Public wellbeing analytics framework using social media chatter data
Tóm tắt
Public wellbeing has always been crucial. Many governments around the globe prioritize the impact of their decisions on public wellbeing. In this paper, we propose an end-to-end public wellbeing analytics framework designed to predict the public’s wellbeing status and infer insights through the continuous analysis of social media content over several temporal events and across several locations. The proposed framework implements a novel distant supervision approach designed specifically to generate wellbeing-labeled datasets. In addition, it implements a wellbeing prediction model trained on contextualized sentence embeddings using BERT. Wellbeing predictions are visualized using several spatiotemporal analytics that can support decision-makers in gauging the impact of several government decisions and temporal events on the public, aiding in improving the decision-making process. Empirical experiments evaluate the effectiveness of the proposed distant supervision approach, the prediction model, and the utility of the produced analytics in gauging the public wellbeing status in a specific context.
Tài liệu tham khảo
Allen J, Cotter-Roberts A, Kadel R, Hughes K, Dyakova M (2021) COVID-19 impact on financial security: evidence from the National Public Engagement Survey in Wales. Eur J Public Health. https://doi.org/10.1093/eurpub/ckab165.324
Almouzini S, Khemakhem M, Alageel A (2019) Detecting Arabic depressed users from twitter data. Procedia Comput Sci 163:257–265. https://doi.org/10.1016/j.procs.2019.12.107
Alvarez-Jimenez M, Murray G, McLeod H, Allan S, Van Dam L, Rietstra S, Van der Drift E, Jan M, Stams GJ, Van der Mei R, Mahfoud M, Popma A, Schlossberg E, Pentland A, Reid TG (2019) Can an emoji a day keep the doctor away? An explorative mixed-methods feasibility study to develop a self-help app for youth with mental health problems. Psychiatry 10:593. https://doi.org/10.3389/fpsyt.2019.00593
Boon-Itt S, Skunkan Y (2020) Public perception of the COVID-19 pandemic on twitter: sentiment analysis and topic modeling study. JMIR Public Health Surveill 6(4):e21978. https://doi.org/10.2196/21978
Branco P, Torgo L, & Ribeiro R (2015) A survey of predictive modelling under imbalanced distributions
Bustos VP, Comer CD, Manstein SM, Laikhter E, Shiah E, Xun H, Lee BT, Lin SJ (2022) Twitter voices: twitter users’ sentiments and emotions about COVID-19 vaccination within the United States. Eur J Environ Public Health 6(1):em0096. https://doi.org/10.21601/EJEPH/11499
Chatterjee A, Narahari KN, Joshi M, & Agrawal P (2019) SemEval-2019 task 3: EmoContext contextual emotion detection in text. In: NAACL HLT 2019 - international workshop on semantic evaluation, SemEval 2019, proceedings of the 13th workshop, pp. 39–48. Doi: https://doi.org/10.18653/V1/S19-2005
Chen E, Lerman K, Ferrara E (2020) Tracking social media discourse about the COVID-19 pandemic: development of a public coronavirus twitter data set. JMIR Public Health Surveill. https://doi.org/10.2196/19273
Chintalapudi N, Battineni G, Amenta F (2021) Sentimental analysis of COVID-19 tweets using deep learning models. Infect Dis Rep 13(2):329. https://doi.org/10.3390/IDR13020032
De Choudhury M, Gamon M, Counts S, & Horvitz E (2013) Predicting depression via social media. In: Proceedings of the 7th international conference on weblogs and social media, ICWSM 2013, pp. 128–137
Coppersmith G, Dredze M, & Harman C (2015) Quantifying mental health signals in twitter. pp. 51–60. Doi: https://doi.org/10.3115/V1/W14-3207
Devlin J, Chang M-W, Lee K, Google KT, & Language AI (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the north, pp. 4171–4186. doi: https://doi.org/10.18653/V1/N19-1423
