Sentiment analysis and polarity detection is a type of text classification where natural language opinion is analyzed in order to classify it into either positive or negative categories. Classification of text into sentiment labels is a very difficult task as opinions expressed in natural language may contain abbreviations, slangs, sarcasm, irony and/or idioms. The proposed research focuses on the use of SentiWordNet3.0 as a labeled corpus for training purposes. We present a complete framework based on a dictionary named Normalized SentiMI (nSentiMI) which is created by calculating point-wise mutual information for each term/part-of-speech pair extracted from SentiWordNet. The proposed framework is applied on a dataset of 50,000 movie reviews to identify the value of a weight factor α and then evaluated on an unseen test dataset of 2000 movie reviews. Comparison with state of art techniques also confirms the superiority of proposed approach.
OhanaBTierneyB2009Sentiment classification of reviews using SentiWordNet9th IT&T Conference, Dublin Institute of TechnologyDublin, Ireland
2.
KennedyAInkpenD2006Sentiment classification of movie reviews using contextual valence shiftersComputational Intelligence22110125
3.
PangBLeeL2008Opinion mining and sentiment analysisFoundations and Trends in Information Retrieval21-21135
4.
EsuliASebastianiF2006Sentiwordnet: A publicly available lexical resource for opinion mining5th Conference on Language Resources and Evaluation
5.
PaltoglouG2014Sentiment analysis on social media. Online collaborative actionSpringer
6.
YeQZhangZLawR2009Sentiment classification of online reviews to travel destinations by supervised machine learning approachesmExpert Systems with Applications363Part 265276535Elsevier
7.
HanJKamberM2006Data Mining: Concepts and TechniquesSecond editionMorgan kaufmann
8.
YangYPedersenJO1997A comparative study on feature selection in text categorization14th ICML
9.
KazemzadehALeeSNarayananS2013Fuzzy logic models for the meaning of emotion wordsIEEE Computational Intelligence Magazine823449
10.
WilsonTWiebeJHoffmannP2009Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysisComputational Linguistics353399403
11.
ZhangCZengDLiJWangFZuoW2009Sentiment analysis of chinese document: From sentence to document levelJournal of the Association for Information Science and Technology601224742487
12.
TurneyP2002Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews40th Annual Meeting of ACL417424Philadelphia
13.
ReadJ2005Using emoticons to reduce dependency in machine learning techniques for sentiment classificationACL Student Research Workshop4348
14.
KeefeTKoprinskaI2009Feature Selection and Weighting Methods in Sentiment Analysis14th Australian Document Computing Symposium
15.
VermaSBhattacharyyaP2008Incorporating Semantic Knowledge for Sentiment Analysis. India6th International Conference on Natural Language Processing
16.
ReyesARossoP2014On the difficulty of automatically detecting irony: Beyond a simple case of negationKnowledge and Information Systems403595614
17.
BarndenJReyesAShutovaERossoPVealeT2015Sentiment analysis of figurative language in twitter. SemEval-task11
18.
BlitzerJDredzeMPereiraF2007Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. 45th ACL187205
19.
DredzeMCrammerKPereiraF2008Confidence-weighted linear classification25th International Conference on Machine Learning ACM264271
20.
PangBLeeLVaithyanathanS2002Thumbs up?: Sentiment classification using machine learning techniquesACL-02 Conference on Empirical Methods in Natural Language Processing107986
21.
AbbasiAFranceSZhangZChenH2011Selecting attributes for sentiment classification using feature relation networksIEEE Transactions on Knowledge and Data Engineering233447462
22.
WiegandMBalahurA2010A Survey on the Role of Negation in Sentiment AnalysisWorkshop on Negation and Speculation in Natural Language Processing
23.
JivaniAG2011A comparative study of Stemming algorithmsInternational Journal of Computer Technology and Applications2619301938
24.
JainAKPandeyY2013Analysis and implementation of sentiment classification using lexical POS markersInternational Journal of Computing, Comm and Networking213640
25.
LinYZhangJWangXZhouA2012An information theoretic approach to sentiment polarity classification2nd Joint WICOW/AIRWeb Workshop on Web Quality540ACM
26.
SaggionHFunkA2010Interpreting SentiWordNet for opinion classification7th LREC11291133
27.
LarsenRJMarxML2000An Introduction to Mathematical Statistics and Its ApplicationsThird EditionISBN 0-13-922303-7282
28.
CarrollSRCarrollDJ2002Statistics Made Simple for School LeadersRowman & LittlefieldRetrieved 7 June 2009
29.
YangCBhattacharyaSSrinivasanP2012Lexical and Machine Learning Approaches Toward Online Reputation ManagementCLEF (Online Working Notes/Labs/Workshop)
30.
TanSZhangJ2008An empirical study of sentiment analysis for chinese documentsExpert Systems with Applications34426222629
31.
SharmaADeyS2012Performance Investigation of Feature Selection Methods and Sentiment Lexicons for Sentiment AnalysisSpecial Issue of International Journal of Computer Applications (0975 –8887)–ACCTHPCA1520
32.
SocherRPenningtonJHuangEHNgAYManningCD2011Semi-supervised Recursive Autoencoders for Predicting Sentiment Distributions. EMNLP’11151161
33.
HeYZhouD2011Self-Training from Labeled Features for Sentiment AnalysisInformation processing and management
34.
VermaSBhattacharyyaP2008Incorporating Semantic Knowledge for Sentiment Analysis. IndiaProceedings of ICON-2008:6th International Conference on Natural Language Processing
