Inferring User Political Preferences from Streaming Communications Svitlana Volkova 1, Glen Coppersmith 2 and Benjamin Van Durme 1,2 1 Center for Language.

Slides:



Advertisements
Similar presentations
1 ©2009 MeeMix MeeMix – A personalized Experience.
Advertisements

Leveraging FaceBook for Your Business March 3 rd, 2010.
Chapter 9: Customer Service via Technology
Online Max-Margin Weight Learning with Markov Logic Networks Tuyen N. Huynh and Raymond J. Mooney Machine Learning Group Department of Computer Science.
Alexander Statnikov1, Douglas Hardin1,2, Constantin Aliferis1,3
Faster Language Learning with Englishtown Englishtown IMS GLC Learning Impact Award Last Update: 25 th Mar, 2011.
L3S Research Center University of Hanover Germany
COPYRIGHT © 2011 ALCATEL-LUCENT. ALL RIGHTS RESERVED. INFORM: a dynamic INterest FORwarding Mechanism for Information Centric Networking Raffaele Chiocchetti,
1 ©2009 MeeMix MeeMix – A personalized Experience.
The Draft of Lithuanian Information Society Development Strategy for
March 2012 Therese Sheehan New Jersey Department of Education Office of Special Education Professional Development Requirements for Educational Interpreters.
Measurement and Analysis of Online Social Networks 1 A. Mislove, M. Marcon, K Gummadi, P. Druschel, B. Bhattacharjee Presentation by Shahan Khatchadourian.
BURSTY SUBGRAPHS IN SOCIAL NETWORKS. Introduction 2.
Bayesian network for gene regulatory network construction
Finding a needle in Haystack Facebook’s Photo Storage
Vanderbilt Sports Medicine Discharge Instructions for Youth Sports- Related Concussions in the Pediatric Emergency Department Mark Riederer,
Sl No Top-up Amount No Of Affiliate Ads Payment Per Day By Affiliate Ad Total Affiliate Ad Income 1.5,000/- Daily 2 ad for 100 days 100/- Affiliate.
Université du Québec École de technologie supérieure Face Recognition in Video Using What- and-Where Fusion Neural Network Mamoudou Barry and Eric Granger.
Influenza Vaccine Manufacturing
Virtual Distance: A Generalized Metric for Overlay Tree Construction ISCC12 July Suat Mercan (Zirve University) & Murat Yuksel (University of Nevada,
Nam P. Nguyen, Thang N. Dinh, Sindhura Tokala and My T. Thai
SEO in 2010 January 21 st, 2010 Steve Thomas President, The Net Impact.
More Usability Testing – Better User Experience New Trends – Remaining Challenges Silvia Zimmermann UPA International.
Penn State Smeal MBA Program Establishing your LinkedIn Profile presented by Emily Giacomini August 22, 2012.
Landmark-Based User Location Inference in Social Media YUTO YAMAGUCHI †, TOSHIYUKI AMAGASA † AND HIROYUKI KITAGAWA † †UNIVERSITY OF TSUKUBA 13/10/08 COSN.
University of Minnesota Location-based & Preference-Aware Recommendation Using Sparse Geo-Social Networking Data Location-based & Preference-Aware Recommendation.
Media Playground 2013 #mtplayground Social TV analytics A look at the new engagement metrics An overview of the social TV market and SecondSync analysis.
Tweeting, Twittering & Twitterdom Dr Matthew Coxon.
Partitioning Social Networks for Fast Retrieval of Time-dependent Queries Mindi Yuan, David Stein, Berenice Carrasco, Joana Trindade, Yi Lu University.
LANDSCAPE 2012 Engagement and Radio 1. LANDSCAPE % A personal, para-social interaction with their favorite Radio personality 79% Listen longer.
1/26Remco Chang – Dagstuhl 14 Analyzing User Interactions for Data and User Modeling Remco Chang Assistant Professor Tufts University.
Item Based Collaborative Filtering Recommendation Algorithms
Oracle User Productivity Kit Professional Ensuring Success with Oracle Apps
Mining Triadic Closure Patterns in Social Networks
A Local-Optimization based Strategy for Cost-Effective Datasets Storage of Scientific Applications in the Cloud Many slides from authors’ presentation.
Viral Marketing – Learning Influence Probabilities.
LEARNING INFLUENCE PROBABILITIES IN SOCIAL NETWORKS Amit Goyal Francesco Bonchi Laks V. S. Lakshmanan University of British Columbia Yahoo! Research University.
Online Max-Margin Weight Learning for Markov Logic Networks Tuyen N. Huynh and Raymond J. Mooney Machine Learning Group Department of Computer Science.
Towards Twitter Context Summarization with User Influence Models Yi Chang et al. WSDM 2013 Hyewon Lim 21 June 2013.
Pete Bohman Adam Kunk.  Introduction  Related Work  System Overview  Indexing Scheme  Ranking  Evaluation  Conclusion.
Understanding Cancer-based Networks in Twitter using Social Network Analysis Dhiraj Murthy Daniela Oliveira Alexander Gross Social Network Innovation Lab.
Predicting Tie Strength with the Facebook API Tasos Spiliotopoulos Madeira-ITI, University of Madeira, Portugal / Harokopio University, Greece Diogo Pereira.
Industrial Engineering College of Engineering Bayesian Kernel Methods for Binary Classification and Online Learning Problems Theodore Trafalis Workshop.
Online Bayesian Models for Personal Analytics in Social Media Svitlana Volkova and Benjamin Van Durme
Modeling Relationship Strength in Online Social Networks Rongjing Xiang: Purdue University Jennifer Neville: Purdue University Monica Rogati: LinkedIn.
Data Analysis in YouTube. Introduction Social network + a video sharing media – Potential environment to propagate an influence. Friendship network and.
Pete Bohman Adam Kunk. Real-Time Search  Definition: A search mechanism capable of finding information in an online fashion as it is produced. Technology.
©2015 Apigee Corp. All Rights Reserved. Preserving signal in customer journeys Joy Thomas, Apigee Jagdish Chand, Visa.
Page 1 Inferring Relevant Social Networks from Interpersonal Communication Munmun De Choudhury, Winter Mason, Jake Hofman and Duncan Watts WWW ’10 Summarized.
Zibin Zheng DR 2 : Dynamic Request Routing for Tolerating Latency Variability in Cloud Applications CLOUD 2013 Jieming Zhu, Zibin.
LANGUAGE MODELS FOR RELEVANCE FEEDBACK Lee Won Hee.
Exploit of Online Social Networks with Community-Based Graph Semi-Supervised Learning Mingzhen Mo and Irwin King Department of Computer Science and Engineering.
Improving Search Results Quality by Customizing Summary Lengths Michael Kaisser ★, Marti Hearst  and John B. Lowe ★ University of Edinburgh,  UC Berkeley,
Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis Kei Hashimoto, Yoshihiko Nankaku, and Keiichi.
CoCQA : Co-Training Over Questions and Answers with an Application to Predicting Question Subjectivity Orientation Baoli Li, Yandong Liu, and Eugene Agichtein.
Measuring Behavioral Trust in Social Networks
1 Epidemic Spreading Parameters: External Model based on population density and travel statistics.
Towards Social User Profiling: Unified and Discriminative Influence Model for Inferring Home Locations Rui Li, Shengjie Wang, Hongbo Deng, Rui Wang, Kevin.
Bayesian Speech Synthesis Framework Integrating Training and Synthesis Processes Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda Nagoya Institute.
The world’s libraries. Connected. Managing your Private and Public Data: Bringing down Inference Attacks against your Privacy Group Meeting in 2015.
Speaker : Yu-Hui Chen Authors : Dinuka A. Soysa, Denis Guangyin Chen, Oscar C. Au, and Amine Bermak From : 2013 IEEE Symposium on Computational Intelligence.
Supervised Random Walks: Predicting and Recommending Links in Social Networks Lars Backstrom (Facebook) & Jure Leskovec (Stanford) Proc. of WSDM 2011 Present.
Pete Bohman Adam Kunk.  Introduction  Related Work  System Overview  Indexing Scheme  Ranking  Evaluation  Conclusion.
Alvin CHAN Kay CHEUNG Alex YING Relationship between Twitter Events and Real-life.
Inferring Perceived Demographics from User Emotional Tone and User-Environment Emotional Svitlana Volkova 1, Yoram Bachrach 2 1 Center for Language and.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Trading Timeliness and Accuracy in Geo-Distributed Streaming Analytics
Deceptive News Prediction Clickbait Score Inference
Dieudo Mulamba November 2017
Quantifying Deception Propagation on Social Networks
Presentation transcript:

Inferring User Political Preferences from Streaming Communications Svitlana Volkova 1, Glen Coppersmith 2 and Benjamin Van Durme 1,2 1 Center for Language and Speech Processing 2 Human Language Technology Center of Excellence ACL 2014, Baltimore

Motivation Personalized, diverse and timely data Can reveal user interests, preferences and opinions DemographicsPro – WolphralAlpha Analytics –

Applications Large-scale passive polling and real-time live polling Online advertising Healthcare analytics Personalized recommendation systems and search

User Attribute Prediction Political Preference Rao et al., 2010; Conover et al., 2011, Pennacchiotti and Popescu, 2011; Zamal et al., 2012; Cohen and Ruths, Communications Gender Garera and Yarowsky, 2009; Rao et al., 2010; Burger et al., 2011; Van Durme, 2012; Zamal et al., 2012; Bergsma and Van Durme, 2013 Age Rao et al., 2010; Zamal et al., 2012; Cohen and Ruth, 2013; Nguyen et al., 2011, 2013 … … … … …

Existing Approaches ~1K Tweets* ….… Does an average Twitter user produce thousands of tweets? *Rao et al., 2010; Conover et al., 2011; Pennacchiotti and Popescu, 2011a; Burger et al., 2011; Zamal et al., 2012; Nguyen et al., 2013 Tweets as a document

How Active are Twitter Users?

Real-World Predictions Not active users: no or limited content Average Twitter users Median = 10 tweets per day Active users 1,000+ tweets Private users: no content 10% 50% 20%

Our Approach 1.Take advantage of user local neighborhoods 2.Incremental dynamic real-time predictions Real world batch predictions Streaming predictions

Our Approach 1.Take advantage of user local neighborhoods 2.Incremental dynamic real-time predictions Real world batch predictions

Attributed Social Network User Local Neighborhoods a.k.a. Social Circles

Twitter Network Data Code, data and trained models for gender, age, political preference prediction

Twitter Social Graph I.Candidate-Centric 1,031 users of interest II.Geo-Centric 270 users III.Politically Active* 371 users neighbors of each type per user ~50K nodes, ~60K edges What types of neighbors lead to the best attribute prediction for a given user? *Pennacchiotti and Popescu, 2011; Zamal et al., 2012; Cohen and Ruths, 2013 Code, data and trained models for gender, age, political preference prediction

Experiments Log-linear binary unigram models: (I)Users vs. (II) Neighbors and (III) Both Evaluate the relative utility of different neighborhood types: – varying neighborhood size n=[1, 2, 5, 10] and content amount t=[5, 10, 15, 25, 50, 100, 200] – 10-fold cross validation with 100 random restarts for every n and t parameter combination

Neighborhood Comparison Tweets per Neighbor 1 Neighbor10 Neighbors Accuracy

Optimizing Twitter API Calls Cand-Centric Graph: Friend Circle

Summary: Batch Real-World Predictions with Limited User Data More data is better How to get it? More neighbors per user > additional content from the existing neighbors What kind of data? Follower, retweet Users recently joined Twitter No or limited access to user tweets no or very limited content! Real-world predictions

Our Approach 1.Take advantage of user local neighborhoods 2.Incremental dynamic real-time predictions Streaming predictions

Iterative Bayesian Predictions Time … ?

Cand-Centric Graph: Belief Updates ? … Time ? …

Cand-Centric Graph: Prediction Time User-Neighbor 100 users 75% confidence Cand 75% 95% User Stream

Batch vs. Online Performance

Summary Neighborhood content is useful * Neighborhoods constructed from friends, usermentions and retweets are most effective Signal is distributed in the neighborhood Streaming models > batch models *Pennacchiotti and Popescu, 2011a, 2001b; Conover et al., 2011a, 2001b; Golbeck et al., 2011; Zamal et al., 2012

Thank you! Labeled Twitter network data for gender, age, political preference prediction: Code and pre-trained models available upon request: