Social Media Analy.cs (SMA)
|
|
- Cathleen Adams
- 8 years ago
- Views:
Transcription
1 Social Media Analy.cs (SMA) Emanuele Della Valle DEIB - Politecnico di Milano emanuele.dellavalle@polimi.it hap://emanueledellavalle.org
2 What's social media? haps:// Emanuele Della Valle hap://emanueledellavalle.org 2
3 shall I care? haps:// Emanuele Della Valle hap://emanueledellavalle.org 3
4 I'm s.ll unconvinced haps:// Emanuele Della Valle hap://emanueledellavalle.org 4
5 Personal Social Media Analy.cs Facebook Analy.cs haps:// /insights/ TwiAer Analy.cs haps://analy.cs.twiaer.com/ Any social media site has one, some.me it is pay per use, e.g., flickr More generally for any other Website under individual control, one can use google analy.cs hap:// 5
6 Facebook analy.cs 6 [source: haps:// guide- to- social- media/]
7 Facebook analy.cs cont. 7
8 Facebook analy.cs cont. 8
9 TwiAer Analy.cs 9 [source: hap://organizedassistant.com/5- recent- social- media- changes/ ]
10 Google Analy.cs 10 [source: haps://flic.kr/p/kjz4t]
11 What can you do as a company? The goal: reach à engage à acquire à mone.se How: Social media plan 11 [source: haps://
12 What can you do as a company? Unless you want to spend in manually integra.ng the personal social media tools seen before, you need a cross- plakorm tool Market hap://sysomos.com/ hap:// media- marke.ng/radian6 hap://hootsuite.com (the analy.cs part) hap:// (applicable to social media data) 12
13 sysomos.com 13 haps://youtu.be/trjo8w737i8
14 Radiant6 [haps://youtu.be/8i6exg3urg0] B 1/12/2014 hap://emanueledellavalle.org 14
15 Take home message Analysing social media you may be able to feel the pulse of the piece of reality genera.ng them and make sense of it 15
16 Is this new? [source: haps:// 16
17 No. So what's new? How pervasive the digital world is in the physical world There's a log way From web logs to App analy.cs of users sharing loca.ons! Big Data! We now have the enabling technology: 17
18 how does SMA relates with Big Data? Big Data technologies can scale this ability to the volume generated by a global contact centre, a na.on, the planet the velocity generated by a TV show, a sport event, IoT sensors the variety of en..es, languages or cultures the veracity problems caused by spelling errors, ambiguous words, irony/sarcasm Meaning of the colour: doable, possible, challenging 18
19 Key idea: from micropost to data Collect microposts Named En.ty Recogni.on En.ty Linking Sen.ment Opinion extrac.on Extract data 19
20 Facebook APIs Collect microposts haps://developers.facebook.com/ TwiAer APIs haps://dev.twiaer.com/docs/api Instagram APIs hap://instagram.com/developer/endpoints/ 20
21 Anatomy of a micropost sender Emanuele Della Valle Men.oned Happily lost in a boale of Heineken beer #heinekendesignweek at the Heineken Magazzini hap:// Link to a Web resource hap://emanueledellavalle.org 21 hashtag
22 Anatomy of a micropost There is already an amount of data here! Emanuele Della Bla bla bla bla bla bla bla bla bla bla bla bla #heinekendesignweek bla bla bla bla bla bla hap:// hap://emanueledellavalle.org 22
23 Emanuele Della Valle Anatomy of a micropost There is already an amount of data Bla bla bla bla bla bla bla bla bla bla bla bla #heinekendesignweek bla bla bla bla bla bla hap:// #heinekendesignweek hap://emanueledellavalle.org 23 type posts hashtag type link hap:// men.ons
24 Named En.ty Recogni.on (NER) Defini.on loca.ng and classifying atomic elements [...] into predefined categories such as names, persons, organiza.ons, loca.ons, expressions of.me, quan..es, monetary values, etc. A.k.a. C.J.Rijsbergen, Informa.on Retrieval (1979) En.ty Iden.fica.on En.ty Extrac.on 24
25 Named En.ty Recogni.on, example Input: Armstrong landed the Eagle on the Moon. Possible outputs: Armstrong Eagle Moon Person: animal. Company Band (misspelled). Character 25 Vehicle
26 Named En.ty Recogni.on, example Input: Armstrong landed the Eagle on the Moon. Desired Output: Armstrong: person Eagle: vehicle Moon: celes.al body Note: a very hard task :- ( Early solu.ons were based on manually wriaen grammars Modern solu.ons are base on Machine Learning Advance solu.ons perform NER together with En.ty linking 26
27 Defini.on En.ty Linking (EL) It is the task of determining the iden.ty of en..es men.oned in text. It is dis.nct from named en.ty recogni.on (NER) in that it iden.fies not the occurrence of names (and a limited classifica.on of those), but their reference. 27 haps://en.wikipedia.org/wiki/en.ty_linking
