Determining Negation Scope and Strength in Sentiment Analysis SMC 2011 Paul van Iterson Erasmus School of Economics Erasmus University Rotterdam

Slides:



Advertisements
Similar presentations
RCQ-ACS: RDF Chain Query Optimization Using an Ant Colony System WI 2012 Alexander Hogenboom Erasmus University Rotterdam Ewout Niewenhuijse.
Advertisements

Polarity Analysis of Texts using Discourse Structure CIKM 2011 Bas Heerschop Erasmus University Rotterdam Frank Goossen Erasmus.
Distant Supervision for Emotion Classification in Twitter posts 1/17.
Learning Semantic Information Extraction Rules from News The Dutch-Belgian Database Day 2013 (DBDBD 2013) Frederik Hogenboom Erasmus.
Semantic News Recommendation Using WordNet and Bing Similarities 28th Symposium On Applied Computing 2013 (SAC 2013) March 21, 2013 Michel Capelle
A Linguistic Approach for Semantic Web Service Discovery International Symposium on Management Intelligent Systems 2012 (IS-MiS 2012) July 13, 2012 Jordy.
TEMPLATE DESIGN © Identifying Noun Product Features that Imply Opinions Lei Zhang Bing Liu Department of Computer Science,
Exploiting Discourse Structure for Sentiment Analysis of Text OR 2013 Alexander Hogenboom In collaboration with Flavius Frasincar, Uzay Kaymak, and Franciska.
Title Course opinion mining methodology for knowledge discovery, based on web social media Authors Sotirios Kontogiannis Ioannis Kazanidis Stavros Valsamidis.
Connecting Customer Relationship Management Systems to Social Networks 7th International Conference on Knowledge Management, Services, and Cloud Computing.
Sentiment Analysis An Overview of Concepts and Selected Techniques.
Jean-Eudes Ranvier 17/05/2015Planet Data - Madrid Trustworthiness assessment (on web pages) Task 3.3.
Exploiting Emoticons in Sentiment Analysis SAC 2013 Daniella Bal Erasmus University Rotterdam Flavius Frasincar Erasmus University.
A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts 04 10, 2014 Hyun Geun Soo Bo Pang and Lillian Lee (2004)
Erasmus University Rotterdam Frederik HogenboomEconometric Institute School of Economics Flavius Frasincar.
April 22, Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Doerre, Peter Gerstl, Roland Seiffert IBM Germany, August 1999 Presenter:
RCQ-GA: RDF Chain Query Optimization using Genetic Algorithms BNAIC 2009 Alexander Hogenboom, Viorel Milea, Flavius Frasincar, and Uzay Kaymak Erasmus.
Sentiment Lexicon Creation from Lexical Resources BIS 2011 Bas Heerschop Erasmus School of Economics Erasmus University Rotterdam
Automatically Annotating Web Pages Using Google Rich Snippets 11th Dutch-Belgian Information Retrieval Workshop (DIR 2011) February 4, 2011 Frederik Hogenboom.
Optimizing RDF Chain Queries using Genetic Algorithms DBDBD 2010 Alexander Hogenboom, Viorel Milea, Flavius Frasincar, and Uzay Kaymak Erasmus University.
Detecting Economic Events Using a Semantics-Based Pipeline 22nd International Conference on Database and Expert Systems Applications (DEXA 2011) September.
An Overview of Event Extraction from Text Workhop on Detection, Representation, and Exploitation of Events in the Semantic Web (DeRiVE'11) October 23,
News Personalization using the CF-IDF Semantic Recommender International Conference on Web Intelligence, Mining, and Semantics (WIMS 2011) May 25, 2011.
Semantic Video Classification Based on Subtitles and Domain Terminologies Polyxeni Katsiouli, Vassileios Tsetsos, Stathes Hadjiefthymiades P ervasive C.
Analyzing Sentiment in a Large Set of Web Data while Accounting for Negation AWIC 2011 Bas Heerschop Erasmus School of Economics Erasmus University Rotterdam.
Text Mining: Finding Nuggets in Mountains of Textual Data Jochen Dijrre, Peter Gerstl, Roland Seiffert Presented by Drew DeHaas.
Word Sense Disambiguation for Automatic Taxonomy Construction from Text-Based Web Corpora 12th International Conference on Web Information System Engineering.
Sentiment Analysis with a Multilingual Pipeline 12th International Conference on Web Information System Engineering (WISE 2011) October 13, 2011 Daniëlla.
Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product Reviews K. Dave et al, WWW 2003, citations Presented by Sarah.
