Challenges of Cloud Scale Natural Language Processing
|
|
|
- Samantha Dixon
- 10 years ago
- Views:
Transcription
1 Challenges of Cloud Scale Natural Language Processing Mark Dredze Johns Hopkins University
2 My Interests? Information Expressed in Human Language Machine Learning Natural Language Processing Intelligent User Interfaces
3 Some History Large scale computing resources Large scale data
4 Information Growth In the past 10 years 200 billion daily 100 million users 1 trillion URLs 18 million users 300 million users MySpace, Blogs, Podcasts, YouTube
5 Intelligent Information Systems Computers help us organize and understand information! Linguistically informed data driven learning User interfaces backed by intelligent systems Intelligent Management behaviors by role (CHI 2005) Activity management (IUI 2006) Summarization (IUI 2008) Triage and search (IJCAI 2009) Large scale data = tremendous opportunities Statistical NLP can change how we process information
6 Challenges of Cloud Scale With Great Data Comes Great Responsibility Learning high quality advanced NLP systems from data is not trivial The old way: carefully curated controlled corpora Advantages: easy to learn Disadvantages: small datasets The new way: large amounts of raw data Advantages: data is everyone you look! Disadvantages:
7 Today: Learning Challenges Outline Large scale learning Challenge: How can algorithms designed for thousands of examples scale to billions? Solution: Confidence-Weighted Learning Heterogeneous data Challenge: data is messy, highly varied and unpredictable: different domains, genres, languages, users, etc.? Solution: Apply Confidence-Weighted learning Multi-domain learning Recognizing domain shifts
8 A Learning Foundation Online learning algorithms for linear classifiers Updates hypothesis after every example (streaming) Ex. Perceptron, Winnow, MIRA Strength in simplicity Naturally handles many examples Widely used in many statistical NLP systems Weakness in naïve assumptions Few assumptions about data are naïve Limits the update options
9 Online Linear Classifiers Linear classifier A parameter for each feature Prediction: linear combination of parameters Binary classification = sign(prediction) Margin = abs(prediction) Classifier parameters (weight vector) Example Prediction Update: this example is negative! Change parameters to be more negative
10 Representing Data NLP represents data as sparse feature vectors I loved watching this sensational movie Even for simple tasks we have tens of thousands of features! Some much more common than others loved vs. sensational
11 Rare Features are Useful
12 Parameter Confidence Online classifier does not track feature frequency Intuition: the more a parameter is updated, the less it should change Solution: introduce parameter confidence More parameter confidence smaller changes
13 Confidence Weighted Learning Represent each parameter value as a Gaussian Why Gaussian? Mean: the parameter s value Variance: confidence in the parameter s value Learning: Update parameter: move mean Increase confidence: reduce variance Dredze et al. ICML 2008, Crammer et al. NIPS 2009, Crammer et al. EMNLP 2009
14 Confidence Weighted Update 1) 2) Objective: Condition: Smallest possible change to parameters Classify example correctly 1) min µ,σ D ( KL (µ,σ) (µ i,σ i )) Smallest change s.t. Pr y i (w x i ) 0 [ ] η 2) Correct with probability η η (0.5, 1) Sigma always decreases (more confident) Update weighted by covariance
15 Low Variance for Frequent or Useful Features
16 Take Away Message Intuition about language improves learning Parameter confidence improves learning CW beats Perceptron, MIRA, SGD, Maxent, SVM Useful in other settings Large scale learning Parallel training Heterogeneous data Multi-domain learning Recognizing domain shifts
17 Scaling Online Learning Cloud systems: many machines to process data Learn many linear classifiers across many machines Combine the final classifiers How should we combine many classifiers? Option 1: average Option 2: CW combinations Average CW Combination 1 million sentiment examples on 10 machines Single Machine Accuracy
18 Heterogeneous Data More data doesn t mean more of the same data More domains, genres, languages Algorithms must handle heterogeneous data Multi-domain learning A single classifier for many different domains Detecting domain shift When has the topic changed and impacted accuracy? We care about scale Use the online setting
19 Domain Change Example Sentiment classification: predict if a product review is positive or negative This book has interesting characters, a well developed plot, suspense, action, adventure. What I would expect from an award winning author.? This blender is durable, and affordable. It comes with a five year warranty and creates tasty smoothies. Training Data Test Data
20 Learning Across Domains Setting: domains interleaved for sentiment classification Assume we know domain for each example Training: given labels for learning Kitchen Electronics Movies Books Appliances Stream of product reviews Learn all domains at once!