28 En.ty Linking - process Determine all possible en.ty links candidates Select the best en.ty link 28
29 En.ty Linking - process Determine all possible En.ty Mapping Candidates linguis.c analysis, i.e., part- of- speech (POS) tagging Normaliza.on encoding and spelling special (language dependent) characters language dependent spellings abbrevia.ons, acronyms type dependent spellings alterna.ve names and synonyms fuzzy string mapping 29
30 En.ty Linking - process Select the best en..es links from all possible candidate ones: Popularity/sta=s=c based strategies based on a reference text corpus Linguis=c/Seman=c based strategies based on a knowledge base/graph At high level Make an assump.on Run strategies in parallel 30 Decide using logical/ probabilis.c rules
31 En.ty Linking - example Determine candidates links Input: Armstrong landed the Eagle on the Moon. B 1/12/2014 [source: hap:// hpi- semweb06part ] hap://emanueledellavalle.org 31
32 En.ty Linking - example Select Links Input: Armstrong landed the Eagle on the Moon. B 1/12/2014 [source: hap:// hpi- semweb06part ] hap://emanueledellavalle.org 32
33 En.ty Linking - example Input: Armstrong landed the Eagle on the Eagle. Output: Armstrong hap://dbpedia.org/resource/neil_armstrong Eagle hap://dbpedia.org/resource/apollo_lunar_module Moon hap://dbpedia.org/resource/moon 33
34 Applying NER From micropost to data drink Emanuele Della Bla bla bla bla bla bla bla bla Heineken beer #heinekendesignweek bla the bla bla Magazzini hap:// hap://emanueledellavalle.org 34 company Place event
35 Company Drink From micropost to data Adding the data to those we got before Emanuele Della Valle Place Event type type type type User "Heineken" type "beer" "The Magazzini" "#heinekendesignweek" topic topic topic posts micropost42 link hap://emanueledellavalle.org 35 men.ons hap://
36 From micropost to Bla bla bla bla bla bla bla bla Heineken beer #heinekendesignweek hap://wordnet Emanuele Della Valle linking en..es bla the bla bla Magazzini hap:// hap://emanueledellavalle.org 36 hap://dbpedia.org/ hap://fuorisalone hap://fuorisalone
37 From micropost to data Adding the data (which are also linked) to those we got before User Company type Heineken topic type type Drink Emanuele Della Valle Place Event type type type bear The Magazzini Heineken design week topic topic topic posts micropost42 link men.ons hap://
38 From micropost to data Adding the data (which are also linked) to those we got before Heineken User type follows produces topic type organizes Emanuele Della Valle offers Located at Heineken design week beer The Magazzini topic topic topic posts micropost42 link men.ons hap:// offers
39 Adding sen.ment and opinion Machine learning Given a large mount of training data Classify unseen data Dic.onary approach Sen.WordNet hap://sen.wordnet.is..cnr.it/ WordNet- Affect hap://wndomains.xk.eu/wnaffect.html Advance approaches (combines the previous two) Sta.s.cal Approach Seman.c Approach 39
40 linking en..es From micropost to data Posi.ve opinion Emanuele Della Happily bla bla bla bla bla bla Heineken beer #heinekendesignweek bla the bla bla Magazzini hap:// hap://emanueledellavalle.org 40
41 From micropost to data Adding sen.ment / opinion User produces Heineken Posi=ve topic type type follows organizes Emanuele Della Valle offers Located at Heineken design week beer The Magazzini topic topic topic posts micropost42 link men.ons sen=ment hap:// 0.9 offers
42 Adding sen.ment and opinion Discussion about precision Hard also for humans as well! Sarcasm Irony Be aware of contradic.ons and value them The food and the service are good, but the service sucks 42
43 Tools hap:// hap://viewer.opencalais.com/ hap:// hap://dandelion.eu/ (Italian is supported!) 43
44 Key idea: from micropost to data Collect microposts Named En.ty Recogni.on En.ty Linking Sen.ment Opinion extrac.on Extract data 44
45 Acknowledges OpenHPI Named En.ty Recogni.on, by Harald Sack hap:// hpi- semweb06part
46 Thank you! Any Ques.on? Emanuele Della Valle DEIB - Politecnico di Milano emanuele.dellavalle@polimi.it hap://emanueledellavalle.org
Extrac'ng People s Hobby and Interest Informa'on from Social Media Content
Extrac'ng People s Hobby and Interest Informa'on from Social Media Content Thomas Forss, Shuhua Liu and Kaj- Mikael Björk Dept of Business Administra?on and Analy?cs Arcada University of Applied Sciences
More informationOpportuni)es and Challenges of Textual Big Data for the Humani)es
Opportuni)es and Challenges of Textual Big Data for the Humani)es Dr. Adam Wyner, Department of Compu)ng Prof. Barbara Fennell, Department of Linguis)cs THiNK Network Knowledge Exchange in the Humani)es
More informationLanguage Resources, Language Technology, Text Mining, the Seman8c Web: How interoperability of machines can help humans in the mul8lingual web
Language Resources, Language Technology, Text Mining, the Seman8c Web: How interoperability of machines can help humans in the mul8lingual web Felix Sasaki DFKI / University of Appl. Sciences Potsdam W3C
More informationTheo JD Bothma Department of Informa1on Science theo.bothma@up.ac.za
Theo JD Bothma Department of Informa1on Science theo.bothma@up.ac.za Reflec1ons on the role of corpora and big data in e- lexicography in rela1on to end user informa1on needs CILC 2015 7th Interna1onal
More informationMastering the variety dimension
Mastering the variety dimension Emanuele Della Valle DEIB - Politecnico di Milano emanuele.dellavalle@polimi.it h>p://emanueledellavalle.org Agenda In a changing world variety is unavoidable SemanEc Technologies
More informationIntroduc)on to the IoT- A methodology
10/11/14 1 Introduc)on to the IoTA methodology Olivier SAVRY CEA LETI 10/11/14 2 IoTA Objec)ves Provide a reference model of architecture (ARM) based on Interoperability Scalability Security and Privacy
More informationHow To Use A Webmail On A Pc Or Macodeo.Com
Big data workloads and real-world data sets Gang Lu Institute of Computing Technology, Chinese Academy of Sciences BigDataBench Tutorial MICRO 2014 Cambridge, UK INSTITUTE OF COMPUTING TECHNOLOGY 1 Five
More informationFrom Big Data to Value
From Big Data to Value The Power of Master Data Management 2.0 Sergio Juarez SVP Elemica EMEA & LATAM Reveal Oct 2014 Agenda Master Data Management Why Now? What To Do? How To Do It? What s Next? Today
More informationXML, Seman9c Web and Content Analy9cs
XML, Seman9c Web and Content Analy9cs XML Prague Pre- conference 2014 Felix Sasaki DFKI / W3C Fellow 1 What do you need to follow this session? Ideal: a computer with internet access, to be able to provide
More informationData Warehousing. Yeow Wei Choong Anne Laurent
Data Warehousing Yeow Wei Choong Anne Laurent Databases Databases are developed on the IDEA that DATA is one of the cri>cal materials of the Informa>on Age Informa>on, which is created by data, becomes
More informationHow To Use Splunk For Android (Windows) With A Mobile App On A Microsoft Tablet (Windows 8) For Free (Windows 7) For A Limited Time (Windows 10) For $99.99) For Two Years (Windows 9
Copyright 2014 Splunk Inc. Splunk for Mobile Intelligence Bill Emme< Director, Solu?ons Marke?ng Panos Papadopoulos Director, Product Management Disclaimer During the course of this presenta?on, we may
More informationBig Data in medical image processing
Big Data in medical image processing Konstan3n Bychenkov, CEO Aligned Research Group LLC bychenkov@alignedresearch.com Big data in medicine Genomic Research Popula3on Health Images M- Health hips://cloud.google.com/genomics/v1beta2/reference/
More informationMastering the Velocity Dimension of Big Data
Mastering the Velocity Dimension of Big Data Emanuele Della Valle DEIB - Politecnico di Milano emanuele.dellavalle@polimi.it It's a streaming world Agenda Mastering the velocity dimension with informaeon
More informationSeven Steps to Client Success Understanding the Flow of ediscovery
Seven Steps to Client Success Understanding the Flow of ediscovery Seven Steps to Client Success An Overview of Electronic Discovery Understanding Electronic Discovery Defini&ons and Descrip&ons Understanding
More informationBoise State University Social Media Handbook
Boise State University Social Media Handbook A best practices and style guide for social media management and networking using the Boise State University brand Compiled by Marketing Minds and implemented
More informationAdvanced Invoice Processing: One Step at a Time. Sam Abadir Solu.on Manager Accoun.ng Percep.ve So7ware
Advanced Invoice Processing: One Step at a Time Sam Abadir Solu.on Manager Accoun.ng Percep.ve So7ware AutomaAon of Accounts Payable With only about 5 % of the world s invoices truly automated end- to-
More informationProtec'ng Informa'on Assets - Week 10 - Identity Management and Access Control. MIS 5206 Protec/ng Informa/on Assets Greg Senko
Protec'ng Informa'on Assets - Week 10 - Identity Management and Access Control In the News Readings MIS5206 Week 10 Identity Management and Access Control Test Taking Tip Quiz In the News Discuss items
