Skip to main content

Seasonal Variation in Collective Mood via Twitter Content and Medical Purchases

  • Conference paper
  • First Online:
Advances in Intelligent Data Analysis XVI (IDA 2017)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 10584))

Included in the following conference series:

Abstract

The analysis of sentiment contained in vast amounts of Twitter messages has reliably shown seasonal patterns of variation in multiple studies, a finding that can have great importance in the understanding of seasonal affective disorders, particularly if related with known seasonal variations in certain hormones. An important question, however, is that of directly linking the signals coming from Twitter with other sources of evidence about average mood changes. Specifically we compare Twitter signals relative to anxiety, sadness, anger, and fatigue with purchase of items related to anxiety, stress and fatigue at a major UK Health and Beauty retailer. Results show that all of these signals are highly correlated and strongly seasonal, being under-expressed in the summer and over-expressed in the other seasons, with interesting differences and similarities across them. Anxiety signals, extracted from both Twitter and from Health product purchases, peak in spring and autumn, and correlate also with the purchase of stress remedies, while Twitter sadness has a peak in the Winter, along with Twitter anger and remedies for fatigue. Surprisingly, purchase of remedies for fatigue do not match the Twitter fatigue, suggesting that perhaps the names we give to these indicators are only approximate indications of what they actually measure. This study contributes both to the clarification of the mood signals contained in social media, and more generally to our understanding of seasonal cycles in collective mood.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    The data for purchases of over-the-counter Health products comes from a major UK health and beauty retailer, and has been made available to the University of Nottingham (JG), under an NDA agreement that restricts naming of the retailer. The raw data cannot be published, however examples of health and fatigue related products for which data has been made available are detailed in the “Appendix - Examples of health and fatigue related products”, but have been partly anonymized to respect this agreement.

References

  1. Bamman, D., Eisenstein, J., Schnoebelen, T.: Gender identity and lexical variation in social media. J. Sociolinguistics 18(2), 135–160 (2014)

    Article  Google Scholar 

  2. Dzogang, F., Lansdall-Welfare, T., Cristianini, N.: Seasonal fluctuations in collective mood revealed by wikipedia searches and twitter posts. In: 2016 IEEE International Conference on Data Mining Workshop (SENTIRE) (2016)

    Google Scholar 

  3. Gimpel, K., Schneider, N., O’Connor, B., Das, D., Mills, D., Eisenstein, J., Heilman, M., Yogatama, D., Flanigan, J., Smith, N.A.: Part-of-speech tagging for twitter: annotation, features, and experiments. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers, vol. 2, pp. 42–47 (2011)

    Google Scholar 

  4. Golder, S.A., Macy, M.W.: Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures. Science 333(6051), 1878–1881 (2011)

    Article  Google Scholar 

  5. Hadlow, N.C., Brown, S., Wardrop, R., Henley, D.: The effects of season, daylight saving and time of sunrise on serum cortisol in a large population. Chronobiol. Int. 31(2), 243–251 (2014)

    Article  Google Scholar 

  6. Lansdall-Welfare, T., Dzogang, F., Cristianini, N.: Change-point analysis of the public mood in UK twitter during the brexit referendum. In: 2016 IEEE International Conference on Data Mining in Politics Workshop (DMIP) (2016)

    Google Scholar 

  7. Leonard, W., Levy, S., Tarskaia, L., Klimova, T., Fedorova, V., Baltakhinova, M., Krivoshapkin, V., Snodgrass, J.: Seasonal variation in basal metabolic rates among the yakut (sakha) of northeastern siberia. Am. J. Hum. Biol. 26(4), 437–445 (2014)

    Article  Google Scholar 

  8. Melrose, S.: Seasonal affective disorder: an overview of assessment and treatment approaches. Depression Res. Treat. (2015)

    Google Scholar 

  9. Migaud, M., Butrille, L., Batailler, M.: Seasonal regulation of structural plasticity and neurogenesis in the adult mammalian brain: focus on the sheep hypothalamus. Front. Neuroendocrinol. 37, 146–157 (2015)

    Article  Google Scholar 

  10. Pennebaker, J.W., Boyd, R.L., Jordan, K., Blackburn, K.: The development and psychometric properties of liwc2015. Technical report (2015)

    Google Scholar 

  11. Piantadosi, S.T.: Zipfs word frequency law in natural language: a critical review and future directions. Psychon. Bull. Rev. 21(5), 1112–1130 (2014)

    Article  Google Scholar 

  12. Tausczik, Y.R., Pennebaker, J.W.: The psychological meaning of words: liwc and computerized text analysis methods. J. Lang. Soc. Psychol. 29(1), 24–54 (2010)

    Article  Google Scholar 

  13. Walton, J.C., Weil, Z.M., Nelson, R.J.: Influence of photoperiod on hormones, behavior, and immune function. Front. Neuroendocrinol. 32(3), 303–319 (2011)

    Article  Google Scholar 

  14. Watson, D., Clark, L.A.: The panas-x: manual for the positive and negative affect schedule-expanded form (1999)

    Google Scholar 

  15. Winthorst, W.H., Roest, A.M., Bos, E.H., Meesters, Y., Penninx, B.W., Nolen, W.A., Jonge, P.: Self-attributed seasonality of mood and behavior: a report from the netherlands study of depression and anxiety. Depress. Anxiety 31(6), 517–523 (2014)

    Article  Google Scholar 

Download references

Acknowledgments

NC and FD are supported by the ERC advanced Grant ThinkBig. JG is supported by the EPSRC Neodemographics grant, EP/L021080/1.

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Fabon Dzogang or Nello Cristianini .

Editor information

Editors and Affiliations

Appendix

Appendix

Greeting messages. The signal about mood could be skewed by the presence of large amounts of standardised greeting messages in specific seasons, which make use of mood related words, while not expressing the mood of the writer. These standard greeting messages were removed from the data as follows: we ignored any Twitter post containing the word happy, merry, good, lovely, nice, great, or wonderful followed by either of christmas, halloween, valentine, easter, new year, mothers’ day, fathers’ day, and their variants (e.g. starting with a leading # or separated by a dash, a space or ending with ’s when applicable) was not considered for analysis.

Table 4. Most popular mood words extracted from Twitter based on the LIWC word lists. Our indicator of fatigue on the social platform is based on the PANAS word list, formed by just four words.

We verified that posts matching this pattern were indeed concentrated in very specific days (the expected ones for each holiday).

Examples of mood and fatigue keywords. Table 4 illustrates the most popular words on Twitter for each indicator of mood and for fatigue. The mood keywords are based on the LIWC word lists, those for fatigue are based on the PANAS word list.

Fig. 4.
figure 4

Top 10 most popular Health products presented for the searches anxiety, stress, and fatigue on the retailer’s online web interface.

Examples of health and fatigue related product. Fig. 4 gives an example of the most popular products for the searches anxiety, stress, and fatigue on the UK Health and Beauty retailer’s online web interface, as queried on May 2017.

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Dzogang, F., Goulding, J., Lightman, S., Cristianini, N. (2017). Seasonal Variation in Collective Mood via Twitter Content and Medical Purchases. In: Adams, N., Tucker, A., Weston, D. (eds) Advances in Intelligent Data Analysis XVI. IDA 2017. Lecture Notes in Computer Science(), vol 10584. Springer, Cham. https://doi.org/10.1007/978-3-319-68765-0_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-68765-0_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-68764-3

  • Online ISBN: 978-3-319-68765-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics