Semantic Filtering in Social Media for Trend Modeling

Applications that utilize publically available content from the web have been successful in tracking major events across a number of areas. We have developed a method of filtering to characterize trends of consumer behavior in relationship to specific products using the Twitter messaging system. Our process considers semantics at three successive levels to determine a demand signal. This begins with the establishment of ground truth keywords followed by word-level and category-level empirical keywords. Next, semantic categories of humor, emotion and negation are considered. Following, a classifier is applied for additional filtering to further support the characterization of consumer behavior. We apply this procedure to the goal of modeling vehicle purchase behavior with data acquired from Twitter. Results present strong correlation to sales data, allowing for contributions to forecasting efforts as well as Customer Relationship Management (CRM).

[1]  Fang Wu,et al.  Social Networks that Matter: Twitter Under the Microscope , 2008, First Monday.

[2]  Ruifeng Xu,et al.  Corse-fine opinion mining , 2009, 2009 International Conference on Machine Learning and Cybernetics.

[3]  David A. Ostrowski.  Predictive Semantic Social Media Analysis , 2011, 2011 IEEE Fifth International Conference on Semantic Computing.

[4]  Johan Bos,et al.  Predicting the 2011 Dutch Senate Election Results with Twitter , 2012 .

[5]  Mark A. Bedau,et al.  Twitter Keyword Volume, Current Spending, and Weekday Spending Norms Predict Consumer Spending , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[6]  C. Baird,et al.  From social media to social customer relationship management , 2013, IEEE Engineering Management Review.

[7]  Kam-Fai Wong,et al.  The Unified Collocation Framework for Opinion Mining , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[8]  Edoardo M. Airoldi,et al.  Markov Blankets and Meta-heuristics Search: Sentiment Extraction from Unstructured Texts , 2004, WebKDD.

[9]  A. Smeaton,et al.  On Using Twitter to Monitor Political Sentiment and Predict Election Results , 2011 .

[10]  Bernardo A. Huberman,et al.  Predicting the Future with Social Media , 2010, Web Intelligence.

[11]  Hosung Park,et al.  What is Twitter, a social network or a news media? , 2010, WWW '10.

[12]  Detlef Schoder,et al.  Web Science 2.0: Identifying Trends through Semantic Social Network Analysis , 2008, 2009 International Conference on Computational Science and Engineering.

[13]  Alberto Maria Segre,et al.  The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic , 2011, PloS one.

[14]  Anat Keinan,et al.  Cómo capitalizar el efecto del desaventejado , 2010 .

[15]  Shishir K. Shandilya,et al.  Automatic Opinion Extraction from Web Documents , 2009, 2009 International Conference on Computer and Automation Engineering.

[16]  Daryl Travis.  BRANDING IN THE DIGITAL AGE , 2001 .

[17]  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.

[18]  David C. Edelman.  Branding in The Digital Age You're Spending Your Money In All the Wrong Places , 2010 .

[19]  G. Eysenbach,et al.  Pandemics in the Age of Twitter: Content Analysis of Tweets during the 2009 H1N1 Outbreak , 2010, PloS one.

[20]  Andrew McCallum,et al.  Topics over time: a non-Markov continuous-time model of topical trends , 2006, KDD '06.

[21]  Isabell M. Welpe,et al.  Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment , 2010, ICWSM.