Sentiment Analysis Innovation Leverage Social Signals to Business Advantage

Transcription

1 Sentiment Analysis Innovation Leverage Social Signals to Business Advantage April 29 & 30, 2015 San Francisco, CA JW Marriott, Union Square

2 Current Speakers Current Speakers Include: Staff Software Engineer, Google Chief Data Scientist, HireVue Chief Technical Officer, metamind Staff Technical Program Manager, Twitter Staff Software Engineer, LinkedIn Head of Text Analytics, Thomson Reuters Manager, R&D Machine Learning, Bloomberg Senior Data Scientist, Glassdoor Senior Research Scientist, Yahoo! Director, Data Science & Engineering, MyFitnessPal Director, Customer Analytics, Toyota Financial Big Data Architect, Skype & Many More..

3 Who Will You Meet? There is no question that IE. provides the gold standard events in the industry and will connect you with decision makers within the analytics industry. You will be meeting s e n i o r l ev e l ex e c u t i v e s f ro m m a j o r corporations and innovative small to medium size companies. Company Size Of Attendees Employees Employees Employees Less than 49 Employees 56% 81% Job Title Of Attendees 78% Attendees are at Director level or above 3% 21% President /Principal SVP/VP 12% C-Level 42% Snr. Director /Director 25% Attendees are companies with at least 300 employees 13% Global Head / Head 8% Snr. Manager /Manager 11% 8% Academic (1%) Past Delegates Include President, Analytics - Amazon Vice Data Scientist, - Twitter Director, - Yammer Director, Analytics Engineering Sr. Director - ebay - Google Exec Director, Marketing - EA Electronic Arts F TI L

4 About The Summit With the rise of social media in recent years online opinion is now a key indicator for businesses as to their customers wants and needs. The challenge remains to accurately analyze behavior and sentiment in order gain a crucial advantage over competitors. By using natural language processing, text analytics and computational linguistics organizations can begin to filter through the noise and begin to identify the relevant content within conversations. Offering more clarity than basic text analytics, sentiment analysis is the way forward for organizations who want to tap into the mind of the consumer. Illustrated intermittently with case studies, interactive panel sessions and deep-dive discussions, this summit offers solutions and insight from some of the leaders using sentiment analysis to great effect. Current Speaker Information Benjamin Taylor Chief Data Scientist HireVue I am "cloud boy". I have had experience setting up large GPU compute clusters the manual way with ip tables, NFS mounts, ssh keys, ssh cloud configs scripts, service configs, and all of the unexpected troubleshooting that comes with that. It sucks. Now I have seen the light with virtual cloud solutions like AWS and I am in heaven! I can do what use to take me weeks in minutes. Need a 1000 node hadoop/ cassandra/mysql cluster/sun grid/cluster? No problem! Need dynamic expansion/contraction? NO PROBLEM! Need a cloud AI optimizer? Oh wait, that doesn't exist yet... don't worry I am on it. Latest Text Feature Creation & Reduction Methods Demonstrated on Interview Ranking Models Ben will demonstrate in detail some of the many text features beyond just simple word or n-gram use. Automated feature engineering will also be demonstrated using deep learning techniques. Finally, after generating 100,000s of features how do you reduce the features effectively to reduce computation costs and increase accuracy. Metaheuristic feature reduction on distributed systems will be demonstrated to address automated feature reduction. Lastly, examples and data analysis will be presented with real interview data on one of the world's largest digital repositories of recorded interviews. Vita Markman Staff Software Engineer LinkedIn I am currently employed as a Staff Software Engineer at LinkedIn, where I work on various natural language processing applications such as performing sentiment a n a l ys i s of c u s t o m e r f e e d b a c k, m e m b e r d a t a standardization, and context-sensitive spam detection. Before joining LinkedIn, I was a Staff Research Engineer at Samsung Research America, where among other projects, I worked on extracting topic-indicative phrases from a stream of closed caption news data in real-time and textmining customer support chat-logs for common issues customers experience. Mining Topic-Based Sentiment in Customer Feedback at LinkedIn This talk addresses the topic-based sentiment analysis of customer support feedback focusing on the following questions 1) how do we find the most relevant topics of a product in question 2) how do we ensure to attribute sentiment to these specific topics as opposed to the feedback as a whole 3) how do we leverage natural language processing tools such as key phrase extraction, synonym identification, and summarization to make the obtained topic-sentiment information best suitable for human consumption. The model proposed here is extendable to mining sentiment in reviews or any other sentiment-bearing text.

