Who Needs Polls? Gauging Public Opinion from Twitter Data David Cummings Haruki Oh Ningxuan (Jason) Wang.

Slides:



Advertisements
Similar presentations
From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series Brendan O’Connor Ramnath Balasubramanyan Bryan R. Routledge Noah A. Smith Carnegie.
Advertisements

Sentiment Analysis on Twitter Data
Confidence Intervals for Population Means
#Retweet this: HIV stigma in the twitterverse Miriam Y. Vega, PhD Latino Commission on AIDS & SPSSI UN NGO Abstract: TUAD0301.
Tweet Classification for Political Sentiment Analysis Micol Marchetti-Bowick.
Distant Supervision for Emotion Classification in Twitter posts 1/17.
Subjectivity and Sentiment Analysis of Arabic Tweets with Limited Resources Supervisor Dr. Verena Rieser Presented By ESHRAG REFAEE OSACT 27 May 2014.
Prediction and sentiment analysis Mahsa Elyasi.
SemEval 2013 Task 2 Labs AVAYA: Sentiment Analysis in Twitter with Self-Training and Polarity Lexicon Expansion Lee Becker, George Erhart, David Skiba,
Sentiment Analysis An Overview of Concepts and Selected Techniques.
Approaches to Sentiment Analysis MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way Based in part on notes from Aditya Joshi.
S ENTIMENTAL A NALYSIS O F B LOGS B Y C OMBINING L EXICAL K NOWLEDGE W ITH T EXT C LASSIFICATION. 1 By Prem Melville, Wojciech Gryc, Richard D. Lawrence.
Social network analysis of the West African Ebola Outbreak INTRODUCTION The Ebola outbreak in West Africa has drawn the World’s attention given the spread.
UNITED NATIONS HUMAN RIGHTS COMMISSION WORKSHOP ON UNILATERAL COERCIVE MEASURES Gallup World Poll Iran May 23, 2014 Geneva.
Extracting Strong Sentiment Trends from Twitter Patrick Lai Computer Science Department Stanford University.
1 Proximity-Based Opinion Retrieval Mark CarmanFabio CrestaniShima Gerani.
CSE 300: Software Reliability Engineering Topics covered: Software metrics and software reliability Software complexity and software quality.
Analyzing Sentiment in a Large Set of Web Data while Accounting for Negation AWIC 2011 Bas Heerschop Erasmus School of Economics Erasmus University Rotterdam.
Forecasting with Twitter data Presented by : Thusitha Chandrapala MARTA ARIAS, ARGIMIRO ARRATIA, and RAMON XURIGUERA.
More than words: Social networks’ text mining for consumer brand sentiments A Case on Text Mining Key words: Sentiment analysis, SNS Mining Opinion Mining,
(ACM KDD 09’) Prem Melville, Wojciech Gryc, Richard D. Lawrence
Public Opinion, Political Socialization and the Media
| Social Intelligence Guide for Marketing 6 essential social listening metrics.
Mid-Term Election Outlook & 2011 Policy Implications October 2010 Daniel Clifton
Cook’s Tour of American Politics and Economics Published February 13, 2013 Updated August 26, 2015 National Journal Presentation Credits Contributors:
Question # 1 For $100 15$1,000,000 14$500,000 13$250,000 12$125,000 11$64,000 10$32,000 9$16,000 8$8,000 7$4,000 6$2,000 5$1,000 4$500 3$300 2$200 1$100.
Election News and Numbers Making sense of polls, statistics and more for the 2008 election!
120 Exchange Street Portland Maine 1 October 2010 Maine Voter Preference Study – Wave III Prepared for: Maine Today Media October.
*Erasmus University Rotterdam P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands † Teezir BV Wilhelminapark 46, NL-3581 NL, Utrecht, the Netherlands.
How Useful are Your Comments? Analyzing and Predicting YouTube Comments and Comment Ratings Stefan Siersdorfer, Sergiu Chelaru, Wolfgang Nejdl, Jose San.
Prediction of Influencers from Word Use Chan Shing Hei.
CIKM Opinion Retrieval from Blogs Wei Zhang 1 Clement Yu 1 Weiyi Meng 2 1 Department of.
TEXT ANALYTICS - LABS Maha Althobaiti Udo Kruschwitz Massimo Poesio.
Evaluating Results of Learning Blaž Zupan
​ Text Analytics ​ Teradata & Sabanci University ​ April, 2015.
Poorva Potdar Sentiment and Textual analysis of Create-Debate data EECS 595 – End Term Project.
Financial Statistics Unit 2: Modeling a Business Chapter 2.2: Linear Regression.
Recognizing Stances in Online Debates Unsupervised opinion analysis method for debate-side classification. Mine the web to learn associations that are.
Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales Bo Pang and Lillian Lee Cornell University Carnegie.
Comparative Experiments on Sentiment Classification for Online Product Reviews Hang Cui, Vibhu Mittal, and Mayur Datar AAAI 2006.
KNN & Naïve Bayes Hongning Wang Today’s lecture Instance-based classifiers – k nearest neighbors – Non-parametric learning algorithm Model-based.
1 Adaptive Subjective Triggers for Opinionated Document Retrieval (WSDM 09’) Kazuhiro Seki, Kuniaki Uehara Date: 11/02/09 Speaker: Hsu, Yu-Wen Advisor:
From Change to Change: Obama and the Tea Party in 2010 Presented by Terry Nelson November 30, 2010 International Democrat Union.
A Generation Model to Unify Topic Relevance and Lexicon-based Sentiment for Opinion Retrieval Min Zhang, Xinyao Ye Tsinghua University SIGIR
Objectivity of the Aleksandr Sinayev PhD Candidate, Quantitative Psychology Ohio State University.
-Rolling Stones “I CANT GET NO… UTILITY?”.  Utility  Way we measure satisfaction, it can factor out our emotions and subjective feelings  Consumers.
Frankfurt (Germany), 6-9 June 2011 HOW THE CUSTOMERS PERCEIVE THE PROBLEM OF VOLTAGE QUALITY Martin KAŠPÍREK David MEZERA
Charlie Cook’s Five Factors to Watch in 2015 Published October 4, 2013 Updated July 6, 2015 National Journal Presentation Credits Contributors: Charlie.
Charlie Cook’s Tour of American Politics and Economics February 23, 2016 First Published: February 13, 2013 Producer: Alexander Perry With Contributions.
2014 Lexicon-Based Sentiment Analysis Using the Most-Mentioned Word Tree Oct 10 th, 2014 Bo-Hyun Kim, Sr. Software Engineer With Lina Chen, Sr. Software.
National Update May 2016 Bill McInturff SLIDE 1. SLIDE 2 Public Opinion Strategies—May 2016 SLIDE 2 Heading into the Election Year.
Measuring User Influence in Twitter: The Million Follower Fallacy Meeyoung Cha Hamed Haddadi Fabricio Benevenuto Krishna P. Gummadi.
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
Alvin CHAN Kay CHEUNG Alex YING Relationship between Twitter Events and Real-life.
Our path Understanding emphaty in a Twitter community - Valerio Cestrone, Simona Balbi, Agnieszka Stawinoga What empathy is ? How can be measured on Twitter.
PUBLIC OPINION Chapter 6. The Power of Public Opinion  The Power of Presidential Approval  What Is Public Opinion?  Expressed through voting  The.
Influence detection of famous personalities using Politeness and Likeability Navita Jain.
KNN & Naïve Bayes Hongning Wang
COMPARING POLLS AND MARKETS
Name: Sushmita Laila Khan Affiliation: Georgia Southern University
TITLE: Detection and Polarization of Political Sentiments on Twitter
Sentiment analysis tools
Retrieval of audio testimonials via voice search
Past and Present: Verb Tenses Across Blog Topics
Network of Twitter interactions.
Public Opinion Chapter 10.
Sentiment/opinion analysis
Audience Interaction Why I’m using Twitter and Facebook
Big Data Environment. Analysing Public Perceptions of South Africa’s Local Elections by using Geo-located Twitter Data.
Presentation transcript:

Who Needs Polls? Gauging Public Opinion from Twitter Data David Cummings Haruki Oh Ningxuan (Jason) Wang

From Tweets to Poll Numbers Motivation: People spend millions of dollars on polling every year: politics, economy, entertainment Millions of posts on Twitter every day Can we model public opinion using tweets? Data: 476 million tweets from June to December 2009, courtesy of Jure Lescovec Public polls from The Gallup Organization (presidential approval, economic confidence) and Rasmussen Reports (generic Congressional ballot) Goal: high correlation with public opinion polls All correlation figures for 6-day smoothing window

Approach 1: Volume The simplest metric: percentage of tweets that mention a given topic in a certain time window Moderate negative correlation (-36.3%, -35.7%) for economy and Congressional ballot: mention things you want to complain about more often Higher correlation (52.4%) for Obama

Approach 2: Generic Sentiment Can we distinguish between positive and negative sentiment of tweets? University of Pennsylvania OpinionFinder subjective polarity lexicon “conceited”strong negative-10 “ironic”weak negative-5 “trendy”weak positive+5 “illuminating”strong positive+10 Sum word scores for a tweet to classify it as positive, negative, or neutral; then subtract negative counts from positive counts and normalize over window

Approach 2: Generic Sentiment Good results on economic confidence: 60.4% correlation, 70.1% correlation on 15-day window Poor performance on presidential approval and Congressional ballot: -24.5% and 21.5% correlation respectively Sentiment about politics expressed differently?

Approach 3: LM-based Classification Train three language models (positive, negative, and neutral) on hand-classified data Classify each tweet according to the language model that affords it the highest probability Applied for the case of Obama: manually classified 3,633 tweets “can we all talk about how awesome Obama is?” “that Obama sticker on your car might as well say ‘Yes I’m stupid’ #tcot #iamthemob #teaparty #glennbeck” Then we tested the language models: best performer was a linearly interpolated bigram model

Approach 3: LM-based Classification Much-improved results on presidential approval: 49.4% correlation Throwing out retweets and duplicate tweets helps a little more: 55.9% correlation Finally, combining both volume and LM-based sentiment gives best results: 63.3% correlation, or 69.6% correlation on a 15-day window