Advertisement

Personal and Ubiquitous Computing

, Volume 22, Issue 4, pp 723–737 | Cite as

Mood modeling: accuracy depends on active logging and reflection

  • Aaron Springer
  • Victoria Hollis
  • Steve Whittaker
Original Article

Abstract

Current behavior change systems often demand extremely advanced sensemaking skills, requiring users to interpret personal datasets in order to understand and change behavior. We describe EmotiCal, a system to help people better manage their emotions, that finesses such complex sensemaking by directly recommending specific mood-boosting behaviors to users. This paper first describes how we develop the accurate mood models that underlie these mood-boosting recommendations. We go on to analyze what types of information contribute most to the predictive power of such models, and how we might design systems to reliably collect such predictive information. Our results show that we can derive very accurate mood models with relatively small samples of just 70 users. These models explain 61% of variance by combining: (a) user reflection about the effects of different activities on mood, (b) user explanations of how different activities affect mood, and (c) individual differences. We discuss the implications of these findings for the design of behavior change systems, as well as for theory and practice. Contrary to many recent approaches, our findings argue for the importance of active user reflection rather than passive sensing.

Keywords

Mood Forecasting System Reflection Machine learning Well-being Emotion regulation 

References

  1. 1.
    Lin JJ, Mamykina L, Lindtner S, Delajoux G, Henry B (2006) Fish’n’Steps: encouraging physical activity with an interactive computer game. In: Int Conf Ubiquitous Comput Springer, Heidelberg, pp 261–278Google Scholar
  2. 2.
    Isaacs E, Konrad A, Walendowski A, Lennig T, Hollis, V, Whittaker S (2013) Echoes from the past: how technology mediated reflection improves well-being. ACM Press, New York, p 1071Google Scholar
  3. 3.
    LiKamWa R, Liu Y, Lane ND, Zhong L (2013) Moodscope: building a mood sensor from smartphone usage patterns. In: Proceeding 11th Annu. Int. Conf. Mob. Syst. Appl. Serv. ACM, pp 389–402Google Scholar
  4. 4.
    Barwais FA, Cuddihy TF, Tomson LM (2013) Physical activity, sedentary behavior and total wellness changes among sedentary adults: a 4-week randomized controlled trial. Health Qual Life Outcomes 11:183.  https://doi.org/10.1186/1477-7525-11-183 CrossRefGoogle Scholar
  5. 5.
    Cadmus-Bertram LA, Marcus BH, Patterson RE, Parker BA, Morey BL (2015) Randomized trial of a Fitbit-based physical activity intervention for women. Am J Prev Med 49:414–418.  https://doi.org/10.1016/j.amepre.2015.01.020 CrossRefGoogle Scholar
  6. 6.
    Peuhkuri K, Sihvola N, Korpela R (2012) Diet promotes sleep duration and quality. Nutr Res 32:309–319.  https://doi.org/10.1016/j.nutres.2012.03.009 CrossRefGoogle Scholar
  7. 7.
    Brockton West Roxbury VA (1997) Sleep, sleep deprivation, and daytime activities a randomized controlled trial of the effect of exercise on sleep. Sleep 20:95–101CrossRefGoogle Scholar
  8. 8.
    Cacioppo JT, Hawkley LC, Berntson GG, Ernst JM, Gibbs AC, Stickgold R, Hobson JA (2002) Do lonely days invade the nights? Potential social modulation of sleep efficiency. Psychol Sci 13:384–387CrossRefGoogle Scholar
  9. 9.
    Peters E, Hibbard J, Slovic P, Dieckmann N (2007) Numeracy skill and the communication, comprehension, and use of risk-benefit information. Health Aff (Millwood) 26:741–748.  https://doi.org/10.1377/hlthaff.26.3.741 CrossRefGoogle Scholar
  10. 10.
    Fitbit Fitbit App & Dashboard. https://www.fitbit.com/app. Accessed 7 Mar 2017
  11. 11.
    Jawbone Jawbone | JAMBOX Wireless Speakers | UP Wristband | Bluetooth Headsets. In: Jawbone. https://jawbone.com/support/articles/000005227/understanding-your-data. Accessed 7 Mar 2017
  12. 12.
    Bentley F, Tollmar K, Stephenson P, Levy L, Jones B, Robertson S, Price E, Catrambone R, Wilson J (2013) Health mashups: presenting statistical patterns between wellbeing data and context in natural language to promote behavior change. ACM Trans Comput-Hum Interact 20:1–27.  https://doi.org/10.1145/2503823 CrossRefGoogle Scholar
  13. 13.
    Gollwitzer PM (1999) Implementation intentions: strong effects of simple plans. Am Psychol 54:493–503CrossRefGoogle Scholar
  14. 14.
    Gilbert DT, Pinel EC, Wilson TD, Blumberg SJ, Wheatley TP (1998) Immune neglect: a source of durability bias in affective forecasting. J Pers Soc Psychol 75:617–638CrossRefGoogle Scholar
  15. 15.
    Tice DM, Bratslavsky E, Baumeister RF (2001) Emotional distress regulation takes precedence over impulse control: if you feel bad, do it! J Pers Soc Psychol 80:53–67.  https://doi.org/10.1037//0022-3514.80.1.53 CrossRefGoogle Scholar
  16. 16.
    Konrad A, Tucker S, Crane J, Whittaker S (2016) Technology and reflection: mood and memory mechanisms for well-being. Psychol Well-Being 6:5.  https://doi.org/10.1186/s13612-016-0045-3 CrossRefGoogle Scholar
  17. 17.
    Watkins PC, Mathews A, Williamson DA, Fuller RD (1992) Mood-congruent memory in depression: emotional priming or elaboration? J Abnorm Psychol 101:581–586CrossRefGoogle Scholar
  18. 18.
    Cuijpers P, van Straten A, Warmerdam L (2007) Behavioral activation treatments of depression: a meta-analysis. Clin Psychol Rev 27:318–326.  https://doi.org/10.1016/j.cpr.2006.11.001 CrossRefGoogle Scholar
  19. 19.
    Chung C, Pennebaker JW (2007) The psychological functions of function words. Soc Commun:343–359Google Scholar
  20. 20.
    Turner R, Ward M, Turner D (1979) Behavioral treatments for depression: an evaluation of their therapeutic components. J Clin Psychol 35:167–175CrossRefGoogle Scholar
  21. 21.
    Hollis V, Konrad A, Springer A, Antoun M, Antoun C, Martin R, Whittaker S (2017) What does all this data mean for my future mood? Actionable Analytics and Targeted Reflection for Emotional Well-Being. Human Comput Interact 32:208–267.  https://doi.org/10.1080/07370024.2016.1277724 CrossRefGoogle Scholar
  22. 22.
    Lane ND, Lin M, Mohammod M, Yang X, Lu H, Cardone G, Ali S, Doryab A, Berke E, Campbell AT, Choudhury T (2014) Bewell: sensing sleep, physical activities and social interactions to promote wellbeing. Mob Netw Appl 19:345–359.  https://doi.org/10.1007/s11036-013-0484-5 CrossRefGoogle Scholar
  23. 23.
    Larsen RJ (2000) Toward a science of mood regulation. Psychol Inq 11:129–141.  https://doi.org/10.1207/S15327965PLI1103_01 CrossRefGoogle Scholar
  24. 24.
    Russell JA (1991) Culture and the categorization of emotions. Psychol Bull 110:426–450.  https://doi.org/10.1037/0033-2909.110.3.426 CrossRefGoogle Scholar
  25. 25.