More informationPa8ern Recogni6on. and Machine Learning. Chapter 4: Linear Models for Classifica6on
Pa8ern Recogni6on and Machine Learning Chapter 4: Linear Models for Classifica6on Represen'ng the target values for classifica'on If there are only two classes, we typically use a single real valued output
More informationGet a room: Eight things people want when booking a hotel
Get a room: Eight things people want when booking a hotel Introduc)on Booking a hotel room. No two journeys are alike. The average person visits 38 websites searching for the best hotel, in the best loca?on,
More informationSocial Network Mining
SSIIM - Seminários de Sistemas Inteligentes, Interacção e Mul8média, MIEIC Social Network Mining Eduarda Mendes Rodrigues Assistant Professor DEI- FEUP, Universidade do Porto hhp://www.fe.up.pt/~eduarda
More informationUsing Social Media to Drive Recommender Systems for Mobile Apps. - GRP Presenta=on - Jovian Lin (A0026542M)
Using Social Media to Drive Recommender Systems for Mobile Apps - GRP Presenta=on - Jovian Lin (A0026542M) Structure of Presenta=on Introduc=on Why Recommender Systems (RS)? Problems in Recommending Our
More informationKeeping Pace with Big Data
- A Data Mining Perspec>ve Huan Liu, Tempe, AZ hep://www.public.asu.edu/~huanliu NSF Workshop on Big Data Analy6cs for Infrastructure and Building Resilience and Sustainability, Beijing, China Sept 19-20,
More informationUNIFIED, END- TO- END EDISCOVERY
ac.onable informa.on governance Partners Providing Excellence in: UNIFIED, END- TO- END EDISCOVERY 2011 IBM Corpora.on Meet the Presenters Amir Jaibaji Vice President, Product Management StoredIQ Kevin
More informationRESTful or RESTless Current State of Today's Top Web APIs
RESTful or RESTless Current State of Today's Top Web APIs Frederik Buelthoff, Maria Maleshkova AIFB, Karlsruhe Ins-tute of Technology (KIT), Germany [1] Growing Number of Web APIs Challenges Scalability
More informationDTCC Data Quality Survey Industry Report
DTCC Data Quality Survey Industry Report November 2013 element 22 unlocking the power of your data Contents 1. Introduction 3 2. Approach and participants 4 3. Summary findings 5 4. Findings by topic 6
More informationFixed Scope Offering (FSO) for Oracle SRM
Fixed Scope Offering (FSO) for Oracle SRM Agenda iapps Introduc.on Execu.ve Summary Business Objec.ves Solu.on Proposal Scope - Business Process Scope Applica.on Implementa.on Methodology Time Frames Team,
More informationOffensive & Defensive & Forensic Techniques for Determining Web User Iden<ty
Offensive & Defensive & Forensic Techniques for Determining Web User Iden
More informationSocial Media! Marketing!
Social Media! Marketing! First things first [Marke2ng] is more about giving, than taking. You have to create communica2ons that actually enhance the meaning in someone s life that give them insights into
More informationHands On- Google Grants Google Adwords for Non- Pro5its
Hands On- Google Grants Google Adwords for Non- Pro5its Search Adver5sing Approach and Strategy Katherine Cleland ClelandMarke5ng 1 Why Google Adwords? Online Search has replaced Yellow Pages 80% of online
More informationAn Open Dynamic Big Data Driven Applica3on System Toolkit
An Open Dynamic Big Data Driven Applica3on System Toolkit Craig C. Douglas University of Wyoming and KAUST This research is supported in part by the Na3onal Science Founda3on and King Abdullah University
More informationSecure Because Math: Understanding ML- based Security Products (#SecureBecauseMath)
Secure Because Math: Understanding ML- based Security Products (#SecureBecauseMath) Alex Pinto Chief Data Scien2st Niddel / MLSec Project @alexcpsec @MLSecProject @NiddelCorp Agenda Security Singularity
More informationIns+tuto Superior Técnico Technical University of Lisbon. Big Data. Bruno Lopes Catarina Moreira João Pinho
Ins+tuto Superior Técnico Technical University of Lisbon Big Data Bruno Lopes Catarina Moreira João Pinho Mo#va#on 2 220 PetaBytes Of data that people create every day! 2 Mo#va#on 90 % of Data UNSTRUCTURED
More informationANALYTICAL TECHNIQUES FOR DATA VISUALIZATION
ANALYTICAL TECHNIQUES FOR DATA VISUALIZATION CSE 537 Ar@ficial Intelligence Professor Anita Wasilewska GROUP 2 TEAM MEMBERS: SAEED BOOR BOOR - 110564337 SHIH- YU TSAI - 110385129 HAN LI 110168054 SOURCES
More informationThis presenta,on covers the essen,al informa,on about IT services and facili,es which all new students will need to get started.
This presenta,on covers the essen,al informa,on about IT services and facili,es which all new students will need to get started. 1 Most of the informa,on is covered in more depth on the Informa,on Services
More informationRealm of Big Data Ini0a0ves
Realm of Big Data Ini0a0ves Kamlesh Mhashilkar Head - Analy0cs, Big Data and Informa0on Management (ABIM) Prac0ce TCS Digital Enterprise Copyright 2013 Tata Consultancy Services Limited 1 Realm of Big
More informationCS 5150 So(ware Engineering Evalua4on and User Tes4ng
Cornell University Compu1ng and Informa1on Science CS 5150 So(ware Engineering Evalua4on and User Tes4ng William Y. Arms Usability: The Analyze/Design/Build/Evaluate Loop Analyze requirements Design User
More informationSecurity Leadership: Preven4ng and Responding to Future Cyber A<acks. Mark Seward, Sr. Director, Security and Compliance
Security Leadership: Preven4ng and Responding to Future Cyber A
More informationHow to write a Bachelor s Thesis in Cogni4ve and Decision Sciences? Gilles Du4lh
How to write a Bachelor s Thesis in Cogni4ve and Decision Sciences? Gilles Du4lh Who I Am Gilles Du4lh, 32 Psychology at University of Amsterdam Master Psychological Methods Got my PhD in mathema4cal psychology
More informationHoneycomb Crea/ve Works is financed by the European Union s European Regional Development Fund through the INTERREG IVA Cross- border Programme
Honeycomb Crea/ve Works is financed by the European Union s European Regional Development Fund through the INTERREG IVA Cross- border Programme managed by the Special EU Programmes Body. Web Analy*cs In
More informationMaking Sense of Big Data. Dr. Thomas E. Potok Computa2onal Data Analy2cs Group Leader Oak Ridge Na2onal Laboratory potokte@ornl.
Making Sense of Big Data Dr. Thomas E. Potok Computa2onal Data Analy2cs Group Leader Oak Ridge Na2onal Laboratory potokte@ornl.gov 865-574- 0834 ORNL s Big Data Legacy Science National Security Energy
More informationAdvanced Archive- It Applica2on Training: Archiving Social Networking and Social Media Sites
Advanced Archive- It Applica2on Training: Archiving Social Networking and Social Media Sites 1 Agenda Overview of Social Networking/Media sites Why archive these sites? Typical Challenges Best Prac2ces:
More informationThe Library (Big) Data scien4st
The Library (Big) Data scien4st IFLA/ALA webinar: Big Data: new roles and opportuni4es for new librarians June 15 th 2016 IFLA Big Data Special Interest Group (SIG) Wouter Klapwijk, Stellenbosch University,
More informationPhone Systems Buyer s Guide
Phone Systems Buyer s Guide Contents How Cri(cal is Communica(on to Your Business? 3 Fundamental Issues 4 Phone Systems Basic Features 6 Features for Users with Advanced Needs 10 Key Ques(ons for All Buyers
More informationCloud Compu)ng: Overview & challenges. Aminata A. Garba
Cloud Compu)ng: Overview & challenges Aminata A. Garba Outline I. Introduc*on II. Virtualiza*on III. Resources Op*miza*on VI. Challenges 2 A Historical Note 1960, the idea of organizing computa)on as a
More informationCS 91: Cloud Systems & Datacenter Networks Failures & Replica=on
CS 91: Cloud Systems & Datacenter Networks Failures & Replica=on Types of Failures fail stop : process/machine dies and doesn t come back. Rela=vely easy to detect. (oien planned) performance degrada=on:
More informationCO-OCCURRENCE EXTRACTOR
Page 1 of 7 CO-OCCURRENCE EXTRACTOR Sede opertiva: Piazza Vermicelli 87036 Rende (CS), Italy Page 2 of 7 TABLE OF CONTENTS 1 APP DOCUMENTATION... 3 1.1 HOW IT WORKS 3 1.2 Input data 4 1.3 Output data 4
More informationThe Data Reservoir. 10 th September 2014. Mandy Chessell FREng CEng FBCS Dis4nguished Engineer, Master Inventor Chief Architect, Informa4on Solu4ons
Mandy Chessell FREng CEng FBCS Dis4nguished Engineer, Master Inventor Chief Architect, Solu4ons The Reservoir 10 th September 2014 A growing demand Business Teams want Open access to more informa4on More
More informationHIPAA Compliance and Electronic Protected Health Informa6on: Ignorance is not bliss!
Maxxum, Inc. HIPAA Compliance and Electronic Protected Health Informa6on: Ignorance is not bliss! Medical Device ephi Risk Iden6fica6on and Mi6ga6on Webinar Overview Relevance why this topic? Risk a perspective
More informationPu?ng B2B Research to the Legal Test
With the global leader in sampling and data services Pu?ng B2B Research to the Legal Test Ashlin Quirk, SSI General Counsel 2014 Survey Sampling Interna6onal 1 2014 Survey Sampling Interna6onal Se?ng the
More informationBig Data Analytics The Next Frontier in Logistics? www.dataart.com
Big Data Analytics The Next Frontier in Logistics? www.dataart.com Today s presentation Today s presentation What is Big Data about? Today s presentation What is Big Data about? How is it used? Today s
More informationGyrus: A Framework for User- Intent Monitoring of Text- Based Networked ApplicaAons
Gyrus: A Framework for User- Intent Monitoring of Text- Based Networked ApplicaAons Yeongjin Jang*, Simon P. Chung*, Bryan D. Payne, and Wenke Lee* *Georgia Ins=tute of Technology Nebula, Inc 1 Tradi=onal
More informationEnsemble Methods. Adapted from slides by Todd Holloway h8p://abeau<fulwww.com/2007/11/23/ ensemble- machine- learning- tutorial/
Ensemble Methods Adapted from slides by Todd Holloway h8p://abeau
More information10 Steps to Preparedness
10 Steps to Preparedness Key Take- Aways Review basics of disaster recovery and con2nuity of opera2ons. Understand what you can do to prepare your pool and its members for an unplanned interrup2on. Ini2ate
More informationInsider s Guide to Digital Media Measurement Sen5ment Analysis Symposium 2015
Insider s Guide to Digital Media Measurement Sen5ment Analysis Symposium 2015 Presented By Stephen D. Rappaport, Global Digital Advisor, Sunstar Inc. Senior Consultant SDR Consul5ng E. steve@sdrconsul5ngllc.com
More informationApplying Machine Learning to Network Security Monitoring. Alex Pinto Chief Data Scien2st MLSec Project @alexcpsec @MLSecProject!