5 Current Speaker Information Richard Socher Alessandro Chief Technical Gagliardi Officer Senior metamind Data Institute Scientist Glassdoor Richard Socher is the co-founder and CTO of MetaMind, a young machine learning company focused on pushing the Alessandro Gagliardi is a Sr. Data Scientist at Glassdoor state of the art in AI and making it accessible to many and an instructor of Data Science at General Assembly in people. More concretely, MetaMind uses deep learning and San Francisco. At Glassdoor, he uses big data and machine m a c h i n e l e a r n i n g t e c h n i q u e s t o s o l v e m a n y learning techniques to predict salaries and present the different natural language processing and computer vision best opportunities to job seekers. Prior to that, he worked problems. In 2014, Richard received his PhD from Stanford for Path, analyzing terabytes of customer activity logs to University working with Chris Manning and Andrew Ng. He provide business insights for product development. was awarded the 2011 Yahoo! Key Scientific Challenges Alessandro received his B.A. in Computer Science from the Award and a 2013 "Magic Grant" from the Brown Institute University of California. for Media Innovation. Deep Learning Applied to Real Problems Using Sentiment NLP analysis to is Improve both linguistically the Job interesting Hunting and Experience crucial to business intelligence. In this talk, I will first describe overly simple methods for sentiment analysis that Alessandro have been used will in discuss the past. his work Next, I in will applying describe machine current learning methods of techniques sentiment to analysis extrapolate and demo salaries an easy from to user generated tool for text content, and sentiment as well classification: providing statistical etcml.com. analysis In the of third search part, I will metrics introduce to more provide sophisticated a better models job hunting based experience on recursive for deep Glassdoor's learning customers. which I believe will eventually supersede currently used algorithms thanks to their improved performance. Jim Skinner Staff Technical Program Manager Twitter Jim Skinner has spent the last 20 years developing distributed platforms that enable the consumption of digital content. During his 14 years at Microsoft Jim helped bring MovieLink.com, Korea Telecom's MegaTV and Microsoft's IPTV (sold as AT&T U-Verse, British Telecom Vision, Deutsche Telekom T-Home, etc.) to life. At Netflix Jim focused on video encoding, the content ingestion pipeline and content recommendations. Jim is expanding the functionality of the Twitter client by providing technical program management of the Twitter Cards platform. The Business of Big Data Companies like Gnip, Google, IBM and Metamind are turning data analytics and machine learning into viable products. Will these commercial offerings overtake the "free to use" tools such as the Torch framework and Stanford's Classifier? This technical talk will focus on the marketplace for big data (who is buying what), the vendors trying to survive in that marketplace and their current product offerings. You'll learn about the difference between free and paid access to big data, the limitations of existing machine learning "products" and the opportunity this presents for data scientists. Zornitsa Kozareva Senior Research Scientist Yahoo! I am interested in natural language processing such as large-scale knowledge acquisition from the Web and its a p p l i c a t i o n to r e a l wo r l d p ro b l e m s l i k e n a m e disambiguation, entity extraction and paraphrase acquisition. I am also interested and have worked on machine learning, social media, sentiment analysis and graph-based algorithms for text processing. Multilingual Affect Polarity and Valence Prediction in Metaphors Understanding metaphor rich texts like "Her lawyer is a shark", "Time is money and the affect associated with them is a challenging problem, which has been of interest to the research community for a long time. I will introduce the task of multilingual sentiment analysis of metaphors and will present novel algorithms that integrate affective, perceptual and social processes with stylistic and lexical information. Finally, by running evaluations on datasets in English, Spanish, Farsi and Russian, I will show that the method is portable and works equally well when applied to different languages.