    Bradley MM, Greenwald MK, Petry MC, Lang PJ (1992) Remembering pictures: pleasure and arousal in memory. J Exp Psychol Learn Mem Cogn 18:379–390.  https://doi.org/10.1037/0278-7393.18.2.379 CrossRefGoogle Scholar
  26. 26.
    Plutchik R (2001) The nature of emotions. Am Sci 89:344–350CrossRefGoogle Scholar
  27. 27.
    Tellegen A (1985) Structures of mood and personality and their relevance to assessing anxiety, with an emphasis on self-report. In: Tuma AH, Maser JD (eds) Anxiety anxiety disord. Lawrence Erlbaum Associates, Inc, Hillsdale, pp 681–706Google Scholar
  28. 28.
    Stone AA, Schwartz JE, Schkade D, Schwarz N, Krueger A, Kahneman D (2006) A population approach to the study of emotion: diurnal rhythms of a working day examined with the day reconstruction method. Emotion 6:139–149.  https://doi.org/10.1037/1528-3542.6.1.139 CrossRefGoogle Scholar
  29. 29.
    Wilson T, Laser P, Stone J Judging the predictors of one’s own mood: accuracy and the use of shared theories. J Exp Soc Psychol 18:537–556Google Scholar
  30. 30.
    MacPhillamy D, Lewinsohn P (1982) The pleasant events schedule: studies on reliability, validity, and scale intercorrelation. J Consult Clin Psychol 50:363–380CrossRefGoogle Scholar
  31. 31.
    Lewinsohn PM, Amenson CS (1978) Some relations between pleasant and unpleasant mood-related events and depression. J Abnorm Psychol 87:644–654.  https://doi.org/10.1037/0021-843X.87.6.644 CrossRefGoogle Scholar
  32. 32.
    Robinson MD, Clore GL (2002) Belief and feeling: evidence for an accessibility model of emotional self-report. Psychol Bull 128:934–960.  https://doi.org/10.1037//0033-2909.128.6.934 CrossRefGoogle Scholar
  33. 33.
    Walker WR, Skowronski JJ, Thompson CP (2003) Life is pleasant—and memory helps to keep it that way! Rev Gen Psychol 7:203–210.  https://doi.org/10.1037/1089-2680.7.2.203 CrossRefGoogle Scholar
  34. 34.
    Zeiss AM, Lewinsohn PM, Muñoz RF (1979) Nonspecific improvement effects in depression using interpersonal skills training, pleasant activity schedules, or cognitive training. J Consult Clin Psychol 47:427–439CrossRefGoogle Scholar
  35. 35.
    Dobson KS, Joffe R (1986) The role of activity level and cognition in depressed mood in a university sample. J Clin Psychol 42(2):264–271Google Scholar
  36. 36.
    Seligman MEP, Steen TA, Park N, Peterson C (2005) Positive psychology progress: empirical validation of interventions. Am Psychol 60:410–421.  https://doi.org/10.1037/0003-066X.60.5.410 CrossRefGoogle Scholar
  37. 37.
    Parks AC, Della Porta MD, Pierce RS, Zilca R, Lyubomirsky S (2012) Pursuing happiness in everyday life: the characteristics and behaviors of online happiness seekers. Emotion 12:1222–1234.  https://doi.org/10.1037/a0028587 CrossRefGoogle Scholar
  38. 38.
    Hollis V, Konrad A, Whittaker S (2015) Change of heart: emotion tracking to promote behavior change. ACM Press, pp 2643–2652Google Scholar
  39. 39.
    Peesapati ST, Schwanda V, Schultz J, et al (2010) Pensieve: supporting everyday reminiscence. In: Proc SIGCHI Conf Hum Factors Comput Syst ACM, New York, NY, USA, pp 2027–2036Google Scholar
  40. 40.
    Bardram JE, Frost M, Szántó K, Marcu G (2012) The MONARCA self-assessment system: a persuasive personal monitoring system for bipolar patients. In: Proc. 2nd ACM SIGHIT Int. health inform. Symp. ACM, pp 21–30CrossRefGoogle Scholar
  41. 41.
