SlideShare ist ein Scribd-Unternehmen logo
1 von 25
An Ensemble Model for Cross-Domain Polarity 
Classification on Twitter 
Adam Tsakalidis, Symeon Papadopoulos, Yiannis Kompatsiaris 
15th Web Information System Engineering (WISE 2014) 
Thessaloniki, 14 October 2014 
Information Technologies Institute (ITI) 
Center for Research & Technology Hellas (CERTH) 
#wiseconf2014
Overview 
• The Problem 
• Existing Approaches 
• Proposed Ensemble Model 
• Experimental Study 
• Summary – Future Work 
#wiseconf2014 #2
Polarity Classification 
motivation & definition 
#wiseconf2014 #3
Polarity Classification - Problem 
Finding about whether a piece of text (e.g. tweet) 
conveys a positive or negative sentiment about a 
topic or entity of interest (person, party, brand, etc.) 
#wiseconf2014 #4
Polarity Classification - Applications 
• Monitoring sentiment about a brand could help take 
appropriate measures in case of negative sentiment 
increase (e.g. apology, assistance, compensation). 
• Aggregating over many tweets could help form an 
overall impression of the public opinion about the 
topic/entity of interest. 
#wiseconf2014 
#5
The Cross-Domain Challenge 
• Depending on the domain (and sometimes even the 
topic) of interest, the vocabulary and phrasing of 
sentiment may vary wildly. 
• Most sentiment detection approaches require 
manually created ground truth from the same 
domain to achieve high performance  expensive! 
• We propose a framework that leverages an 
ensemble of sentiment detectors to tackle the cross-domain 
#wiseconf2014 
challenge. 
#6
Related Work 
#wiseconf2014 
#7
Background: Sentiment Analysis 
Two main problems: subjectivity & polarity 
TTeexxtt RReepprreesseennttaattioionn LLeeaarrnniningg SSeenntitmimeenntt 
NNBB SSVVMM 
#wiseconf2014 #8 
Hybrid- 
Hybrid- 
Ensemble 
Unsupervised SSSSLL Ensemble UUnnigigrarammss BBigigrarammss PPOOSS OOththeerr SSuuppeervrvisiseedd Unsupervised
Hybrid Models 
Barbosa and Feng, COLING 2010 
• Combines sentiment labels from three independent sources 
• Considers the quality of individual sources 
• Considers the different bias of individual sources 
Gonçalves et al., COSN 2013 
• First evaluates 8 different methods with respect to coverage 
and agreement 
• Proposes a combined method, which combines individual 
method outputs based on their performance (first in terms of 
coverage and then in terms of accuracy) on an independent 
dataset 
#wiseconf2014 
#9
Ensemble Model for Cross-Domain 
Polarity Classification 
approach description 
#wiseconf2014 
#10
Method Overview 
#wiseconf2014 
#11 
TTBBRR 
FFBBRR 
CCRR 
LLBBRR 
CCLL__TTBBRR 
CCLL__FFBBRR 
TTwweeeett 
CCLL__CCRR 
CCLL__LLBBRR 
HHCC 
LLCC 
CCOOMMBB 
representation learning ensembling
Representation 
• TBR 
– binary n-grams 
– n-grams with tf 
– n-grams with tf-idf 
– n = 1, 2, 3  9 representations 
• FBR 
• CR 
– TBR + POS tagging 
• LBR 
– SentiWordNet (5D): sum of scores for Noun, Verbs, Adjectives, 
Adverbs, sum of keywords (#pos - #neg) 
– Opinion Lexicon: Sum of keywords (#pos - #neg) 
#wiseconf2014 
#12 
TBR, FBR and CR with tf < 2 
were removed!
Ensemble Learning 
• Combine two types of classifiers: HC and LC 
• Hybrid classifier (HC) [domain-dependent] 
i: tweet, c: class (pos/neg), r: TBR, FBR, LR, wr: weights defined based on 