Applying Machine Learning to Network Security Monitoring Alex Pinto Chief Data Scien2st MLSec Project @alexcpsec @MLSecProject! whoami Almost 15 years in Informa2on Security, done a licle bit of everything.
More informationCompu4ng Privacy Requirements
Security Requirements Security in Compu4ng, Chapters 1 & 10. 1 Topics What are the key requirements to implement a secure system? Privacy Anonymity Authen4ca4on & Authorisa4on Integrity Audit 2 Privacy
More informationRetaining globally distributed high availability Art van Scheppingen Head of Database Engineering
Retaining globally distributed high availability Art van Scheppingen Head of Database Engineering Overview 1. Who is Spil Games? 2. Theory 3. Spil Storage Pla9orm 4. Ques=ons? 2 Who are we? Who is Spil
More informationTrace evidence and archival data
Updates Trace evidence and archival data Review materials posted soon Old quiz ques>ons posted soon Final exam: 2/3 new, 1/3 old Old review materials s>ll apply Similar format: some fill- ins, some shor>sh-
More informationGyrus: A Framework for User- Intent Monitoring of Text- Based Networked ApplicaAons
Gyrus: A Framework for User- Intent Monitoring of Text- Based Networked ApplicaAons Yeongjin Jang*, Simon P. Chung*, Bryan D. Payne, and Wenke Lee* *Georgia Ins=tute of Technology Nebula, Inc 1 Tradi=onal
More informationHow To Understand The Big Data Paradigm
Big Data and Its Empiricist Founda4ons Teresa Scantamburlo The evolu4on of Data Science The mechaniza4on of induc4on The business of data The Big Data paradigm (data + computa4on) Cri4cal analysis Tenta4ve
More informationSeman&c Web: Benefits For Clinical Decision Support At The Bedside. Emory Fry, MD SemTechBiz 2013
Seman&c Web: Benefits For Clinical Decision Support At The Bedside Emory Fry, MD SemTechBiz 2013 Clinical Decision Support (CDS) A system providing knowledge and person specific or popula8on informa8on
More informationWeb Services and Development of Semantic Applications
Web Services and Development of Semantic Applications Trish Whetzel Outreach Coordinator THE NATIONAL CENTER FOR BIOMEDICAL ONTOLOGY Na#onal Center for Biomedical Ontology Mission To create software for
More informationIndia s Integrated Taxpayer Data Management System (ITDMS) - A data mining tool for non-intrusive anti-tax evasion work
India s Integrated Taxpayer Data Management System (ITDMS) - A data mining tool for non-intrusive anti-tax evasion work Winner of Prime Minister Award For Excellence In Public Administration April 2010
More informationTrends in Big Data Discovery and Analytics! Summary Results! November 2014!
Trends in Big Data Discovery and Analytics! Summary Results! November 2014! Program Overview! In October and November 2014, Gatepoint Research invited selected marke=ng and technology execu=ves to par=cipate
More informationData Mining. Supervised Methods. Ciro Donalek donalek@astro.caltech.edu. Ay/Bi 199ab: Methods of Computa@onal Sciences hcp://esci101.blogspot.
Data Mining Supervised Methods Ciro Donalek donalek@astro.caltech.edu Supervised Methods Summary Ar@ficial Neural Networks Mul@layer Perceptron Support Vector Machines SoLwares Supervised Models: Supervised
More informationBetter Transnational Access and Data Sharing to Solve Common Questions
Better Transnational Access and Data Sharing to Solve Common Questions Julia Lane American Ins0tutes for Research University of Strasbourg University of Melbourne Overview Common Ques0ons New kinds of
More informationFacilitating Business Process Discovery using Email Analysis
Facilitating Business Process Discovery using Email Analysis Matin Mavaddat Matin.Mavaddat@live.uwe.ac.uk Stewart Green Stewart.Green Ian Beeson Ian.Beeson Jin Sa Jin.Sa Abstract Extracting business process
More informationHortonworks & SAS. Analytics everywhere. Page 1. Hortonworks Inc. 2011 2014. All Rights Reserved
Hortonworks & SAS Analytics everywhere. Page 1 A change in focus. A shift in Advertising From mass branding A shift in Financial Services From Educated Investing A shift in Healthcare From mass treatment
More informationMergers in Produc.on and Percep.on. Ka.e Drager (University of Hawai i at Mānoa) Jennifer Hay (University of Canterbury)
Mergers in Produc.on and Percep.on Ka.e Drager (University of Hawai i at Mānoa) Jennifer Hay (University of Canterbury) Big huge thank you to: Our collaborators: Paul Warren, Bryn Thomas, and Rebecca Clifford
More informationCloud, and Digital Iden1ty Management (DIM) Exis1ng DIMs and their Limita1ons Our Goals World of Group Signatures SPICE!