6 Current Speaker Information Chul Lee Alessandro Director, DataGagliardi Engineering & Science Senior MyFitnessPal Data Scientist Glassdoor As Director of Data Engineering & Science, Chul is Alessandro Gagliardi responsible for the development is a Sr. Data of Scientist data products at Glassdoor related andreal-time to an instructor nutrition of Data andscience fitness attracking, General insights Assembly and in San Francisco. community activities At Glassdoor, at MyFitnessPal. he uses bigchul dataholds and machine Ph.D. in learning techniques Computer Science from to predict University salaries of Toronto, and present where the he best opportunities focused on web algorithms to job seekers. andprior texttomining. that, hehe worked also for Path, analyzing authored many patents terabytes and papers of customer that appeared activity logs in topto provide business journals insightsand for product proceedings. development. tier peer-reviewed conference Alessandro received his B.A. in Computer Science from the University of California. Driving Real-Time Nutrition with Sentiment Using NLP to Improve the Job Hunting Analysis Experience Chul will discuss his work in leading the data engineering & Alessandro science team, willwith discuss a heavy his work focusin on applying text mining, machine at learning techniques MyFitnessPal for the development to extrapolate of data salaries products from related user generated to real-time content, nutrition as well and as fitness providing tracking, statistical insights analysis and of search activities. community metrics to provide a better job hunting experience for Glassdoor's customers. Nishant Rohatgi Director, Data & Analytics Toyota Financial Services Jim Skinner has spent the last 20 years developing distributed platforms that enable the consumption of digital content. During his 14 years at Microsoft Jim helped bring MovieLink.com, Korea Telecom's MegaTV and Microsoft's IPTV (sold as AT&T U-Verse, British Telecom Vision, Deutsche Telekom T-Home, etc.) to life. At Netflix Jim focused on video encoding, the content ingestion pipeline and content recommendations. Jim is expanding the functionality of the Twitter client by providing technical program management of the Twitter Cards platform. Text Mining as part of the Digital Services Strategy In this presentation, Nishant will use case studies of his experiences at Toyota Financial Services, where he successfully developed text/speech analytics modeling to promote a necessary shift to digital servicing strategy, saving over $8 million in costs so far. Saila Talagadadeevi Gary Kazantsev Big Data Architect Skype Manager, R&D Machine Learning Bloomberg I am a technology leader, an engineer, and an architect with strong experiences in Big Data, NLP, Information Retrieval, Machine Learning, NoSQL, server side programming, Linux system programming, and algorithm development. I have proven track record of building and managing engineering teams, delivering distributed computing products, and working with cross functional groups. Gary Kazantsev runs the R&D Machine Learning group at Bloomberg, leading research and projects at the intersection of computational linguistics and machine learning such as sentiment analysis, market impact indicators, text classification, social media analytics, question answering, recommendation systems and predictive modeling of financial markets. He holds degrees in physics, mathematics and computer science from Boston University.

7 The Information Sentiment Analysis Innovation Summit Date: Location: Venue: Accommodation: April 29 & 30, 2015 San Francisco, CA JW Marriott, Union Square Online Reservations, or call and quote Summit15 Registration Pricing Silver Pass Gold Pass Diamond Pass $1495 $1795 $1995 Access to all sessions & networking events 7 days access to presentations from the summit via ieondemand Access to all sessions, networking events & unlimited access to presentations from the summit via ieondemand Access to all sessions, networking events, annual subscription to all content on the Big Data & Analytics channels via ieondemand $1295 $1595 $1795 Early Bird Price (before Feb 27) Early Bird Price (before Feb 27) Early Bird Price (before Feb 27) Access All Areas Pass On-Demand Pass 1 Day Pass $2095 Diamond access to this summit & the Social Media & Web Analytics Summit. $895 $600 Full access to the sessions to your chosen day of the summit, 7 days access to presentations from the summit via ieondemand Unlimited access to presentations from the summit via ieondemand, including presentations, interviews & the ability to contact speakers $695 Unlimited access to summit presentations via ieondemand $1995 Early Bird Price (before Feb 27) Early Bird Price (before Feb 27) Group Discount Offers 3 Silver Passes: 5 Silver Passes: 3 Gold Passes: 5 Gold Passes: 3 Diamond Passes: 5 Diamond Passes: $3000 ($1000 per attendee) $4500 ($900 per attendee) $3900 ($1300 per attendee) $6000 ($1200 per attendee) $4500 ($1500 per attendee) $7000 ($1400 per attendee) For larger groups or special requests contact Andrew by calling or achristofi@theiegroup.com * Team discounts are applicable at the point of registration only. Ways to Register Register Online Here F TI L

8 Registration Form Sentiment Analysis Innovation Summit April 29 & 30, 2015 JW Marriott, Union Square San Francisco California For registration or more information on the program, please call Andrew on , or fax this registration form to +1 (323) Delegate Information... NAME OF EACH ATTENDEE TITLE OF EACH ATTENDEE DEPARTMENT COMPANY INDUSTRY ADDRESS CITY STATE/PROVINCE ZIP/POSTAL CODE COUNTRY OF EACH ATTENDEE BUSINESS PHONE NUMBER 2. Pass Types... Early Bird Pass Options until February 27, 2015 Early Bird Silver: $1295 Early Bird Gold: $1595 Early Bird Diamond: $1795 Regular Pass Options after February 27, 2015 Silver Pass: $1495 Gold Pass: $1795 Diamond Pass: $1995 Group Discount Pass Options 3 Silver Passes $3000 ($1000 per attendee) 5 Silver Passes $4500 ($900 per attendee) 3 Gold Passes $3900 ($1300 per attendee) 5 Gold Passes $6000 ($1200 per attendee) 3 Diamond Passes $4500 ($1500 per attendee) 5 Diamond Passes $7000 ($1400 per attendee) For larger groups or special requests contact Andrew Christofi by calling or achristofi@theiegroup.com Group passes only available when all participants register together. Pass Descriptions: Silver Pass: Access to all sessions & networking events Gold Pass: Access to all sessions, networking events & unlimited access to the summit presentations via ieondemand Diamond Pass: Access to all sessions, networking events, annual subscription to all content on the Big Data & Analytics channels via ieondemand 3. Payment Options... Check (Make checks payable to The Innovation Enterprise Ltd) Invoice me Visa Mastercard American Express Diners Club Discover CARD NUMBER EXPIRATION DATE SECURITY NO. CARDHOLDERS NAME CARDHOLDER S SIGNATURE BILLING ADDRESS INDUSTRY Prices are exclusive of VAT. Places are transferable without any charge to another Summit occurring within 12 months of the original purchase. Team discounts are applicable at the point of registration only. Any cancellations within a group registration will in turn incur an increase in registration fee for the remaining group participants. Cancellations before March 30, 2015 incur an administrative charge of 50%. If you cancel your registration after March 30, 2015 you will be charged the full fee. You must notify The Innovation Enterprise in writing of a cancellation, or you will be charged the full fee. The Innovation Enterprise reserve the right to make changes to the program without notice. NB: FULL PAYMENT MUST BE RECEIVED BEFORE THE EVENT.

9 Schedule Day One April 29 Session One Coffee Break Session Two Lunch Session Three Coffee Break Session Four Networking Drinks Day Two April 30 Session Five Coffee Break Session Six Lunch Session Seven Coffee Break Session Eight

10 Previous Sponsors Silver Sponsor Bronze Sponsor Exhibitor Exhibitor For sponsorship information contact Euan at F TI L