we have" Uses for sentiment based on how it's implemented, especially as it usually appears in "listening" rather than "research"
- Facebook: Mining the Social Web
Hello Everyone, For this meetup we will be teaming up with "Data Driven DC (http://www.meetup.com/Data-Driven-DC/events/199201722/)": We will demonstrate a range of analyses and insights that can be extracted from Facebook. A thousand friends, a thousand voices, one you. Understanding who you are through data science, social network analysis and graph theory. Learn how Facebook can be utilized to provide deeper insights about peoples lives and relationships. Add to your Google Calendar: https://www.google.com/calendar/event?action=TEMPLATE&tmeid=Z3U5NzVxamM4bjJ0YjduOGlqYnZpbjV2c3MgZG1pdHJpLmFkbGVyQG0&tmsrc=dmitri.adler%40gmail.com (https://www.google.com/calendar/event?action=TEMPLATE&tmeid=bTYwcmRqNDZtb3JhOTM3M3RzcmE4bjI0ajAgZG1pdHJpLmFkbGVyQG0&tmsrc=dmitri.adler%40gmail.com) What you need: your laptop and a version of R and R Studio installed (links: http://cran.r-project.org (http://cran.r-project.org/) & http://www.rstudio.com/products/RStudio/ ) Background required: a basic familiarity with the R programming language If you have gone through the below you will be ready: 1. R tutorial: https://www.datacamp.com/courses/introduction-to-r (intro to basics is sufficient but of course the more you know the better) The event will be followed by networking and drinks @ Tonic (2036 G St NW, Washington, DC[masked]