Cloud, and Digital Iden1ty Management (DIM) Exis1ng DIMs and their Limita1ons Our Goals World of Group Signatures SPICE! Simple Showcase 2 Cloud compu1ng has been envisioned as the next- genera1on architecture
More informationREAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT
REAL-TIME STREAMING ANALYTICS DATA IN, ACTION OUT SPOT THE ODD ONE BEFORE IT IS OUT flexaware.net Streaming analytics: from data to action Do you need actionable insights from various data streams fast?
More informationVision of Interoperability Jamie Ferguson, Stan Huff, Cris Ross
Vision of Interoperability Jamie Ferguson, Stan Huff, Cris Ross Evolu&on of Interoperability As HIE evolves, the interoperability framework standards advance for reliable exchange and data integra=on across
More informationWebsite Design. A Crash Course. Monique Sherre, monique@boxcarmarke4ng.com
Website Design A Crash Course Monique Sherre, monique@boxcarmarke4ng.com When & Why Do We Re- Design no mobile BoxcarMarke6ng.com aesthe6c update Raincoast.com legacy CMS ABCBookWorld.com new company,
More informationMega Modeling for Scien/fic Big Data Processing
Mega Modeling for Scien/fic Big Data Processing Stefano Ceri, Emanuele Della Valle (Politecnico di Milano) Dino Pedreschi, Roberto Trasar/ (ISTI- CNR and University of Pisa) 1 The context 2 Scenario BIG
More informationBig Data. The Big Picture. Our flexible and efficient Big Data solu9ons open the door to new opportuni9es and new business areas
Big Data The Big Picture Our flexible and efficient Big Data solu9ons open the door to new opportuni9es and new business areas What is Big Data? Big Data gets its name because that s what it is data that
More informationFinancial Services/Banking (Portable Technology) Healthcare (Portable Technology) SoPware in U8li8es Industry (Office Produc8vity- CRM)
To show examples of how SMBs use technology in a posi8ve way for their businesses at their desks or out of the office. Focusing this on the many companies that are under 50 employees on Cape Cod and surrounding
More informationThe Billion Dollar Product Online Privacy. Rui Miguel Feio Security Lead RSM Partners
The Billion Dollar Product Online Privacy Rui Miguel Feio Security Lead RSM Partners Agenda Introduc.on Free online services Nothing in life is for free Paid online web services How do they do it? Risks
More informationA Brief Overview of the Mobile App Ecosystem. September 13, 2012
A Brief Overview of the Mobile App Ecosystem September 13, 2012 Presenters Pam Dixon, Execu9ve Director, World Privacy Forum Jules Polonetsky, Director and Co- Chair, Future of Privacy Forum Nathan Good,
More informationTopic Extrac,on from Online Reviews for Classifica,on and Recommenda,on (2013) R. Dong, M. Schaal, M. P. O Mahony, B. Smyth
Topic Extrac,on from Online Reviews for Classifica,on and Recommenda,on (2013) R. Dong, M. Schaal, M. P. O Mahony, B. Smyth Lecture Algorithms to Analyze Big Data Speaker Hüseyin Dagaydin Heidelberg, 27
More informationAnalyzing Data to Make Be1er Decisions July 21, 2015. Trusted Analysis. Be1er Decisions. Stronger Department. / Page 1
Analyzing Data to Make Be1er Decisions July 21, 2015 Trusted Analysis. Be1er Decisions. Stronger Department. / Page 1 DHS MGMT CUBE: Integra(ng the Data Informa(on technology tool that integrates the Department
More informationCloud-Based Commissioning. Dale Davis Mark Walter Keithly Barber Associates
Cloud-Based Commissioning Dale Davis Mark Walter Keithly Barber Associates AIA Quality Assurance The Building Commissioning Association is a Registered Provider with The American Institute of Architects
More informationData Governance Framework: Bank of Canada
Data Governance Framework: Bank of Canada The views and opinions expressed herein are those of the author and do not necessarily reflect the official policy or posi8on of the Bank of Canada or any agency
More informationEffec%ve use of Social Media. Reuben Trusler Crea%ve Director U%lity Crea%ve
Effec%ve use of Social Media Reuben Trusler Crea%ve Director U%lity Crea%ve Once upon a %me Come up with a plan, maintain a presence... and always listen. A bit about me Crea%ve Director at U%lity Crea%ve
More informationAVOIDING SILOED DATA AND SILOED DATA MANAGEMENT
AVOIDING SILOED DATA AND SILOED DATA MANAGEMENT Dalton Cervo Author, Consultant, Management Expert September 2015 This presenta?on contains extracts from books that are: Copyright 2011 John Wiley & Sons,