accuracy on ED dataset, pr: individual classifier output 
• Lexicon-based classifier (LC) [domain-independent] 
• If the outputs of the two classifiers agree, then 
assign the agreed class to the tweet. 
• If the outputs disagree, use a domain-adapted 
classifier (TBR) trained on the agreed tweets. 
#wiseconf2014 
#13
Practical aspects 
• In order for the ensemble model to work well, the 
two types of classifiers need to be individually 
accurate at sufficient rates, since we trust their 
outputs to be used as a new training set! 
• In a real-time scenario, we need to allocate some 
time for the domain adaptation process to take 
place. This should be defined on a per case basis. 
adaptation ensemble model operation 
#wiseconf2014 
#14
Experimental Study 
#wiseconf2014 
#15
Datasets 
• Emoticons Dataset (ED) 
– 250K tweets collected over 2-days (mid-march 2014) containing 
happy/sad emoticons (removed retweets) [English only!] 
– used for feature extraction, preliminary development 
• Development set (DEV) 
– 10K tweets (equally balanced) collected in the same way as ED 
• Stanford Twitter dataset (STS) 
– STS-1: 177 pos, 184 neg 
– STS-2: 108 pos, 75 neg 
• Obama Healthcare Reform (HCR) 
– dev-set: 135 pos, 328 neg 
– test-set: 116 pos, 383 neg 
• Obama-McCain Debate (OMD) 
– subset (agreement>50%): 707 pos, 1190 neg 
#wiseconf2014 
#16
Model building 
• Performance of TBR variants, role of POS (on 33% of ED) 
• Performance of LR features 
• Comparative performance of all classifiers (on DEV) 
#wiseconf2014 
#17
Results 
more realistic estimate of real-world performance / still, far better than other out-of- 
domain methods 
over-optimistic estimate of real-world performance since 90% of set used for training 
#wiseconf2014 
#18
Role of classifier agreement 
• As expected, accuracy on disagreed tweets is lower 
– results produced using a classifier trained on “noisy” data 
– more challenging cases 
• A similar case when training using automatically 
collected data based on emoticons 
#wiseconf2014 
#19
Conclusions & Future Work 
#wiseconf2014 
#20
Conclusions & Future Work 
Conclusion 
•Ensemble model in tandem with domain adaptation is 
an effective strategy for tackling the cross-domain 
challenge! 
Future Work 
•Incorporate the “neutral” class and evaluate 
•Test with more datasets 
•Check with additional classifiers as input 
#wiseconf2014 
#21
Thank you! 
#wiseconf2014 
#22 
Questions? 
https://github.com/socialsensor/sentiment-analysis 
http://socialsensor.eu/ 
adam.tsakalidis@gmail.com / papadop@iti.gr 
a.tsakalidis@warwick.ac.uk
Key References (1/3) 
• Alina Andreevskaia and Sabine Bergler. When specialists and generalists work 
together: Overcoming domain dependence in sentiment tagging. In ACL, pages 
290-298, 2008 
• Luciano Barbosa and Junlan Feng. Robust sentiment detection on twitter from 
biased and noisy data. In Proceedings of the 23rd International Conference on 
Computational Linguistics: Posters, pages 36-44. ACL, 2010 
• Adam Bermingham and Alan F Smeaton. Classifying sentiment in microblogs: is 
brevity an advantage? In Proceedings of the 19th ACM international conference 
on Information and knowledge management, pages 1833-1836. ACM, 2010 
• Albert Bifet and Eibe Frank. Sentiment knowledge discovery in twitter 
