根據世界衛生組織(WHO)的調查，憂鬱問題是現今社會非常嚴重的現象，而自我覺察是能夠有效改善憂鬱及負面情緒的方式。另外行為心理學上也指出人的行為模式與其心理狀態有關係，手機使用的行為模式亦是如此，且隨著智慧型手機使用人口的成長，近年來有越來越多的研究者嘗試找出手機使用行為與使用者情緒的關係。本研究嘗試利用手機上的操作紀錄來推測使用者的憂鬱情緒狀態，藉此達到心理狀況監測以提升負面情自覺。
本研究設計一款觀測負面情緒的感受量尺標記系統，且利用手機上螢幕顯示的應用程式名稱作為手機使用行為的基本資料。本研究透過數個不同大小的時間區間來決定使用特徵與情緒標記是否有關係。反應情緒的使用特徵因人而異，本研究利用了數種不同的特徵選擇方式來選取每位使用者的個人行為特徵，同時也考慮多種分類器來當作機器學習模型。總括來說，本研究考慮了四種時間區間大小、五種特徵擷取方式，以及四種分類器，此三者的每一種組合都可以視為一個模型。最後我們設計了一套模型選擇流程來選出最佳的組合做為負面情緒的偵測系統。
每個人有其自己的手機操特徵，因此我們利用個人的資料來訓練個人化的偵測系統。個人化的偵測系統分別在憂鬱、焦慮、壓力三種感受量尺上分別有81.98%、84.58%、以及82.96%的平均準確率，高於Microsoft的MoodScope系統中使用的線性回歸方式、以及預測使用者情緒為最常出現之情緒這兩種方式。系統也透過個人化的模型交給使用者，進行7天以上的實際使用驗證，結果顯示偵測模型在實際使用時有85.9%的準確率。
本研究研發了一套基於手機操作行為的負面情緒前偵測系統，透過14天的訓練資料收集，偵測系統可以透過過去2小時內的手機行為特徵來做負面情緒的偵測。在臨床應用上，模型可以輔助生態瞬時紀錄的療程，透過給予使用著自我情緒狀況的資訊，讓使用者在負面情緒發生前有所自覺，達到前偵測之目的。

According to the World Health Organization (WHO), depression is currently one of many serious problems, and awareness of negative emotions is helpful for treating it. Behavioral patterns can either be an antecedent or a consequence of human emotion. For example, usage patterns on smartphones can reflect the user’s emotion. With the popularity of smartphone ownership, researchers are beginning to examine the association of smartphone usage patterns with emotional conditions. This study uses smart phone usage patterns to detect emotional states, aiming to improve self-awareness of negative emotion.
We developed three Visual Analogue Scales to measure and mark the emotional status. The package names of applications shown on the light-on screen are recorded as phone usages. The timeslots were set for each emotion mark in order to determine whether a usage feature is associated with the mark or not. Different users may have different usage patterns that reflect their emotions. We utilize several feature selection methods and classifiers to determine personalized usage features for the machine learning. In summary, we considered four timeslots, five feature selection methods, and four classifiers; each combination can be viewed as a model. Finally, we developed a detection model selection method based on Rank product scoring to narrow down the combinations and to choose the best combination for the detection model.
The user has his/her distinct behavioral pattern on the smartphone. This unique data was used to train our personalized detection model. All personalized detection models achieved an average accuracy of 81.98 %, 84.58 %, and 82.96 % for detecting depression, anxiety, and stress, respectively, and outperformed the two baseline methods: linear regression (as applied by Microsoft’s MoodScope system) and general guessing. The general guessing method considers all detections according to the level of emotional conditions that appears most frequently. The personalized models were sent back to subjects for further evaluation and the results showed that the models predicted their emotional states with an accuracy rate of 85.9%.
We have developed an early negative emotion detection model for smartphones that, after a 14-day personalized training period, is able to detect negative emotional states based on the smartphone usage patterns two hours before detection. This model has a potential for ecological momentary intervention for depressive disorders by envisioning negative emotions and informing the users how they have interacted with the smartphone before they actually reach negative emotional status.

[1] Bauer, G. and Lukowicz, P., "Can smartphones detect stress-related changes in the behaviour of individuals?," in Pervasive Computing and Communications Workshops (PERCOM Workshops), 2012 IEEE International Conference on, pp.423-426, 2012.