Dubey AD (2020) Twitter sentiment analysis during COVID-19 outbreak. SSRN Electron J. https://doi.org/10.2139/SSRN.3572023
Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern Part C Appl Rev 42(4):463–484. https://doi.org/10.1109/TSMCC.2011.2161285
Guntuku SC, Yaden DB, Kern ML, Ungar LH, Eichstaedt JC (2017) Detecting depression and mental illness on social media: an integrative review. Curr Opin Behav Sci 18:43–49. https://doi.org/10.1016/j.cobeha.2017.07.005
Orabi AH, Buddhitha P, Orabi MH, & Inkpen D (2018) Deep learning for depression detection of twitter users. Aclweb.Org, pp. 88–97. Doi: https://doi.org/10.18653/v1/w18-0609
Inui T, Umesawa Y, Yamamoto M (2013) Complaint sentence detection via automatic training data generation using sentiment lexicons and context coherence. J Nat Lang Process 20(5):683–705. https://doi.org/10.5715/jnlp.20.683
Ismail HM, Belkhouche B, Zaki N (2018) Semantic Twitter sentiment analysis based on a fuzzy thesaurus. Soft Comput 22(18):6011–6024. https://doi.org/10.1007/s00500-017-2994-8
Jones S, Murphy F, Edwards M, James J (2008) Doing things differently: advantages and disadvantages of Web questionnaires. Nurse Res 15(4):15–26. https://doi.org/10.7748/NR2008.07.15.4.15.C6658
Khaledi M, Haghighatdoost F, Feizi A, Aminorroaya A (2019) The prevalence of comorbid depression in patients with type 2 diabetes: an updated systematic review and meta-analysis on huge number of observational studies. Acta Diabetologica 56(6):631–650. https://doi.org/10.1007/S00592-019-01295-9
Kleinberg B, Vegt I van der, & Mozes M (2020) Measuring emotions in the COVID-19 real world worry dataset. https://aclanthology.org/2020.nlpcovid19-acl.11
Krendl AC, Perry BL (2021) The impact of sheltering in place during the COVID-19 pandemic on older adults’ social and mental well-being. J Gerontol Ser B 76(2):e53–e58. https://doi.org/10.1093/GERONB/GBAA110
Kydros D, Argyropoulou M, Vrana V (2021) A content and sentiment analysis of greek tweets during the pandemic. Sustainability 13(11):6150. https://doi.org/10.3390/SU13116150
Li S, Wang Y, Xue J, Zhao N, Zhu T (2020) The impact of covid-19 epidemic declaration on psychological consequences: a study on active weibo users. Int J Environ Res Public Health 17(6):2032. https://doi.org/10.3390/ijerph17062032
Li X, Zhou M, Wu J, Yuan A, Wu F, & Li J (2020b) Analyzing COVID-19 on online social media: trends, sentiments and emotions
Liu X-Y, Wu J, Zhou Z-H, Member S (2009) Exploratory undersampling for class-imbalance learning. Cybernetics 39(2):539. https://doi.org/10.1109/TSMCB.2008.2007853
Lustberg L, Reynolds CF (2000) Depression and insomnia: questions of cause and effect. Sleep Med Rev 4(3):253–262. https://doi.org/10.1053/smrv.1999.0075
Mohammad SM, Turney PD (2013) Crowdsourcing a word-emotion association lexicon. Comput Intell 29(3):436–465. https://doi.org/10.1111/j.1467-8640.2012.00460.x
Park G, Andrew Schwartz H, Eichstaedt JC, Kern ML, Kosinski M, Stillwell DJ, Ungar LH, Seligman MEP (2015) Automatic personality assessment through social media language. J Pers Soc Psychol 108(6):934–952. https://doi.org/10.1037/pspp0000020
Patrick SW, Henkhaus LE, Zickafoose JS, Lovell K, Halvorson A, Loch S, Letterie M, Davis MM (2020) Well-being of parents and children during the COVID-19 pandemic: a national survey. Pediatrics 146(4):e2020016824. https://doi.org/10.1542/PEDS.2020-016824
Pennebaker JW, Mehl MR, Niederhoffer KG (2003) Psychological aspects of natural language use: our words, our selves. Annu Rev Psychol 54(1):547–577. https://doi.org/10.1146/annurev.psych.54.101601.145041
Pennebaker JW, Booth RJ, Boyd RL, & Francis ME (n.d.) Linguistic inquiry and word count: LIWC2015 operator’s manual. In downloads.liwc.net.s3.amazonaws
Powers DMW (2015) What the F-measure doesn’t measure: features, flaws, fallacies and fixes
Reece AG, Reagan AJ, Lix KLM, Dodds PS, Danforth CM, Langer EJ (2016) Forecasting the onset and course of mental illness with Twitter data. Sci Rep 7(1):1–11
Resnik P, Garron A, & Resnik R (2013) Using topic modeling to improve prediction of neuroticism and depression in college students. In: EMNLP 2013 - 2013 conference on empirical methods in natural language processing, proceedings of the conference, pp. 1348–1353
Resnik P, Armstrong W, Claudino L, Nguyen T, Nguyen V-A, & Boyd-Graber J (2015) Beyond LDA: exploring supervised topic modeling for depression-related language in twitter. pp. 99–107. Doi: https://doi.org/10.3115/v1/w15-1212
Samuel J, Nawaz Ali GG, Rahman MM, Esawi E, & Samuel Y (n.d.). COVID-19 public sentiment insights and machine learning for tweets classification. Doi: https://doi.org/10.3390/info11060314
Scheuer C, Boot E, Carse N, Clardy A, Gallagher J, Heck S, Marron S, Martinez-Alvarez L, Masarykova D, Mcmillan P, Murphy F, Steel E, Ekdom H Van, & Vecchione H (2020) Measuring emotions in the COVID-19 real world worry dataset. Physical Education and Sport for Children and Youth with Special Needs Researches – Best Practices – Situation, pp. 343–354
Schwartz H, Eichstaedt J, Kern M, Park G, Sap M, Stillwell D, Kosinski M, & Ungar L (2014) Towards assessing changes in degree of depression through Facebook. In: Proceedings of the workshop on computational linguistics and clinical psychology: from linguistic signal to clinical reality
Shahriarirad R, Erfani A, Ranjbar K, Bazrafshan A, Mirahmadizadeh A (2021) The mental health impact of COVID-19 outbreak: a Nationwide Survey in Iran. Int J Mental Health Syst. https://doi.org/10.1186/S13033-021-00445-3
Shetty NP, Muniyal B, Anand A, Kumar S, Prabhu S (2020) Predicting depression using deep learning and ensemble algorithms on raw twitter data. Int J Electr Comput Eng 10(4):3751–3756. https://doi.org/10.11591/ijece.v10i4.pp3751-3756
Son C, Hegde S, Smith A, Wang X, Sasangohar F (2020) Effects of COVID-19 on college students’ mental health in the United States: interview survey study. J Med Internet Res 22(9):14. https://doi.org/10.2196/21279
Tausczik YR, Pennebaker JW (2010) The psychological meaning of words: LIWC and computerized text analysis methods. J Lang Soc Psychol 29(1):24–54. https://doi.org/10.1177/0261927X09351676
Thapa S, Sotang N, Adhikari J, Ghimire A, Limbu AK, Joshi A, Adhikari S (2020) Impact of COVID-19 lockdown on agriculture education in Nepal: an Online survey. Pedagog Res. https://doi.org/10.29333/pr/8465
Tsugawa S, Mogi Y, Kikuchi Y, Kishino F, Fujita K, Itoh Y, Ohsaki H (2013) On estimating depressive tendencies of Twitter users utilizing their tweet data. Proc IEEE Virtual Real. https://doi.org/10.1109/VR.2013.6549431
Tsugawa S, Kikuchi Y, Kishino F, Nakajima K, Itoh Y, & Ohsaki H (2015). Recognizing depression from twitter activity. In: Conference on human factors in computing systems - proceedings, 2015-April, 3187–3196. Doi: https://doi.org/10.1145/2702123.2702280
VanderWeele TJ, Fulks J, Plake JF, Lee MT (2021) National well-being measures before and during the COVID-19 pandemic in online samples. J Gen Intern Med 36(1):248–250. https://doi.org/10.1007/S11606-020-06274-3/TABLES/2
Wang C, Pan R, Wan X, Tan Y, Xu L, Ho CS, Ho RC (2020) Immediate psychological responses and associated factors during the initial stage of the 2019 coronavirus disease (COVID-19) epidemic among the general population in China. Int J Environ Res Public Health 17(5):1729. https://doi.org/10.3390/ijerph17051729
Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag 13(3):55–75. https://doi.org/10.1109/MCI.2018.2840738
Zhou J, Liu L, Xue P, Yang X, Tang X (2020) Mental health response to the COVID-19 outbreak in China. Am J Psychiatry 177(7):574–575. https://doi.org/10.1176/Appi.Ajp.2020.20030304