21 Naïve Approaches Assume one data set Domains are different! Very long battery life vs. Very long movie Assume different data sets More similarities than differences! I loved this book vs. I loved this movie
22 Multi-Domain Learning How can we learn a system for a single task across many domains? Examples Sentiment classification across product types Spam classification across different users Named entity recognition across different genres
23 Combined Approach Shared parameters: a parameter for each feature regardless of domain Captures shared behaviors I loved this book vs. I loved this movie Domain parameters: a parameter for each feature in each domain Captures domain behaviors Very long battery life vs. Very long movie
24 Learning with New Parameters Combine domain specific and shared parameters for learning Classify examples with combined parameters Update parameters to change combined behavior How to combine parameters? How to learn with the combination? Confidence Weighted Learning
25 Combining Parameters Recall combining parameters from many machines Averaging Parameters 2 Shared CW Combination -1 Domain Specific.5 Combined
26 Learning We know how to combine parameters for prediction How do we update parameters? Shared behavior shared parameters Domain behavior domain parameters How do we know which features are which? Recall: Low variance means useful for prediction In combination, low variance contributes more New online update using combination!
27 Multi-Domain Regularization Domain parameters regularize each other We want parameters to be similar if possible (shared) New update using combination 1) Smallest parameter change 2) Classify example correctly Dredze and Crammer, 2008; Dredze et al. 2009
28 Evaluation on Sentiment Methods Proposed method: Multi-domain regularization Single classifier: best for shared behaviors Separate classifiers: best for domain specific behaviors Sentiment classification Rate product reviews: positive/negative 4 datasets All- 7 Amazon product types Books- different rating thresholds DVDs- different rating thresholds Books+DVDs 1500 train, 100 test per domain
29 Results Test Error Single Separate MDR 5 0 Books DVD Books+DVD All Test error (smaller better) 10-fold CV, one pass online training Books, DVDs, Books+DVDs p=.001
30 Discovering Domain Change Sentiment Classification System Movies Kitchen
31 Changing Domains Data changes in the real world and hurts accuracy If we knew we had a new domain Turn off a badly performing system! Fix it How do we know that we have a new domain? Detect when we encounter a new domain!
32 Detecting Domain Shifts Assumptions: A new domain will be signaled by Accuracy: classifier accuracy drops Margin: some features disappear= smaller margins We can t measure accuracy, can we use margins?
33 Improved Margins Margins are a signal of confidence Fewer important features less confidence Is there a better way to get confidence estimates? Confidence Weighted margin values from a Confidence Weighted classifier Linear combinations of Scalar parameters scalar margin Gaussian parameters Gaussian margin Mean = margin Variance = confidence in margin Normalized margins mean/variance 2
34 Domain Shift Accuracy Average Book Reviews Shift Margin DVD Reviews Average
35 Experiments Data Sentiment classification between domains Spam classification between users Named entity classification between genres News articles, broadcast news, telephone, blogs, etc. Simulate domain shifts between each pair 500 source examples, 1500 target examples CW margin for examples with source domain classifier Baseline: Support Vector Machine margin When does an A-Distance tracker detect change?
