Using Twitter to Predict Sales: A Case Study

This paper studies the relation between activity on Twitter and sales. While research exists into the relation between Tweets and movie and book sales, this paper shows that the same relations do not hold for products that receive less attention on social media. For such products, classification of Tweets is far more important to determine a relation. Also, for such products advanced statistical relations, in addition to correlation, are required to relate Twitter activity and sales. In a case study that involves Tweets and sales from a company in four countries, the paper shows how, by classifying Tweets, such relations can be identified. In particular, the paper shows evidence that positive Tweets by persons (as opposed to companies) can be used to forecast sales and that peaks in positive Tweets by persons are strongly related to an increase in sales. These results can be used to improve sales forecasts and to increase sales in marketing campaigns.

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

[2]  Hakan Ferhatosmanoglu,et al.  Short text classification in twitter to improve information filtering , 2010, SIGIR.

[3]  W. H. M. Zijm,et al.  Generic planning and control of automated material handling systems: Practical requirements versus existing theory , 2013, Comput. Ind..

[4]  Ramanathan V. Guha,et al.  The predictive power of online chatter , 2005, KDD '05.

[5]  Mark Dredze,et al.  You Are What You Tweet: Analyzing Twitter for Public Health , 2011, ICWSM.

[6]  Erwin W. Hans,et al.  Vehicle routing under time-dependent travel times: The impact of congestion avoidance , 2012, Comput. Oper. Res..

[7]  Daniel Gayo-Avello,et al.  No, You Cannot Predict Elections with Twitter , 2012, IEEE Internet Comput..

[8]  JungherrAndreas,et al.  Why the Pirate Party Won the German Election of 2009 or The Trouble With Predictions , 2012 .

[9]  Duncan J. Watts,et al.  Everyone's an influencer: quantifying influence on twitter , 2011, WSDM '11.

[10]  Timothy W. Finin,et al.  Why we twitter: understanding microblogging usage and communities , 2007, WebKDD/SNA-KDD '07.

[11]  Connie St Louis,et al.  Can Twitter predict disease outbreaks? , 2012, BMJ : British Medical Journal.

[12]  P. Gloor,et al.  Predicting Stock Market Indicators Through Twitter “I hope it is not as bad as I fear” , 2011 .

[13]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[14]  Rimmert van der Kooij,et al.  Simulation framework to analyze Operating Room release mechanisms , 2014, Proceedings of the Winter Simulation Conference 2014.

[15]  Jo van Nunen,et al.  Dynamic demand fulfillment in spare parts networks with multiple customer classes , 2013, Eur. J. Oper. Res..

[16]  Paul Grefen,et al.  The development of measures of process harmonization , 2013 .

[17]  Aron Culotta,et al.  Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages , 2012, Language Resources and Evaluation.

[18]  Stephen Dann,et al.  Twitter content classification , 2010, First Monday.

[19]  CulottaAron Lightweight methods to estimate influenza rates and alcohol sales volume from Twitter messages , 2013 .

[20]  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.

[21]  K Kristina Sharypova,et al.  Scheduled service network design with synchronization and transshipment constraints for intermodal container transportation networks , 2012 .

[22]  Tom Van Woensel,et al.  A Vehicle Routing Problem with Flexible Time Windows , 2014, Comput. Oper. Res..

[23]  Egon Lüftenegger,et al.  The state of the art of innovation-driven business models in the financial services industry , 2010 .

[24]  Kmr Kristel Hoen,et al.  Effect of carbon emission regulations on transport mode selection in supply chains , 2010 .

[25]  Soo-Min Kim,et al.  Crystal: Analyzing Predictive Opinions on the Web , 2007, EMNLP.

[26]  Bernard J. Jansen,et al.  Twitter power: Tweets as electronic word of mouth , 2009, J. Assoc. Inf. Sci. Technol..

[27]  Y. Sheffi,et al.  Relationship between freight accessibility and logistics employment in US counties , 2013 .

[28]  Erwin W. Hans,et al.  Improve OR-schedule to reduce number of required beds , 2012 .

[29]  Virgílio A. F. Almeida,et al.  Detecting Spammers on Twitter , 2010 .

[30]  Kmr Kristel Hoen,et al.  Effect of carbon emission regulations on transport mode selection under stochastic demand , 2014 .

[31]  de Ag Ton Kok Inventory control with manufacturing lead time flexibility , 2011 .

[32]  Mor Naaman,et al.  Is it really about me?: message content in social awareness streams , 2010, CSCW '10.

[33]  Simme Douwe Flapper,et al.  Aggregate overhaul and supply chain planning for rotables , 2015, Ann. Oper. Res..

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

[35]  Barry Wellman,et al.  Geography of Twitter networks , 2012, Soc. Networks.

[36]  Rji Rob Basten,et al.  An iterative method for the simultaneous optimization of repair decisions and spare parts stocks , 2009 .

[37]  van Gjjan Geert-Jan Houtum,et al.  Inventory planning for spare parts networks with delivery time requirements , 2009 .

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

[39]  Paul Grefen,et al.  An efficient method to construct minimal protocol adaptors , 2009 .

[40]  Rob J. I. Basten,et al.  An optimal approach for the joint problem of level of repair analysis and spare parts stocking , 2010 .

[41]  Daniel E. O'Leary,et al.  Event Study Methodologies in Information Systems Research , 2011, Int. J. Account. Inf. Syst..

[42]  Michael J. Cafarella,et al.  Using Social Media to Measure Labor Market Flows , 2014 .

[43]  Krishna P. Gummadi,et al.  Measuring User Influence in Twitter: The Million Follower Fallacy , 2010, ICWSM.

[44]  Mizuki Morita,et al.  Twitter Catches The Flu: Detecting Influenza Epidemics using Twitter , 2011, EMNLP.

[45]  Alex Hai Wang,et al.  Don't follow me: Spam detection in Twitter , 2010, 2010 International Conference on Security and Cryptography (SECRYPT).

[46]  Martijn Mes,et al.  A generalized simulation model of an integrated emergency post , 2012, Proceedings Title: Proceedings of the 2012 Winter Simulation Conference (WSC).

[47]  Ahmad Al Hanbali,et al.  Last time buy and repair decisions for spare parts , 2015, Eur. J. Oper. Res..

[48]  J. Fransoo,et al.  Regional logistics land allocation policies: Stimulating spatial concentration of logistics firms , 2013 .

[49]  Egon Lüftenegger,et al.  A Framework for Business Innovation Directions , 2011 .

[50]  Jeremy Ginsberg,et al.  Detecting influenza epidemics using search engine query data , 2009, Nature.

[51]  Hajo A. Reijers,et al.  The link between product data model and process model : the effect of changes in the product data model on the process model , 2009 .