Real-Time Twitter Sentiment toward Thanksgiving and Christmas Holidays


Thanksgiving and Christmas are two major holidays in the United States. Many people use social media to stay connected with their families and friends, including sharing their holiday experiences. This study utilized a stream of millions of tweets on Twitter to explore how people feel about these two holidays through real-time sentiment analysis. With help of Twitter Streaming API, we discovered the patterns of sentiment changes by hour before and after the two holidays in 2011, thus providing a unique peek into the celebration of these holidays that could not be accomplished with traditional methods. Our analysis suggested that in 2011 people had higher sentiment toward Christmas than Thanksgiving on average. The sentiment reached its maximum on the Thanksgiving Day and on The Christmas Eve and Christmas Day, highlighting stronger zeal for Christmas than Thanksgiving, while remained a stable and lower sentiment before and after the holidays. Typically there was a peak of sentiment toward Thanksgiving and Christmas in the morning of each day around 9:00am (EST). On the Thanksgiving Day the number of tweets on shopping increased rapidly and monotonically to its maximum as time approaching the midnight when people thinking of shopping on the Black Friday, but unexpectedly the sentiment toward shopping dropped quickly and monotonically, displaying the exact opposite trend. We also investigated the shopping distraction on the theme of these two holidays. It was found that there were more people talking about thankfulness than shopping during the Thanksgiving season, but more people talking about shopping than Jesus during the Christmas season.

Share and Cite:

Hu, W. (2013) Real-Time Twitter Sentiment toward Thanksgiving and Christmas Holidays. Social Networking, 2, 77-86. doi: 10.4236/sn.2013.22009.

Conflicts of Interest

The authors declare no conflicts of interest.


[3] B. Pang and L. Lee, “Opinion Mining and Sentiment Analysis, Foundations and Trends in Information Retrieval,” Vol. 2, No. 1-2, 2008, pp. 1-135. doi:10.1561/1500000011
[4] A. Pak and P. Paroubek, “Twitter as a Corpus for Sentiment Analysis and Opinion Mining,” Proceedings of LREC, Valletta, 19-21 May 2010.
[5] M. Q. Hu and B. Liu, “Mining and Summarizing Customer Reviews,” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD-2004), Seattle, 22-25 August 2004, pp. 168-177.
[6] L. Velikovich, S. Blair-Goldensohn, K. Hannan and R. McDonald, “The Viability of Web-Derived Polarity Lexicons, Human Language Technologies,” The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Los Angeles, 2-4 June 2010.
[7] B. O’Connor, R. Balasubramanyan, B. R. Routledge and N. A. Smith, “From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series,” Proceedings of the International AAAI Conference on Weblogs and Social Media, 23-26 May 2010, Washington DC, pp. 122-129.
[8] W. Hu, “Real-Time Twitter Sentiment toward Midterm Exams,” Sociology Mind, Vol. 2, No. 2, 2012, pp. 177- 184. doi:10.4236/sm.2012.22023

Copyright © 2022 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.