streaming data. In Discovery Science, pages 1-15. Springer, 2010 
• Johan Bollen, Huina Mao, and Alberto Pepe. Modeling public mood and 
emotion: Twitter sentiment and socio-economic phenomena. In ICWSM, 2011 
• Samuel Brody and Nicholas Diakopoulos. 
Cooooooooooooooollllllllllllll !!!!!!!!!!!!!!: using word lengthening to detect 
sentiment in microblogs. In Proceedings of the Conference on EMNLP, pages 
562-570. ACL, 2011. 
#wiseconf2014 
#23
Key References (2/3) 
• Andrea Esuli and Fabrizio Sebastiani. Sentiwordnet: A publicly available lexical 
resource for opinion mining. In Proceedings of LREC, vol. 6, pages 417-422, 2006 
• Alec Go, Richa Bhayani, and Lei Huang. Twitter sentiment classification using 
distant supervision. CS224N Project Report, Stanford, pages 1-12, 2009 
• Pollyanna Goncalves, Matheus Araujo, Fabricio Benevenuto, and Meeyoung Cha. 
Comparing and combining sentiment analysis methods. In Proceedings of the first 
ACM COSN, pages 27-38. ACM, 2013 
• Minqing Hu and Bing Liu. Mining and summarizing customer reviews. In 
Proceedings of the tenth ACM SIGKDD international conference on Knowledge 
discovery and data mining, pages 168-177. ACM, 2004 
• Long Jiang, Mo Yu, Ming Zhou, Xiaohua Liu, and Tiejun Zhao. Target-dependent 
twitter sentiment classification. In Proceedings of the 49th Annual Meeting of the 
ACL: HLT-Vol. 1, pages 151-160. ACL, 2011 
• Jonathon Read. Using emoticons to reduce dependency in machine learning 
techniques for sentiment classification. In Proceedings of the ACL Student Research 
Workshop, pages 43-48. ACL, 2005 
• Hassan Saif, Yulan He, and Harith Alani. Semantic sentiment analysis of twitter. In 
The Semantic Web-ISWC 2012, pages 508-524. Springer, 2012 
#wiseconf2014 
#24
Key References (3/3) 
• Emmanouil Schinas, Symeon Papadopoulos, Sotiris Diplaris, Yiannis Kompatsiaris, 
Yosi Mass, Jonathan Herzig, and Lazaros Boudakidis. Eventsense: Capturing the 
pulse of large-scale events by mining social media streams. In Proceedings of the 
17th Panhellenic Conference on Informatics, pages 17-24. ACM, 2013 
• Michael Speriosu, Nikita Sudan, Sid Upadhyay, and Jason Baldridge. Twitter 
polarity classification with label propagation over lexical links and the follower 
graph. In Proceedings of the First workshop on Unsupervised Learning in NLP, 
pages 53-63. ACL, 2011 
• Kristina Toutanova, Dan Klein, Christopher D Manning, and Yoram Singer. Feature-rich 
part-of-speech tagging with a cyclic dependency network. In Proceedings of 
the 2003 Conference of the North American Chapter of the ACL on HLT-Vol. 1, 
pages 173-180. ACL, 2003 
• Andranik Tumasjan, Timm Oliver Sprenger, Philipp Sandner, and Isabell Welpe. 
Predicting elections with twitter: What 140 characters reveal about political 
sentiment. In ICWSM 2010, 10:178-185, 2010 
• Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. Recognizing contextual 
polarity in phrase-level sentiment analysis. In Proceedings of the conference on 
HLT and EMNLP, pages 347-354. ACL, 2005 
• Ley Zhang, Riddhiman Ghosh, Mohamed Dekhil, Meichun Hsu, and Bing Liu. 
Combining Lexicon-based and learning-based methods for twitter sentiment 
analysis. HP Laboratories, Technical Report HPL-2011, 89, 2011. 
#wiseconf2014 
#25