36 1200 SVM Margin CW Normalized Margin Num examples after change
37 Summary: Learning Challenges Large scale learning Scaling NLP systems using CW learning Parallelizes across the cloud Heterogeneous data Learn from heterogeneous data in an online setting Learn a single system across many domains Recognizing when data sources shift
38 Cloud Computing Opportunities Enormous data for NLP Challenge: diverse data processing Domains, genres, dialects, languages, users Challenge: scaling up methods Real systems informed by real users Challenge: building intelligent user facing systems Key: understanding what users wants We can change how people interact with information
39 Thank You Data, Code, More Info? Collaborators Koby Crammer: The Technion Alex Kulesza: University of Pennsylvania Tim Oates: University of Maryland - Baltimore County Fernando Pereira: Google Inc. Christine Piatko: Johns Hopkins University
Sentiment Analysis. D. Skrepetos 1. University of Waterloo. NLP Presenation, 06/17/2015
Sentiment Analysis D. Skrepetos 1 1 Department of Computer Science University of Waterloo NLP Presenation, 06/17/2015 D. Skrepetos (University of Waterloo) Sentiment Analysis NLP Presenation, 06/17/2015
Semi-Supervised Learning for Blog Classification
Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (2008) Semi-Supervised Learning for Blog Classification Daisuke Ikeda Department of Computational Intelligence and Systems Science,
Making Sense of the Mayhem: Machine Learning and March Madness
Making Sense of the Mayhem: Machine Learning and March Madness Alex Tran and Adam Ginzberg Stanford University [email protected] [email protected] I. Introduction III. Model The goal of our research
Machine Learning Final Project Spam Email Filtering
Machine Learning Final Project Spam Email Filtering March 2013 Shahar Yifrah Guy Lev Table of Content 1. OVERVIEW... 3 2. DATASET... 3 2.1 SOURCE... 3 2.2 CREATION OF TRAINING AND TEST SETS... 4 2.3 FEATURE
Multi-Domain Learning: When Do Domains Matter?
Multi-Domain Learning: When Do Domains Matter? Mahesh Joshi School of Computer Science Carnegie Mellon University Pittsburgh, PA, 15213, USA [email protected] Mark Dredze Human Language Technology Center
Employer Health Insurance Premium Prediction Elliott Lui
Employer Health Insurance Premium Prediction Elliott Lui 1 Introduction The US spends 15.2% of its GDP on health care, more than any other country, and the cost of health insurance is rising faster than
Chapter 6. The stacking ensemble approach
82 This chapter proposes the stacking ensemble approach for combining different data mining classifiers to get better performance. Other combination techniques like voting, bagging etc are also described
Single-Pass Online Learning: Performance, Voting Schemes and Online Feature Selection
Single-Pass Online Learning: Performance, Voting Schemes and Online Feature Selection ABSTRACT Vitor R. Carvalho a a Language Technologies Institute Carnegie Mellon University 5000 Forbes Avenue,Pittsburgh,
Data Mining - Evaluation of Classifiers
Data Mining - Evaluation of Classifiers Lecturer: JERZY STEFANOWSKI Institute of Computing Sciences Poznan University of Technology Poznan, Poland Lecture 4 SE Master Course 2008/2009 revised for 2010
A Systematic Cross-Comparison of Sequence Classifiers
A Systematic Cross-Comparison of Sequence Classifiers Binyamin Rozenfeld, Ronen Feldman, Moshe Fresko Bar-Ilan University, Computer Science Department, Israel [email protected], [email protected],
Author Gender Identification of English Novels
Author Gender Identification of English Novels Joseph Baena and Catherine Chen December 13, 2013 1 Introduction Machine learning algorithms have long been used in studies of authorship, particularly in
Classification of Bad Accounts in Credit Card Industry
Classification of Bad Accounts in Credit Card Industry Chengwei Yuan December 12, 2014 Introduction Risk management is critical for a credit card company to survive in such competing industry. In addition
Simple and efficient online algorithms for real world applications
Simple and efficient online algorithms for real world applications Università degli Studi di Milano Milano, Italy Talk @ Centro de Visión por Computador Something about me PhD in Robotics at LIRA-Lab,
Example: Credit card default, we may be more interested in predicting the probabilty of a default than classifying individuals as default or not.