    Doryab A, Frost M, Faurholt-Jepsen M, Kessing LV, Bardram JE (2015) Impact factor analysis: combining prediction with parameter ranking to reveal the impact of behavior on health outcome. Pers Ubiquitous Comput 19:355–365.  https://doi.org/10.1007/s00779-014-0826-8 CrossRefGoogle Scholar
  42. 42.
    Faurholt-Jepsen M, Vinberg M, Christensen EM, Frost M, Bardram J, Kessing LV (2013) Daily electronic self-monitoring of subjective and objective symptoms in bipolar disorder—the MONARCA trial protocol (MONitoring, treAtment and pRediCtion of bipolAr disorder episodes): a randomised controlled single-blind trial. BMJ Open 3:e003353–e003353.  https://doi.org/10.1136/bmjopen-2013-0033531 CrossRefGoogle Scholar
  43. 43.
    Russell JA, Pratt G (1980) A description of the affective quality attributed to environments. J Pers Soc Psychol 38:311–322.  https://doi.org/10.1037/0022-3514.38.2.311 CrossRefGoogle Scholar
  44. 44.
    Deci EL, Ryan RM (2000) The “what” and “why” of goal pursuits: human needs and the self-determination of behavior. Psychol Inq 11:227–268.  https://doi.org/10.1207/S15327965PLI1104_01 CrossRefGoogle Scholar
  45. 45.
    Bradley MM, Lang PJ (1994) Measuring emotion: the self-assessment manikin and the semantic differential. J Behav Ther Exp Psychiatry 25:49–59CrossRefGoogle Scholar
  46. 46.
    Seabold S, Perktold J (2010) Statsmodels: Econometric and statistical modeling with python. Proceedings of the 9th Python in Science Conference, AustinGoogle Scholar
  47. 47.
    Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830MathSciNetzbMATHGoogle Scholar
  48. 48.
    Pennebaker J, Booth R, Francis M (2007) Linguistic inquiry and word count: LIWC [computer software]. Austin, TXGoogle Scholar
  49. 49.
    Balahur A, Hermida JM, Montoyo A (2012) Building and exploiting EmotiNet, a knowledge base for emotion detection based on the appraisal theory model. IEEE Trans Affect Comput 3:88–101.  https://doi.org/10.1109/T-AFFC.2011.33 CrossRefGoogle Scholar
  50. 50.
    Chen Y-W, Lin C-J (2006) Combining SVMs with various feature selection strategies. In: Feature Extr Springer, pp 315–324Google Scholar
  51. 51.
    Goyal A, Riloff E, Daumé III H (2010) Automatically producing plot unit representations for narrative text. In: Proc. 2010 Conf. Empir. Methods Nat. Lang. Process. Association for Computational Linguistics, pp 77–86Google Scholar
  52. 52.
    Schein AI, Popescul A, Ungar LH, Pennock DM (2002) Methods and metrics for cold-start recommendations. ACM Press, p 253Google Scholar
  53. 53.
    Jackson DA (1993) Stopping rules in principal components analysis: a comparison of heuristical and statistical approaches. Ecology 74:2204–2214.  https://doi.org/10.2307/1939574 CrossRefGoogle Scholar
  54. 54.
    Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65CrossRefzbMATHGoogle Scholar
  55. 55.
    Liu S, Xie Y, Mcgree J, Ge Z (2016) Computational and statistical methods for analysing big data with applications. In: CERN Doc. Serv. http://cds.cern.ch/record/2204430. Accessed 13 Apr 2017
  56. 56.
    Wang R, Chen F, Chen Z, et al (2014) StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones. ACM Press, pp 3–14Google Scholar
  57. 57.
    Zisook M, Taylor S, Sano A, Picard R (2016) SNAPSHOT expose: stage based and social theory based applications to reduce stress and improve well-being.Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of California Santa CruzSanta CruzUSA

Personalised recommendations