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (6)

Datascience Introduction WebSci Summer School 2014
Datascience Introduction WebSci Summer School 2014Datascience Introduction WebSci Summer School 2014
Datascience Introduction WebSci Summer School 2014
 
Using Agent-Based Simulation to integrate micro/qualitative evidence, macro-q...
Using Agent-Based Simulation to integrate micro/qualitative evidence, macro-q...Using Agent-Based Simulation to integrate micro/qualitative evidence, macro-q...
Using Agent-Based Simulation to integrate micro/qualitative evidence, macro-q...
 
Challenges of using Twitter for sentiment analysis
Challenges of using Twitter for sentiment analysisChallenges of using Twitter for sentiment analysis
Challenges of using Twitter for sentiment analysis
 
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
[WI 2017] Context Suggestion: Empirical Evaluations vs User Studies
 
IIR 2017, Lugano Switzerland
IIR 2017, Lugano SwitzerlandIIR 2017, Lugano Switzerland
IIR 2017, Lugano Switzerland
 
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
Twitter Based Outcome Predictions of 2019 Indian General Elections Using Deci...
 

Ähnlich wie An Ensemble Model for Cross-Domain Polarity Classification on Twitter

Netnography online course part 1 of 3 17 november 2016
Netnography online course part 1 of 3 17 november 2016Netnography online course part 1 of 3 17 november 2016
Netnography online course part 1 of 3 17 november 2016
suresh sood
 
Munassir etec647 e presentation
Munassir etec647 e presentationMunassir etec647 e presentation
Munassir etec647 e presentation
Munassir Alhamami
 
NCME Big Data in Education
NCME Big Data  in EducationNCME Big Data  in Education
NCME Big Data in Education
Philip Piety
 
Web Science Session 4 E-Learning.pdf
Web Science Session 4 E-Learning.pdfWeb Science Session 4 E-Learning.pdf
Web Science Session 4 E-Learning.pdf
Stefanie Panke
 

Ähnlich wie An Ensemble Model for Cross-Domain Polarity Classification on Twitter (20)

Sub1557
Sub1557Sub1557
Sub1557
 
Influencing the MOOC agenda - analysis of #MOOC Twitter Data
Influencing the MOOC agenda - analysis of #MOOC Twitter Data  Influencing the MOOC agenda - analysis of #MOOC Twitter Data
Influencing the MOOC agenda - analysis of #MOOC Twitter Data
 
ESWC 2014 Tutorial Part 4
ESWC 2014 Tutorial Part 4ESWC 2014 Tutorial Part 4
ESWC 2014 Tutorial Part 4
 
Netnography online course part 1 of 3 17 november 2016
Netnography online course part 1 of 3 17 november 2016Netnography online course part 1 of 3 17 november 2016
Netnography online course part 1 of 3 17 november 2016
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
 
Challenge-based gamification as a teaching’Open Educational Innovation strate...
Challenge-based gamification as a teaching’Open Educational Innovation strate...Challenge-based gamification as a teaching’Open Educational Innovation strate...
Challenge-based gamification as a teaching’Open Educational Innovation strate...
 
Learning Analytics: A Messy Research Construct
Learning Analytics: A Messy Research ConstructLearning Analytics: A Messy Research Construct
Learning Analytics: A Messy Research Construct
 
3 D Project Based Learning Basics for the New Generation Science Standards
3 D Project Based  Learning Basics for the New Generation Science Standards3 D Project Based  Learning Basics for the New Generation Science Standards
3 D Project Based Learning Basics for the New Generation Science Standards
 
Markus id project 1
Markus id project 1Markus id project 1
Markus id project 1
 
Scalable Exploration of Relevance Prospects to Support Decision Making
Scalable Exploration of Relevance Prospects to Support Decision MakingScalable Exploration of Relevance Prospects to Support Decision Making
Scalable Exploration of Relevance Prospects to Support Decision Making
 
#Edu14 Seminar on the State of Social Media in Higher Ed
#Edu14 Seminar on the State of Social Media in Higher Ed#Edu14 Seminar on the State of Social Media in Higher Ed
#Edu14 Seminar on the State of Social Media in Higher Ed
 
Munassir etec647 e presentation
Munassir etec647 e presentationMunassir etec647 e presentation
Munassir etec647 e presentation
 
NCME Big Data in Education
NCME Big Data  in EducationNCME Big Data  in Education
NCME Big Data in Education
 
Automatic Movie Rating By Using Twitter Sentiment Analysis And Monitoring Tool
Automatic Movie Rating By Using Twitter Sentiment Analysis And Monitoring ToolAutomatic Movie Rating By Using Twitter Sentiment Analysis And Monitoring Tool
Automatic Movie Rating By Using Twitter Sentiment Analysis And Monitoring Tool
 