[2] Beck, A. T., Steer, R. A., and Carbin, M. G., "Psychometric properties of the Beck Depression Inventory: Twenty-five years of evaluation," Clinical psychology review, Vol.8, No.1, pp.77-100, 1988.
[3] Breitling, R., Armengauda, P., Amtmanna, A., and Herzyk, P., "Rank products: a simple, yet powerful, new method to detect differentially regulated genes in replicated microarray experiments.," Federation of European Biochemical Societies, 2004.
[4] Burns, M. N., Begale, M., Duffecy, J., Gergle, D., Karr, C. J., Giangrande, E., and Mohr, D. C., "Harnessing context sensing to develop a mobile intervention for depression," Journal of Medical Internet Research, Vol.13, No.3, 2011.
[5] Business_Insider, "How Much Time Do We Really Spend On Our Smartphones Every Day? http://www.businessinsider.com.au/how-much-time-do-we-spend-on-smartphones-2013-6," 2013,
[6] Chang, K.-h., Fisher, D., Canny, J., and Hartmann, B., "How's my mood and stress?: an efficient speech analysis library for unobtrusive monitoring on mobile phones," in Proceedings of the 6th International Conference on Body Area Networks, pp.71-77, 2011.
[7] Chittaranjan, G., Blom, J., and Gatica-Perez, D., "Mining large-scale smartphone data for personality studies," Personal and Ubiquitous Computing, Vol.17, No.3, pp.433-450, 2013.
[8] Church, K., Hoggan, E., and Oliver, N., "A study of mobile mood awareness and communication through MobiMood," in Proceedings of the 6th Nordic Conference on Human-Computer Interaction: Extending Boundaries, pp.128-137, 2010.
[9] Csikszentmihalyi, M. and Larson, R., "Validity and reliability of the experience-sampling method," The Journal of nervous and mental disease, Vol.175, No.9, pp.526-536, 1987.
[10] De Choudhury, M., Counts, S., and Horvitz, E., "Predicting postpartum changes in emotion and behavior via social media," in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp.3267-3276, 2013.
[11] Do, T.-M.-T. and Gatica-Perez, D., "By their apps you shall understand them: mining large-scale patterns of mobile phone usage," in Proceedings of the 9th International Conference on Mobile and Ubiquitous Multimedia, p.27, 2010.
[12] Do, T. M. T., Blom, J., and Gatica-Perez, D., "Smartphone usage in the wild: a large-scale analysis of applications and context," in Proceedings of the 13th international conference on multimodal interfaces, pp.353-360, 2011.
[13] Dolan, R. J., "Emotion, cognition, and behavior," Science, Vol.298, No.5596, pp.1191-1194, 2002.
[14] eMarketer, "Smartphone Users Worldwide Will Total 1.75 Billion in 2014 http://www.emarketer.com/Article/Smartphone-Users-Worldwide-Will-Total-175-Billion-2014/1010536#sthash.764ygbiV.dpuf," 2014,
[15] Faurholt-Jepsen, M., Frost, M., Vinberg, M., Christensen, E. M., Bardram, J. E., and Kessing, L. V., "Smartphone data as objective measures of bipolar disorder symptoms," Psychiatry Research, Vol.217, No.1, pp.124-127, 2014.
[16] Geven, A., Tscheligi, M., and Noldus, L., "Measuring Mobile Emotions: Measuring the Impossible?," in Proceedings of the 11th International Conference on Human-Computer Interaction with Mobile Devices and Services, p.109, 2009.
[17] Gil, G. B., Berlanga, A., and Molina, J. M., EmotionContext: user emotion dataset using smartphones, in Ambient Assisted Living and Home Care. 2012, Springer. p. 371-374.
[18] HELPGUIDE.org, "Depression Symtoms & Warning Signs http://www.helpguide.org/mental/depression_signs_types_diagnosis_treatment.htm,"
[19] Herdem, K. C., "Reactions: Twitter based mobile application for awareness of friends' emotions," in Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pp.796-797, 2012.
[20] Hernandez, J., Hoque, M. E., Drevo, W., and Picard, R. W., "Mood meter: counting smiles in the wild," in Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pp.301-310, 2012.
[21] Hung, J. C., Chang, L., Wang, Y.-B., Lee, M.-F., and Lee, Y.-H., "Emotional classification model for tourism base on the point of view of life-record," 2010.
[22] Kim, H.-J. and Choi, Y. S., "Exploring emotional preference for smartphone applications," in Consumer Communications and Networking Conference (CCNC), 2012 IEEE, pp.245-249, 2012.
[23] Kim, M., Kim, H.-J., Lee, S.-J., and Choi, Y. S., "A touch based affective user interface for smartphone," in Consumer Electronics (ICCE), 2013 IEEE International Conference on, pp.606-607, 2013.
[24] Kiukkonen, N., Blom, J., Dousse, O., Gatica-Perez, D., and Laurila, J., "Towards rich mobile phone datasets: Lausanne data collection campaign," Proc. ICPS, Berlin, 2010.
[25] Lane, N. D., Mohammod, M., Lin, M., Yang, X., Lu, H., Ali, S., Doryab, A., Berke, E., Choudhury, T., and Campbell, A., "Bewell: A smartphone application to monitor, model and promote wellbeing," in 5th International ICST Conference on Pervasive Computing Technologies for Healthcare, pp.23-26, 2011.
[26] LiKamWa, R., Liu, Y., Lane, N. D., and Zhong, L., "Can your smartphone infer your mood?," in PhoneSense workshop, 2011.
[27] LiKamWa, R., Liu, Y., Lane, N. D., and Zhong, L., "Moodscope: building a mood sensor from smartphone usage patterns," in Proceeding of the 11th annual international conference on Mobile systems, applications, and services, pp.389-402, 2013.
[28] Mehrabian, A., "Pleasure-arousal-dominance: A general framework for describing and measuring individual differences in temperament," Current Psychology, Vol.14, No.4, pp.261-292, 1996.
[29] Mental_Health_Foundation, "Mental Health Statistics http://www.mentalhealth.org.uk/help-information/mental-health-statistics/,"
[30] Morris, M. E., Kathawala, Q., Leen, T. K., Gorenstein, E. E., Guilak, F., Labhard, M., and Deleeuw, W., "Mobile therapy: case study evaluations of a cell phone application for emotional self-awareness," Journal of Medical Internet Research, Vol.12, No.2, 2010.
[31] Muaremi, A., Arnrich, B., and Tröster, G., "Towards Measuring Stress with Smartphones and Wearable Devices During Workday and Sleep," BioNanoScience, Vol.3, No.2, pp.172-183, 2013.
[32] Nielek, R. and Wierzbicki, A., Emotion aware mobile application, in Computational Collective Intelligence. Technologies and Applications. 2010, Springer. p. 122-131.
[33] pfizer, "Patient Health Questionnaire http://www.phqscreeners.com/,"
[34] Pyszczynski, T. and Greenberg, J., "Self-regulatory perseveration and the depressive self-focusing style: a self-awareness theory of reactive depression," Psychological Bulletin, Vol.102, No.1, p.122, 1987.
[35] Torous, J., Friedman, R., and Keshvan, M., "Smartphone ownership and interest in mobile applications to monitor symptoms of mental health conditions," JMIR MHEALTH AND UHEALTH, Vol.2, No.1, p.e2, 2014.
[36] Vastenburg, M., Romero Herrera, N., Van Bel, D., and Desmet, P., "PMRI: development of a pictorial mood reporting instrument," in CHI'11 Extended Abstracts on Human Factors in Computing Systems, pp.2155-2160, 2011.
[37] WebMD_Depression_Health_Center, "How Stress, Anxiety, and Depression Affect Your Health http://www.webmd.com/depression/stress-anxiety-depression," 2012,
[38] World_Health_Organization, "Depression http://www.who.int/mediacentre/factsheets/fs369/en/," 2012,
[39] Yang, N. and Samuel, A., " Context-rich Detection of User's Emotions Using A Smartphone," Microsoft Research Internship Report, 2011.
[40] Zhang, Y., Tang, J., Sun, J., Chen, Y., and Rao, J., "MoodCast: emotion prediction via dynamic continuous factor graph model," in Data Mining (ICDM), 2010 IEEE 10th International Conference on, pp.1193-1198, 2010.