More informationEnhancing the relativity between Content, Title and Meta Tags Based on Term Frequency in Lexical and Semantic Aspects
Enhancing the relativity between Content, Title and Meta Tags Based on Term Frequency in Lexical and Semantic Aspects Mohammad Farahmand, Abu Bakar MD Sultan, Masrah Azrifah Azmi Murad, Fatimah Sidi me@shahroozfarahmand.com
More informationIntroduc)on to. Eric Nagler 11/15/11
Introduc)on to Eric Nagler 11/15/11 What is Oozie? Oozie is a workflow scheduler for Hadoop Originally, designed at Yahoo! for their complex search engine workflows Now it is an open- source Apache incubator
More informationThe State of Social Media Measurement Standards
The State of Social Media Measurement Standards Presented by: Ka9e Delahaye Paine, SNCR Fellow, CEO KDPaine & Partners 6 th Annual SNCR Research Symposium November 3 4, Harvard University s Faculty Club
More informationBig Data Use Cases. At Salesforce.com. Narayan Bharadwaj Director, Product Management Salesforce.com. @nadubharadwaj
Big Data Use Cases At Salesforce.com Narayan Bharadwaj Director, Product Management Salesforce.com @nadubharadwaj Safe harbor Safe harbor statement under the Private Securi9es Li9ga9on Reform Act of 1995:
More informationDiscovering Computers Fundamentals, 2010 Edition. Living in a Digital World
Discovering Computers Fundamentals, 2010 Edition Living in a Digital World Objec&ves Overview Discuss the importance of project management, feasibility assessment, documenta8on, and data and informa8on
More informationThe Most Commonly Asked Questions on Mobile Surveys
With the global leader in data solu6ons and technology The Future of Mobile Data Collec6on Saran Ganesh, Director of Product Marke6ng Mobile Ken Roe, Vice President So=ware Engineering 2015 Survey Sampling
More informationCloudian The Storage Evolution to the Cloud.. Cloudian Inc. Pre Sales Engineering
Cloudian The Storage Evolution to the Cloud.. Cloudian Inc. Pre Sales Engineering Agenda Industry Trends Cloud Storage Evolu4on of Storage Architectures Storage Connec4vity redefined S3 Cloud Storage Use
More informationFirst Na)on Project Management Boot Camp
First Na)on Project Management Boot Camp Links to Learning - Ontario: Building a Sustainable Future Thunder Bay, Ontario What is a Project / Project Management? A project can be defined as a temporary
More informationAn Integrated Approach to Manage IT Network Traffic - An Overview Click to edit Master /tle style
An Integrated Approach to Manage IT Network Traffic - An Overview Click to edit Master /tle style Agenda A quick look at ManageEngine Tradi/onal Traffic Analysis Techniques & Tools Changing face of Network
More informationCombining learning approaches for incremental on-line parsing
ombining learning approaches for incremental on-line parsing Deryle Lonsdale (lonz@byu.edu) Brigham Young University Department of Linguiscs; 3186 JKHB rovo, UT 84602 USA Michael Manookin (mbm5@email.byu.edu)
More informationBig Data Challenges and Opportuni4es in Railway
Big Data Challenges and Opportuni4es in Railway KTN H2020 Big Data Info Day @ London Piraba Navaratnam, Maria Grazia Viglio4 RSSB 08 Dec 2015 Rail Safety and Standards Board RSSB is an expert body with
More informationDisaster Recovery Planning and Implementa6on. Chris Russel Director, IT Infrastructure and ISO Compu6ng and Network Services York University
Disaster Recovery Planning and Implementa6on Chris Russel Director, IT Infrastructure and ISO Compu6ng and Network Services York University Agenda Background for York s I.T. Disaster Recovery Planning
More information2003-2015 Take 5 Solutions - All Rights Reserved.
2003 - Take 5 Solutions - All Rights Reserved. Overview Why Take 5 Solu/ons? Take 5's Unique Advantages Leadership Team Product Offerings Direct Mail List Rental Email List Rental and Retarge/ng Social
More informationScenarios for Future Internet Business@Energy
Scenarios for Future Internet Business@Energy Global energy challenges Demographic dynamics Scarce resources Climate change Population growth 7.5 bill. in 2020 (+1.1 bill.) Megacities 27 megacities (>10
More informationGAME-CHANGING TRENDS IN SUPPLY CHAIN
customer teams FIRST focused ANNUAL on serving REPORT override system designations BY THE of SUPPLY available CHAIN MANAGEMENT FACULTY AT THE The research partners at UNIVERSITY Ernst and Young OF TENNESSEE
More information