Statistical Learning: Chapter 4 Classification 4.1 Introduction Supervised learning with a categorical (Qualitative) response Notation: - Feature vector X, - qualitative response Y, taking values in C
Big Data Analytics CSCI 4030
High dim. data Graph data Infinite data Machine learning Apps Locality sensitive hashing PageRank, SimRank Filtering data streams SVM Recommen der systems Clustering Community Detection Web advertising
Introduction to Machine Learning Lecture 1. Mehryar Mohri Courant Institute and Google Research [email protected]
Introduction to Machine Learning Lecture 1 Mehryar Mohri Courant Institute and Google Research [email protected] Introduction Logistics Prerequisites: basics concepts needed in probability and statistics
An Introduction to Machine Learning and Natural Language Processing Tools
An Introduction to Machine Learning and Natural Language Processing Tools Presented by: Mark Sammons, Vivek Srikumar (Many slides courtesy of Nick Rizzolo) 8/24/2010-8/26/2010 Some reasonably reliable
Statistical Machine Learning
Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes
Active Learning SVM for Blogs recommendation
Active Learning SVM for Blogs recommendation Xin Guan Computer Science, George Mason University Ⅰ.Introduction In the DH Now website, they try to review a big amount of blogs and articles and find the
Classification Problems
Classification Read Chapter 4 in the text by Bishop, except omit Sections 4.1.6, 4.1.7, 4.2.4, 4.3.3, 4.3.5, 4.3.6, 4.4, and 4.5. Also, review sections 1.5.1, 1.5.2, 1.5.3, and 1.5.4. Classification Problems
Jubatus: An Open Source Platform for Distributed Online Machine Learning
Jubatus: An Open Source Platform for Distributed Online Machine Learning Shohei Hido Seiya Tokui Preferred Infrastructure Inc. Tokyo, Japan {hido, tokui}@preferred.jp Satoshi Oda NTT Software Innovation
Forecasting stock markets with Twitter
Forecasting stock markets with Twitter Argimiro Arratia [email protected] Joint work with Marta Arias and Ramón Xuriguera To appear in: ACM Transactions on Intelligent Systems and Technology, 2013,
Server Load Prediction
Server Load Prediction Suthee Chaidaroon ([email protected]) Joon Yeong Kim ([email protected]) Jonghan Seo ([email protected]) Abstract Estimating server load average is one of the methods that
Sentiment analysis of Twitter microblogging posts. Jasmina Smailović Jožef Stefan Institute Department of Knowledge Technologies
Sentiment analysis of Twitter microblogging posts Jasmina Smailović Jožef Stefan Institute Department of Knowledge Technologies Introduction Popularity of microblogging services Twitter microblogging posts
CSE 473: Artificial Intelligence Autumn 2010
CSE 473: Artificial Intelligence Autumn 2010 Machine Learning: Naive Bayes and Perceptron Luke Zettlemoyer Many slides over the course adapted from Dan Klein. 1 Outline Learning: Naive Bayes and Perceptron
Analysis Tools and Libraries for BigData
+ Analysis Tools and Libraries for BigData Lecture 02 Abhijit Bendale + Office Hours 2 n Terry Boult (Waiting to Confirm) n Abhijit Bendale (Tue 2:45 to 4:45 pm). Best if you email me in advance, but I
Anti-Spam Filter Based on Naïve Bayes, SVM, and KNN model
AI TERM PROJECT GROUP 14 1 Anti-Spam Filter Based on,, and model Yun-Nung Chen, Che-An Lu, Chao-Yu Huang Abstract spam email filters are a well-known and powerful type of filters. We construct different
BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES
BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 123 CHAPTER 7 BEHAVIOR BASED CREDIT CARD FRAUD DETECTION USING SUPPORT VECTOR MACHINES 7.1 Introduction Even though using SVM presents
Sentiment analysis on tweets in a financial domain
Sentiment analysis on tweets in a financial domain Jasmina Smailović 1,2, Miha Grčar 1, Martin Žnidaršič 1 1 Dept of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia 2 Jožef Stefan International
Introduction to Data Mining
Introduction to Data Mining 1 Why Data Mining? Explosive Growth of Data Data collection and data availability Automated data collection tools, Internet, smartphones, Major sources of abundant data Business:
Predicting Flight Delays