Co-designing learning dashboards for scalable feedback
Co-designing learning dashboards for scalable feedbackCo-designing learning dashboards for scalable feedback
Co-designing learning dashboards for scalable feedback
 
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
 
Web Science Session 4 E-Learning.pdf
Web Science Session 4 E-Learning.pdfWeb Science Session 4 E-Learning.pdf
Web Science Session 4 E-Learning.pdf
 
California Community College Student Library & Technology Engagement Survey: ...
California Community College Student Library & Technology Engagement Survey: ...California Community College Student Library & Technology Engagement Survey: ...
California Community College Student Library & Technology Engagement Survey: ...
 
Universal Design for Learning: A framework for addressing learner diversity
Universal Design for Learning: A framework for addressing learner diversityUniversal Design for Learning: A framework for addressing learner diversity
Universal Design for Learning: A framework for addressing learner diversity
 
Advanced Methods for User Evaluation in Enterprise AR
Advanced Methods for User Evaluation in Enterprise ARAdvanced Methods for User Evaluation in Enterprise AR
Advanced Methods for User Evaluation in Enterprise AR
 

Mehr von Symeon Papadopoulos

Mehr von Symeon Papadopoulos (20)

DeepFake Detection: Challenges, Progress and Hands-on Demonstration of Techno...
DeepFake Detection: Challenges, Progress and Hands-on Demonstration of Techno...DeepFake Detection: Challenges, Progress and Hands-on Demonstration of Techno...
DeepFake Detection: Challenges, Progress and Hands-on Demonstration of Techno...
 
Deepfakes: An Emerging Internet Threat and their Detection
Deepfakes: An Emerging Internet Threat and their DetectionDeepfakes: An Emerging Internet Threat and their Detection
Deepfakes: An Emerging Internet Threat and their Detection
 
Knowledge-based Fusion for Image Tampering Localization
Knowledge-based Fusion for Image Tampering LocalizationKnowledge-based Fusion for Image Tampering Localization
Knowledge-based Fusion for Image Tampering Localization
 
Deepfake Detection: The Importance of Training Data Preprocessing and Practic...
Deepfake Detection: The Importance of Training Data Preprocessing and Practic...Deepfake Detection: The Importance of Training Data Preprocessing and Practic...
Deepfake Detection: The Importance of Training Data Preprocessing and Practic...
 
COVID-19 Infodemic vs Contact Tracing
COVID-19 Infodemic vs Contact TracingCOVID-19 Infodemic vs Contact Tracing
COVID-19 Infodemic vs Contact Tracing
 
Similarity-based retrieval of multimedia content
Similarity-based retrieval of multimedia contentSimilarity-based retrieval of multimedia content
Similarity-based retrieval of multimedia content
 
Twitter-based Sensing of City-level Air Quality
Twitter-based Sensing of City-level Air QualityTwitter-based Sensing of City-level Air Quality
Twitter-based Sensing of City-level Air Quality
 
Aggregating and Analyzing the Context of Social Media Content
Aggregating and Analyzing the Context of Social Media ContentAggregating and Analyzing the Context of Social Media Content
Aggregating and Analyzing the Context of Social Media Content
 
Verifying Multimedia Content on the Internet
Verifying Multimedia Content on the InternetVerifying Multimedia Content on the Internet
Verifying Multimedia Content on the Internet
 
A Web-based Service for Image Tampering Detection
A Web-based Service for Image Tampering DetectionA Web-based Service for Image Tampering Detection
A Web-based Service for Image Tampering Detection
 
Learning to detect Misleading Content on Twitter
Learning to detect Misleading Content on TwitterLearning to detect Misleading Content on Twitter
Learning to detect Misleading Content on Twitter
 
Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
Near-Duplicate Video Retrieval by Aggregating Intermediate CNN LayersNear-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
Near-Duplicate Video Retrieval by Aggregating Intermediate CNN Layers
 
Verifying Multimedia Use at MediaEval 2016
Verifying Multimedia Use at MediaEval 2016Verifying Multimedia Use at MediaEval 2016
Verifying Multimedia Use at MediaEval 2016
 
Multimedia Privacy
Multimedia PrivacyMultimedia Privacy
Multimedia Privacy
 
Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...Placing Images with Refined Language Models and Similarity Search with PCA-re...
Placing Images with Refined Language Models and Similarity Search with PCA-re...
 
In-depth Exploration of Geotagging Performance
In-depth Exploration of Geotagging PerformanceIn-depth Exploration of Geotagging Performance
In-depth Exploration of Geotagging Performance
 
Perceived versus Actual Predictability of Personal Information in Social Netw...
Perceived versus Actual Predictability of Personal Information in Social Netw...Perceived versus Actual Predictability of Personal Information in Social Netw...
Perceived versus Actual Predictability of Personal Information in Social Netw...
 
Web and Social Media Image Forensics for News Professionals
Web and Social Media Image Forensics for News ProfessionalsWeb and Social Media Image Forensics for News Professionals
Web and Social Media Image Forensics for News Professionals
 
Predicting News Popularity by Mining Online Discussions
Predicting News Popularity by Mining Online DiscussionsPredicting News Popularity by Mining Online Discussions
Predicting News Popularity by Mining Online Discussions
 
Finding Diverse Social Images at MediaEval 2015
Finding Diverse Social Images at MediaEval 2015Finding Diverse Social Images at MediaEval 2015
Finding Diverse Social Images at MediaEval 2015
 

KĂźrzlich hochgeladen

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
Enterprise Knowledge
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 

KĂźrzlich hochgeladen (20)

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 

An Ensemble Model for Cross-Domain Polarity Classification on Twitter

  • 1. An Ensemble Model for Cross-Domain Polarity Classification on Twitter Adam Tsakalidis, Symeon Papadopoulos, Yiannis Kompatsiaris 15th Web Information System Engineering (WISE 2014) Thessaloniki, 14 October 2014 Information Technologies Institute (ITI) Center for Research & Technology Hellas (CERTH) #wiseconf2014
  • 2. Overview • The Problem • Existing Approaches • Proposed Ensemble Model • Experimental Study • Summary – Future Work #wiseconf2014 #2
  • 3. Polarity Classification motivation & definition #wiseconf2014 #3
  • 4. Polarity Classification - Problem Finding about whether a piece of text (e.g. tweet) conveys a positive or negative sentiment about a topic or entity of interest (person, party, brand, etc.) #wiseconf2014 #4
  • 5. Polarity Classification - Applications • Monitoring sentiment about a brand could help take appropriate measures in case of negative sentiment increase (e.g. apology, assistance, compensation). • Aggregating over many tweets could help form an overall impression of the public opinion about the topic/entity of interest. #wiseconf2014 #5
  • 6. The Cross-Domain Challenge • Depending on the domain (and sometimes even the topic) of interest, the vocabulary and phrasing of sentiment may vary wildly. • Most sentiment detection approaches require manually created ground truth from the same domain to achieve high performance  expensive! • We propose a framework that leverages an ensemble of sentiment detectors to tackle the cross-domain #wiseconf2014 challenge. #6
  • 8. Background: Sentiment Analysis Two main problems: subjectivity & polarity TTeexxtt RReepprreesseennttaattioionn LLeeaarrnniningg SSeenntitmimeenntt NNBB SSVVMM #wiseconf2014 #8 Hybrid- Hybrid- Ensemble Unsupervised SSSSLL Ensemble UUnnigigrarammss BBigigrarammss PPOOSS OOththeerr SSuuppeervrvisiseedd Unsupervised
  • 9. Hybrid Models Barbosa and Feng, COLING 2010 • Combines sentiment labels from three independent sources • Considers the quality of individual sources • Considers the different bias of individual sources Gonçalves et al., COSN 2013 • First evaluates 8 different methods with respect to coverage and agreement • Proposes a combined method, which combines individual method outputs based on their performance (first in terms of coverage and then in terms of accuracy) on an independent dataset #wiseconf2014 #9
  • 10. Ensemble Model for Cross-Domain Polarity Classification approach description #wiseconf2014 #10
  • 11. Method Overview #wiseconf2014 #11 TTBBRR FFBBRR CCRR LLBBRR CCLL__TTBBRR CCLL__FFBBRR TTwweeeett CCLL__CCRR CCLL__LLBBRR HHCC LLCC CCOOMMBB representation learning ensembling
  • 12. Representation • TBR – binary n-grams – n-grams with tf – n-grams with tf-idf – n = 1, 2, 3  9 representations • FBR • CR – TBR + POS tagging • LBR – SentiWordNet (5D): sum of scores for Noun, Verbs, Adjectives, Adverbs, sum of keywords (#pos - #neg) – Opinion Lexicon: Sum of keywords (#pos - #neg) #wiseconf2014 #12 TBR, FBR and CR with tf < 2 were removed!
  • 13. Ensemble Learning • Combine two types of classifiers: HC and LC • Hybrid classifier (HC) [domain-dependent] i: tweet, c: class (pos/neg), r: TBR, FBR, LR, wr: weights defined based on accuracy on ED dataset, pr: individual classifier output • Lexicon-based classifier (LC) [domain-independent] • If the outputs of the two classifiers agree, then assign the agreed class to the tweet. • If the outputs disagree, use a domain-adapted classifier (TBR) trained on the agreed tweets. #wiseconf2014 #13
  • 14. Practical aspects • In order for the ensemble model to work well, the two types of classifiers need to be individually accurate at sufficient rates, since we trust their outputs to be used as a new training set! • In a real-time scenario, we need to allocate some time for the domain adaptation process to take place. This should be defined on a per case basis. adaptation ensemble model operation #wiseconf2014 #14
  • 16. Datasets • Emoticons Dataset (ED) – 250K tweets collected over 2-days (mid-march 2014) containing happy/sad emoticons (removed retweets) [English only!] – used for feature extraction, preliminary development • Development set (DEV) – 10K tweets (equally balanced) collected in the same way as ED • Stanford Twitter dataset (STS) – STS-1: 177 pos, 184 neg – STS-2: 108 pos, 75 neg • Obama Healthcare Reform (HCR) – dev-set: 135 pos, 328 neg – test-set: 116 pos, 383 neg • Obama-McCain Debate (OMD) – subset (agreement>50%): 707 pos, 1190 neg #wiseconf2014 #16
  • 17. Model building • Performance of TBR variants, role of POS (on 33% of ED) • Performance of LR features • Comparative performance of all classifiers (on DEV) #wiseconf2014 #17
  • 18. Results more realistic estimate of real-world performance / still, far better than other out-of- domain methods over-optimistic estimate of real-world performance since 90% of set used for training #wiseconf2014 #18
  • 19. Role of classifier agreement • As expected, accuracy on disagreed tweets is lower – results produced using a classifier trained on “noisy” data – more challenging cases • A similar case when training using automatically collected data based on emoticons #wiseconf2014 #19
  • 20. Conclusions & Future Work #wiseconf2014 #20
  • 21. Conclusions & Future Work Conclusion •Ensemble model in tandem with domain adaptation is an effective strategy for tackling the cross-domain challenge! Future Work •Incorporate the “neutral” class and evaluate •Test with more datasets •Check with additional classifiers as input #wiseconf2014 #21
  • 22. Thank you! #wiseconf2014 #22 Questions? https://github.com/socialsensor/sentiment-analysis http://socialsensor.eu/ adam.tsakalidis@gmail.com / papadop@iti.gr a.tsakalidis@warwick.ac.uk
  • 23. Key References (1/3) • Alina Andreevskaia and Sabine Bergler. When specialists and generalists work together: Overcoming domain dependence in sentiment tagging. In ACL, pages 290-298, 2008 • Luciano Barbosa and Junlan Feng. Robust sentiment detection on twitter from biased and noisy data. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, pages 36-44. ACL, 2010 • Adam Bermingham and Alan F Smeaton. Classifying sentiment in microblogs: is brevity an advantage? In Proceedings of the 19th ACM international conference on Information and knowledge management, pages 1833-1836. ACM, 2010 • Albert Bifet and Eibe Frank. Sentiment knowledge discovery in twitter streaming data. In Discovery Science, pages 1-15. Springer, 2010 • Johan Bollen, Huina Mao, and Alberto Pepe. Modeling public mood and emotion: Twitter sentiment and socio-economic phenomena. In ICWSM, 2011 • Samuel Brody and Nicholas Diakopoulos. Cooooooooooooooollllllllllllll !!!!!!!!!!!!!!: using word lengthening to detect sentiment in microblogs. In Proceedings of the Conference on EMNLP, pages 562-570. ACL, 2011. #wiseconf2014 #23
  • 24. Key References (2/3) • Andrea Esuli and Fabrizio Sebastiani. Sentiwordnet: A publicly available lexical resource for opinion mining. In Proceedings of LREC, vol. 6, pages 417-422, 2006 • Alec Go, Richa Bhayani, and Lei Huang. Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford, pages 1-12, 2009 • Pollyanna Goncalves, Matheus Araujo, Fabricio Benevenuto, and Meeyoung Cha. Comparing and combining sentiment analysis methods. In Proceedings of the first ACM COSN, pages 27-38. ACM, 2013 • Minqing Hu and Bing Liu. Mining and summarizing customer reviews. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 168-177. ACM, 2004 • Long Jiang, Mo Yu, Ming Zhou, Xiaohua Liu, and Tiejun Zhao. Target-dependent twitter sentiment classification. In Proceedings of the 49th Annual Meeting of the ACL: HLT-Vol. 1, pages 151-160. ACL, 2011 • Jonathon Read. Using emoticons to reduce dependency in machine learning techniques for sentiment classification. In Proceedings of the ACL Student Research Workshop, pages 43-48. ACL, 2005 • Hassan Saif, Yulan He, and Harith Alani. Semantic sentiment analysis of twitter. In The Semantic Web-ISWC 2012, pages 508-524. Springer, 2012 #wiseconf2014 #24
  • 25. Key References (3/3) • Emmanouil Schinas, Symeon Papadopoulos, Sotiris Diplaris, Yiannis Kompatsiaris, Yosi Mass, Jonathan Herzig, and Lazaros Boudakidis. Eventsense: Capturing the pulse of large-scale events by mining social media streams. In Proceedings of the 17th Panhellenic Conference on Informatics, pages 17-24. ACM, 2013 • Michael Speriosu, Nikita Sudan, Sid Upadhyay, and Jason Baldridge. Twitter polarity classification with label propagation over lexical links and the follower graph. In Proceedings of the First workshop on Unsupervised Learning in NLP, pages 53-63. ACL, 2011 • Kristina Toutanova, Dan Klein, Christopher D Manning, and Yoram Singer. Feature-rich part-of-speech tagging with a cyclic dependency network. In Proceedings of the 2003 Conference of the North American Chapter of the ACL on HLT-Vol. 1, pages 173-180. ACL, 2003 • Andranik Tumasjan, Timm Oliver Sprenger, Philipp Sandner, and Isabell Welpe. Predicting elections with twitter: What 140 characters reveal about political sentiment. In ICWSM 2010, 10:178-185, 2010 • Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the conference on HLT and EMNLP, pages 347-354. ACL, 2005 • Ley Zhang, Riddhiman Ghosh, Mohamed Dekhil, Meichun Hsu, and Bing Liu. Combining Lexicon-based and learning-based methods for twitter sentiment analysis. HP Laboratories, Technical Report HPL-2011, 89, 2011. #wiseconf2014 #25