A Joint Model of Feature Mining and Sentiment Analysis for Product Review Rating Jorge Carrillo de Albornoz Laura Plaza Pablo Gervás Alberto Díaz Universidad.
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
Erasmus University Rotterdam Introduction Nowadays, emerging news on economic events such as acquisitions has a substantial impact on the financial markets.
Erasmus University Rotterdam Introduction With the vast amount of information available on the Web, there is an increasing need to structure Web data in.
A News-Based Approach for Computing Historical Value-at-Risk International Symposium on Management Intelligent Systems 2012 (IS-MiS 2012) Frederik Hogenboom.
Lemmatization Tagging LELA /20 Lemmatization Basic form of annotation involving identification of underlying lemmas (lexemes) of the words in.
Personalisation Seminar on Unlocking the Secrets of the Past: Text Mining for Historical Documents Sven Steudter.
Survey of Semantic Annotation Platforms
PAUL ALEXANDRU CHIRITA STEFANIA COSTACHE SIEGFRIED HANDSCHUH WOLFGANG NEJDL 1* L3S RESEARCH CENTER 2* NATIONAL UNIVERSITY OF IRELAND PROCEEDINGS OF THE.
 Text Representation & Text Classification for Intelligent Information Retrieval Ning Yu School of Library and Information Science Indiana University.
Part-Of-Speech Tagging using Neural Networks Ankur Parikh LTRC IIIT Hyderabad
An Effective Word Sense Disambiguation Model Using Automatic Sense Tagging Based on Dictionary Information Yong-Gu Lee
1 Team Members: Rohan Kothari Vaibhav Mehta Vinay Rambhia Hybrid Review System.
A Bootstrapping Method for Building Subjectivity Lexicons for Languages with Scarce Resources Author: Carmen Banea, Rada Mihalcea, Janyce Wiebe Source:
14/12/2009ICON Dipankar Das and Sivaji Bandyopadhyay Department of Computer Science & Engineering Jadavpur University, Kolkata , India ICON.
*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.
Semantics-Based News Recommendation with SF-IDF+ International Conference on Web Intelligence, Mining, and Semantics (WIMS 2013) June 13, 2013 Marnix Moerland.
Erasmus University Rotterdam Introduction Content-based news recommendation is traditionally performed using the cosine similarity and TF-IDF weighting.
Lecture 21 Computational Lexical Semantics Topics Features in NLTK III Computational Lexical Semantics Semantic Web USCReadings: NLTK book Chapter 10 Text.
Towards Cross-Language Sentiment Analysis through Universal Star Ratings KMO 2012 Malissa Bal Erasmus University Rotterdam Flavius.
Lexico-semantic Patterns for Information Extraction from Text The International Conference on Operations Research 2013 (OR 2013) Frederik Hogenboom
Number Sense Disambiguation Stuart Moore Supervised by: Anna Korhonen (Computer Lab)‏ Sabine Buchholz (Toshiba CRL)‏
Recognizing Stances in Online Debates Unsupervised opinion analysis method for debate-side classification. Mine the web to learn associations that are.
1 Adaptive Subjective Triggers for Opinionated Document Retrieval (WSDM 09’) Kazuhiro Seki, Kuniaki Uehara Date: 11/02/09 Speaker: Hsu, Yu-Wen Advisor:
Semantics-Based News Recommendation International Conference on Web Intelligence, Mining, and Semantics (WIMS 2012) June 14, 2012 Michel Capelle
Reputation Management System
Machine Learning in Practice Lecture 10 Carolyn Penstein Rosé Language Technologies Institute/ Human-Computer Interaction Institute.
Sentiment Analysis Using Common- Sense and Context Information Basant Agarwal 1,2, Namita Mittal 2, Pooja Bansal 2, and Sonal Garg 2 1 Department of Computer.
Multi-Class Sentiment Analysis with Clustering and Score Representation Yan Zhu.
Short Text Similarity with Word Embedding Date: 2016/03/28 Author: Tom Kenter, Maarten de Rijke Source: CIKM’15 Advisor: Jia-Ling Koh Speaker: Chih-Hsuan.
Kim Schouten, Flavius Frasincar, and Rommert Dekker
Aspect-Based Sentiment Analysis Using Lexico-Semantic Patterns
Aspect-Based Sentiment Analysis on the Web using Rhetorical Structure Theory Rowan Hoogervorst1, Erik Essink1, Wouter Jansen1, Max van den Helder1 Kim.
Erasmus University Rotterdam
Retrieval of audio testimonials via voice search
David Cyphert CS 2310 – Software Engineering
An Overview of Concepts and Selected Techniques
Review-Level Aspect-Based Sentiment Analysis Using an Ontology
Presentation transcript:

Determining Negation Scope and Strength in Sentiment Analysis SMC 2011 Paul van Iterson Erasmus School of Economics Erasmus University Rotterdam Bas Heerschop Erasmus School of Economics Erasmus University Rotterdam Flavius Frasincar Erasmus School of Economics Erasmus University Rotterdam Uzay Kaymak Erasmus School of Economics Erasmus University Rotterdam October 12, 2011 Alexander Hogenboom Erasmus School of Economics Erasmus University Rotterdam

Outline Introduction Sentiment Analysis Accounting for Negation Framework Evaluation Conclusions Future Work SMC

Introduction (1) Need for information monitoring tools for tracking sentiment in today’s complex systems The Web offers an overwhelming amount of textual data, containing traces of sentiment SMC

Introduction (2) Existing sentiment analysis approaches are based on word frequencies There is a tendency of involving various other aspects of content in automated sentiment analysis Accounting for negation seems promising, but how to model the influence of negation keywords on the conveyed sentiment? SMC

Sentiment Analysis Sentiment analysis is typically focused on determining the polarity of natural language texts Applications in summarizing reviews, determining a general mood (consumer confidence, politics) Common approach to sentiment analysis: –Creation of lexicon (list of words and their sentiment scores) –Utilization of lexicon to determine sentiment in text Sentiment analysis approaches differ on several distinguishing characteristic features, e.g., –Analysis level and focus –Handling of syntactic variations, amplification, and negation 55 SMC 2011

Accounting for Negation (1) Common approach: exploitation of negation keywords Challenge lies in finding the negation scope Sophisticated approaches involve complex rules, compositional semantics, or machine learning Many existing sentiment analysis frameworks use rather simple conceptualizations of negation scope 66 SMC 2011

Accounting for Negation (2) Let us consider the following positive sentence: –Example:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! Rest of Sentence (RoS): –Following:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! –Around:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! First Sentiment-Carrying Word (FSW): –Following:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! –Around:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! 77 SMC 2011

Accounting for Negation (3) Let us consider the following positive sentence: –Example:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! Next Non-Adverb (NNA): –Following:Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! Fixed Window Length (FWL): –Following (3):Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! –Around (3):Luckily, the smelly poo did not leave awfully nasty stains on my favorite shoes! 88 SMC 2011

Framework (1) Lexicon-based sentence-level sentiment scoring by using SentiWordNet Optional support for sentiment negation Individual words are scored in the range [-1,1] Word scores are used to classify a sentence as positive (1) or negative (-1) 99 SMC 2011

Framework (2) Score sentences in test corpus for their sentiment For an arbitrary sentence: –Retrieve all words (simple and compound) –Retrieve each words’ Part-Of-Speech (POS) and lemma –Disambiguate word senses (Lesk algorithm) –Retrieve words’ sentiment scores from lexicon –Negate sentiment scores of negated words, as determined by means of one of the considered approaches, by multiplying the scores with an inversion factor (typically negative) –Calculate sentence score as sum of words’ scores –Classify sentence as either positive (score ≥ 0) or negative (score < 0) 10 SMC 2011

Evaluation (1) Implementation in C#, Microsoft SQL Server database, SharpNLP-based POS tagger, WordNet.Net API for lemmatization and word sense disambiguation, SentiWordNet sentiment lexicon Corpus of 930 positive and 1,355 negative manually classified English movie review sentences (60% training set, 40% test set) 11 SMC 2011

Evaluation (2) Baseline: sentiment without accounting for negation Alternatives: negation scoping with RoS, FSW, NNA, and FWL (window sizes ranging from 1 to 4) Optimized inversion factor for best alternative to a value in the range [-2, 0] (hill-climbing on training set) 12 SMC 2011

Evaluation (3) MethodDirectionWindowInversionAccuracyMacro F1 Baseline--49.9%49.4% FSWFollowing-52.3%52.0% FWLFollowing151.3%51.0% FWLFollowing252.7%52.4% FWLFollowing352.0%51.7% FWLFollowing452.2%52.0% FWLFollowing %53.3% 13 SMC 2011

Conclusions Recent sentiment analysis methods consider more and more aspects of content other than word frequencies Our corpus-based evaluation of several common negation scoping methods shows that only some perform significantly better than our baseline of not accounting for negation FWL with a window of 2 words following a negation keyword yields the highest increase in accuracy (5.5%) and macro-level F1 (6.2%) compared to the baseline An optimized inversion factor of rather than -1 yields an accuracy increase of 7.0% and a macro-level F1 increase of 8.0% compared to the baseline SMC

Future Work Let the negation scope detection method depend on the position of a negation keyword Deeper understanding of semantics in order to cope with, e.g., context-dependent interpretations Distinct sentiment inversion factors for negated positive and negative words SMC

Questions? Alexander Hogenboom Erasmus School of Economics Erasmus University Rotterdam P.O. Box 1738, NL-3000 DR Rotterdam, the Netherlands SMC