Predicting Flight Delays Dieterich Lawson [email protected] William Castillo [email protected] Introduction Every year approximately 20% of airline flights are delayed or cancelled, costing
Defending Networks with Incomplete Information: A Machine Learning Approach. Alexandre Pinto [email protected] @alexcpsec @MLSecProject
Defending Networks with Incomplete Information: A Machine Learning Approach Alexandre Pinto [email protected] @alexcpsec @MLSecProject Agenda Security Monitoring: We are doing it wrong Machine Learning
Sentiment Analysis of Movie Reviews and Twitter Statuses. Introduction
Sentiment Analysis of Movie Reviews and Twitter Statuses Introduction Sentiment analysis is the task of identifying whether the opinion expressed in a text is positive or negative in general, or about
Challenges for Data Driven Systems
Challenges for Data Driven Systems Eiko Yoneki University of Cambridge Computer Laboratory Quick History of Data Management 4000 B C Manual recording From tablets to papyrus to paper A. Payberah 2014 2
MACHINE LEARNING IN HIGH ENERGY PHYSICS
MACHINE LEARNING IN HIGH ENERGY PHYSICS LECTURE #1 Alex Rogozhnikov, 2015 INTRO NOTES 4 days two lectures, two practice seminars every day this is introductory track to machine learning kaggle competition!
How to Win at the Track
How to Win at the Track Cary Kempston [email protected] Friday, December 14, 2007 1 Introduction Gambling on horse races is done according to a pari-mutuel betting system. All of the money is pooled,
Beating the NCAA Football Point Spread
Beating the NCAA Football Point Spread Brian Liu Mathematical & Computational Sciences Stanford University Patrick Lai Computer Science Department Stanford University December 10, 2010 1 Introduction Over
Learning to Process Natural Language in Big Data Environment
CCF ADL 2015 Nanchang Oct 11, 2015 Learning to Process Natural Language in Big Data Environment Hang Li Noah s Ark Lab Huawei Technologies Part 1: Deep Learning - Present and Future Talk Outline Overview
Semi-Supervised Support Vector Machines and Application to Spam Filtering
Semi-Supervised Support Vector Machines and Application to Spam Filtering Alexander Zien Empirical Inference Department, Bernhard Schölkopf Max Planck Institute for Biological Cybernetics ECML 2006 Discovery
Computer-Based Text- and Data Analysis Technologies and Applications. Mark Cieliebak 9.6.2015
Computer-Based Text- and Data Analysis Technologies and Applications Mark Cieliebak 9.6.2015 Data Scientist analyze Data Library use 2 About Me Mark Cieliebak + Software Engineer & Data Scientist + PhD
Predict the Popularity of YouTube Videos Using Early View Data
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
Statistics for BIG data
Statistics for BIG data Statistics for Big Data: Are Statisticians Ready? Dennis Lin Department of Statistics The Pennsylvania State University John Jordan and Dennis K.J. Lin (ICSA-Bulletine 2014) Before
Supervised Learning (Big Data Analytics)
Supervised Learning (Big Data Analytics) Vibhav Gogate Department of Computer Science The University of Texas at Dallas Practical advice Goal of Big Data Analytics Uncover patterns in Data. Can be used
Azure Machine Learning, SQL Data Mining and R
Azure Machine Learning, SQL Data Mining and R Day-by-day Agenda Prerequisites No formal prerequisites. Basic knowledge of SQL Server Data Tools, Excel and any analytical experience helps. Best of all:
Information Management course
Università degli Studi di Milano Master Degree in Computer Science Information Management course Teacher: Alberto Ceselli Lecture 01 : 06/10/2015 Practical informations: Teacher: Alberto Ceselli ([email protected])
Applying Data Science to Sales Pipelines for Fun and Profit
Applying Data Science to Sales Pipelines for Fun and Profit Andy Twigg, CTO, C9 @lambdatwigg Abstract Machine learning is now routinely applied to many areas of industry. At C9, we apply machine learning
Machine Learning in Spam Filtering
Machine Learning in Spam Filtering A Crash Course in ML Konstantin Tretyakov [email protected] Institute of Computer Science, University of Tartu Overview Spam is Evil ML for Spam Filtering: General Idea, Problems.
