Improved lexicon-based sentiment analysis for social media analytics

Social media channels, such as Facebook or Twitter, allow for people to express their views and opinions about any public topics. Public sentiment related to future events, such as demonstrations or parades, indicate public attitude and therefore may be applied while trying to estimate the level of disruption and disorder during such events. Consequently, sentiment analysis of social media content may be of interest for different organisations, especially in security and law enforcement sectors. This paper presents a new lexicon-based sentiment analysis algorithm that has been designed with the main focus on real time Twitter content analysis. The algorithm consists of two key components, namely sentiment normalisation and evidence-based combination function, which have been used in order to estimate the intensity of the sentiment rather than positive/negative label and to support the mixed sentiment classification process. Finally, we illustrate a case study examining the relation between negative sentiment of twitter posts related to English Defence League and the level of disorder during the organisation’s related events.

[1]  Andrea Esuli,et al.  SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining , 2006, LREC.

[2]  Fei Wang,et al.  Listening to the Crowd: Automated Analysis of Events via Aggregated Twitter Sentiment , 2013, IJCAI.

[3]  Peter A. Gloor,et al.  Predicting Movie Success and Academy Awards through Sentiment and Social Network Analysis , 2008, ECIS.

[4]  Wenji Mao,et al.  Predicting Popularity of Forum Threads for Public Events Security , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.

[5]  Joel Brynielsson,et al.  Mining the Web for Sympathy: The Pussy Riot Case , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.

[6]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[7]  Xiaojin Zhu,et al.  Fast learning for sentiment analysis on bullying , 2012, WISDOM '12.

[8]  Alan F. Smeaton,et al.  Combining Social Network Analysis and Sentiment Analysis to Explore the Potential for Online Radicalisation , 2009, 2009 International Conference on Advances in Social Network Analysis and Mining.

[9]  Mario Cataldi,et al.  Emerging topic detection on Twitter based on temporal and social terms evaluation , 2010, MDMKDD '10.

[10]  Aitor García,et al.  A Lexicon based sentiment analysis retrieval system for tourism domain. , 2012, ICIT 2012.

[11]  Nello Cristianini,et al.  Flu Detector - Tracking Epidemics on Twitter , 2010, ECML/PKDD.

[12]  Son Doan,et al.  An analysis of Twitter messages in the 2011 Tohoku Earthquake , 2011, eHealth.

[13]  Yaxin Bi,et al.  Twitter Sentiment Analysis for Security-Related Information Gathering , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.

[14]  Martijn Spitters,et al.  Threat Detection in Tweets with Trigger Patterns and Contextual Cues , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.

[15]  Richard Colbaugh,et al.  Agile Sentiment Analysis of Social Media Content for Security Informatics Applications , 2011, 2011 European Intelligence and Security Informatics Conference.

[16]  Juan Luis Castro,et al.  Lexicon-based Comments-oriented News Sentiment Analyzer system , 2012, Expert Syst. Appl..

[17]  Lisa Kaati,et al.  Detecting Linguistic Markers for Radical Violence in Social Media , 2014 .

[18]  Henry A. Kautz,et al.  Predicting Disease Transmission from Geo-Tagged Micro-Blog Data , 2012, AAAI.

[19]  Anshul Mittal,et al.  Stock Prediction Using Twitter Sentiment Analysis , 2011 .

[20]  Hsinchun Chen,et al.  Identifying Top Sellers In Underground Economy Using Deep Learning-Based Sentiment Analysis , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.

[21]  Bernardo A. Huberman,et al.  Predicting the Future with Social Media , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[22]  Michael L. Littman,et al.  Measuring praise and criticism: Inference of semantic orientation from association , 2003, TOIS.

[23]  Y. Matsuo,et al.  Tweet trend analysis in an emergency situation , 2011, SWID '11.

[24]  Markus Zanker,et al.  Classification of Customer Reviews based on Sentiment Analysis , 2012, ENTER.

[25]  James Pustejovsky,et al.  A factuality profiler for eventualities in text , 2008 .

[26]  Richard Colbaugh,et al.  Analyzing Social Media Content for Security Informatics , 2013, 2013 European Intelligence and Security Informatics Conference.

[27]  Richard Colbaugh,et al.  Web Analytics for Security Informatics , 2011, 2011 European Intelligence and Security Informatics Conference.

[28]  Jun Zhao,et al.  A Weakly Supervised Bayesian Model for Violence Detection in Social Media , 2013, IJCNLP.

[29]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[30]  Heng Ji,et al.  The Nature of Communications and Emerging Communities on Twitter Following the 2013 Syria Sarin Gas Attacks , 2014, 2014 IEEE Joint Intelligence and Security Informatics Conference.