Distributed Computing and Big Data: Hadoop and MapReduce
Distributed Computing and Big Data: Hadoop and MapReduce Bill Keenan, Director Terry Heinze, Architect Thomson Reuters Research & Development Agenda R&D Overview Hadoop and MapReduce Overview Use Case:
Predicting Soccer Match Results in the English Premier League
Predicting Soccer Match Results in the English Premier League Ben Ulmer School of Computer Science Stanford University Email: [email protected] Matthew Fernandez School of Computer Science Stanford University
1 Maximum likelihood estimation
COS 424: Interacting with Data Lecturer: David Blei Lecture #4 Scribes: Wei Ho, Michael Ye February 14, 2008 1 Maximum likelihood estimation 1.1 MLE of a Bernoulli random variable (coin flips) Given N
Predicting the Stock Market with News Articles
Predicting the Stock Market with News Articles Kari Lee and Ryan Timmons CS224N Final Project Introduction Stock market prediction is an area of extreme importance to an entire industry. Stock price is
Search Taxonomy. Web Search. Search Engine Optimization. Information Retrieval
Information Retrieval INFO 4300 / CS 4300! Retrieval models Older models» Boolean retrieval» Vector Space model Probabilistic Models» BM25» Language models Web search» Learning to Rank Search Taxonomy!
Machine Learning. Chapter 18, 21. Some material adopted from notes by Chuck Dyer
Machine Learning Chapter 18, 21 Some material adopted from notes by Chuck Dyer What is learning? Learning denotes changes in a system that... enable a system to do the same task more efficiently the next
Recognizing Informed Option Trading
Recognizing Informed Option Trading Alex Bain, Prabal Tiwaree, Kari Okamoto 1 Abstract While equity (stock) markets are generally efficient in discounting public information into stock prices, we believe
Towards better accuracy for Spam predictions
Towards better accuracy for Spam predictions Chengyan Zhao Department of Computer Science University of Toronto Toronto, Ontario, Canada M5S 2E4 [email protected] Abstract Spam identification is crucial
NetView 360 Product Description
NetView 360 Product Description Heterogeneous network (HetNet) planning is a specialized process that should not be thought of as adaptation of the traditional macro cell planning process. The new approach
Practical Data Science with Azure Machine Learning, SQL Data Mining, and R
Practical Data Science with Azure Machine Learning, SQL Data Mining, and R Overview This 4-day class is the first of the two data science courses taught by Rafal Lukawiecki. Some of the topics will be
Learning is a very general term denoting the way in which agents:
What is learning? Learning is a very general term denoting the way in which agents: Acquire and organize knowledge (by building, modifying and organizing internal representations of some external reality);
Linear smoother. ŷ = S y. where s ij = s ij (x) e.g. s ij = diag(l i (x)) To go the other way, you need to diagonalize S
Linear smoother ŷ = S y where s ij = s ij (x) e.g. s ij = diag(l i (x)) To go the other way, you need to diagonalize S 2 Online Learning: LMS and Perceptrons Partially adapted from slides by Ryan Gabbard
Anomaly detection. Problem motivation. Machine Learning
Anomaly detection Problem motivation Machine Learning Anomaly detection example Aircraft engine features: = heat generated = vibration intensity Dataset: New engine: (vibration) (heat) Density estimation
Lecture 9: Introduction to Pattern Analysis
Lecture 9: Introduction to Pattern Analysis g Features, patterns and classifiers g Components of a PR system g An example g Probability definitions g Bayes Theorem g Gaussian densities Features, patterns
How can we discover stocks that will
Algorithmic Trading Strategy Based On Massive Data Mining Haoming Li, Zhijun Yang and Tianlun Li Stanford University Abstract We believe that there is useful information hiding behind the noisy and massive
Projektgruppe. Categorization of text documents via classification
Projektgruppe Steffen Beringer Categorization of text documents via classification 4. Juni 2010 Content Motivation Text categorization Classification in the machine learning Document indexing Construction
II. RELATED WORK. Sentiment Mining
Sentiment Mining Using Ensemble Classification Models Matthew Whitehead and Larry Yaeger Indiana University School of Informatics 901 E. 10th St. Bloomington, IN 47408 {mewhiteh, larryy}@indiana.edu Abstract
Knowledge Discovery from patents using KMX Text Analytics
Knowledge Discovery from patents using KMX Text Analytics Dr. Anton Heijs [email protected] Treparel Abstract In this white paper we discuss how the KMX technology of Treparel can help searchers
Why Semantic Analysis is Better than Sentiment Analysis. A White Paper by T.R. Fitz-Gibbon, Chief Scientist, Networked Insights
Why Semantic Analysis is Better than Sentiment Analysis A White Paper by T.R. Fitz-Gibbon, Chief Scientist, Networked Insights Why semantic analysis is better than sentiment analysis I like it, I don t
Applying Machine Learning to Stock Market Trading Bryce Taylor
Applying Machine Learning to Stock Market Trading Bryce Taylor Abstract: In an effort to emulate human investors who read publicly available materials in order to make decisions about their investments,
203.4770: Introduction to Machine Learning Dr. Rita Osadchy
203.4770: Introduction to Machine Learning Dr. Rita Osadchy 1 Outline 1. About the Course 2. What is Machine Learning? 3. Types of problems and Situations 4. ML Example 2 About the course Course Homepage:
Investigation of Support Vector Machines for Email Classification
Investigation of Support Vector Machines for Email Classification by Andrew Farrugia Thesis Submitted by Andrew Farrugia in partial fulfillment of the Requirements for the Degree of Bachelor of Software
Segmentation and Classification of Online Chats
Segmentation and Classification of Online Chats Justin Weisz Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 [email protected] Abstract One method for analyzing textual chat
Analysis of kiva.com Microlending Service! Hoda Eydgahi Julia Ma Andy Bardagjy December 9, 2010 MAS.622j
Analysis of kiva.com Microlending Service! Hoda Eydgahi Julia Ma Andy Bardagjy December 9, 2010 MAS.622j What is Kiva? An organization that allows people to lend small amounts of money via the Internet
Learning Gaussian process models from big data. Alan Qi Purdue University Joint work with Z. Xu, F. Yan, B. Dai, and Y. Zhu
Learning Gaussian process models from big data Alan Qi Purdue University Joint work with Z. Xu, F. Yan, B. Dai, and Y. Zhu Machine learning seminar at University of Cambridge, July 4 2012 Data A lot of
How To Bet On An Nfl Football Game With A Machine Learning Program
Beating the NFL Football Point Spread Kevin Gimpel [email protected] 1 Introduction Sports betting features a unique market structure that, while rather different from financial markets, still boasts
MAXIMIZING RETURN ON DIRECT MARKETING CAMPAIGNS
MAXIMIZING RETURN ON DIRET MARKETING AMPAIGNS IN OMMERIAL BANKING S 229 Project: Final Report Oleksandra Onosova INTRODUTION Recent innovations in cloud computing and unified communications have made a
HELP DESK SYSTEMS. Using CaseBased Reasoning
HELP DESK SYSTEMS Using CaseBased Reasoning Topics Covered Today What is Help-Desk? Components of HelpDesk Systems Types Of HelpDesk Systems Used Need for CBR in HelpDesk Systems GE Helpdesk using ReMind
Ensemble Methods. Knowledge Discovery and Data Mining 2 (VU) (707.004) Roman Kern. KTI, TU Graz 2015-03-05
Ensemble Methods Knowledge Discovery and Data Mining 2 (VU) (707004) Roman Kern KTI, TU Graz 2015-03-05 Roman Kern (KTI, TU Graz) Ensemble Methods 2015-03-05 1 / 38 Outline 1 Introduction 2 Classification
Oracle Advanced Analytics 12c & SQLDEV/Oracle Data Miner 4.0 New Features
Oracle Advanced Analytics 12c & SQLDEV/Oracle Data Miner 4.0 New Features Charlie Berger, MS Eng, MBA Sr. Director Product Management, Data Mining and Advanced Analytics [email protected] www.twitter.com/charliedatamine
Data Mining Yelp Data - Predicting rating stars from review text
Data Mining Yelp Data - Predicting rating stars from review text Rakesh Chada Stony Brook University [email protected] Chetan Naik Stony Brook University [email protected] ABSTRACT The majority
Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence
Artificial Neural Networks and Support Vector Machines CS 486/686: Introduction to Artificial Intelligence 1 Outline What is a Neural Network? - Perceptron learners - Multi-layer networks What is a Support
Part III: Machine Learning. CS 188: Artificial Intelligence. Machine Learning This Set of Slides. Parameter Estimation. Estimation: Smoothing
CS 188: Artificial Intelligence Lecture 20: Dynamic Bayes Nets, Naïve Bayes Pieter Abbeel UC Berkeley Slides adapted from Dan Klein. Part III: Machine Learning Up until now: how to reason in a model and
Knowledge Discovery and Data Mining. Bootstrap review. Bagging Important Concepts. Notes. Lecture 19 - Bagging. Tom Kelsey. Notes
Knowledge Discovery and Data Mining Lecture 19 - Bagging Tom Kelsey School of Computer Science University of St Andrews http://tom.host.cs.st-andrews.ac.uk [email protected] Tom Kelsey ID5059-19-B &
Can Twitter provide enough information for predicting the stock market?
Can Twitter provide enough information for predicting the stock market? Maria Dolores Priego Porcuna Introduction Nowadays a huge percentage of financial companies are investing a lot of money on Social
Clustering Big Data. Anil K. Jain. (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012
Clustering Big Data Anil K. Jain (with Radha Chitta and Rong Jin) Department of Computer Science Michigan State University November 29, 2012 Outline Big Data How to extract information? Data clustering
Sentiment Analysis of Twitter Feeds for the Prediction of Stock Market Movement
Sentiment Analysis of Twitter Feeds for the Prediction of Stock Market Movement Ray Chen, Marius Lazer Abstract In this paper, we investigate the relationship between Twitter feed content and stock market
Using Twitter as a source of information for stock market prediction
Using Twitter as a source of information for stock market prediction Ramon Xuriguera ([email protected]) Joint work with Marta Arias and Argimiro Arratia ERCIM 2011, 17-19 Dec. 2011, University of
VCU-TSA at Semeval-2016 Task 4: Sentiment Analysis in Twitter
VCU-TSA at Semeval-2016 Task 4: Sentiment Analysis in Twitter Gerard Briones and Kasun Amarasinghe and Bridget T. McInnes, PhD. Department of Computer Science Virginia Commonwealth University Richmond,
Sentiment Analysis Tool using Machine Learning Algorithms
Sentiment Analysis Tool using Machine Learning Algorithms I.Hemalatha 1, Dr. G. P Saradhi Varma 2, Dr. A.Govardhan 3 1 Research Scholar JNT University Kakinada, Kakinada, A.P., INDIA 2 Professor & Head,
Predict Influencers in the Social Network
Predict Influencers in the Social Network Ruishan Liu, Yang Zhao and Liuyu Zhou Email: rliu2, yzhao2, [email protected] Department of Electrical Engineering, Stanford University Abstract Given two persons
The Big Data Paradigm Shift. Insight Through Automation
The Big Data Paradigm Shift Insight Through Automation Agenda The Problem Emcien s Solution: Algorithms solve data related business problems How Does the Technology Work? Case Studies 2013 Emcien, Inc.
